{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/read-json","entry":"read_json","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":250,"n_papers_ran":138,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":173,"n_samples_ran":83,"n_samples_fingerprinted":1,"n_places":262,"n_places_pointer_only":109,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":25,"ran_fixture":0,"ran":57,"unverified":90},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.15657","paper":"/paper/arxiv-2609-15657","title":"Predictive Likelihood Ratios for Language Model Watermark Detection","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"MaStatLab/PLRWatermark","path":"code/check_manuscript_tables.py","file_url":"https://github.com/MaStatLab/PLRWatermark/blob/HEAD/code/check_manuscript_tables.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"905fbfaea546ab77","mcp_get_code":{"code_sha256":"905fbfaea546ab77"}},{"arxiv_id":"2609.13237","paper":"/paper/arxiv-2609-13237","title":"Occlusal Geometry in Closed Form for Orthodontic Report Generation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"GIND123/ODIN_toothfairy4","path":"submission/inference.py","file_url":"https://github.com/GIND123/ODIN_toothfairy4/blob/HEAD/submission/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf012a7a2172e41a","mcp_get_code":{"code_sha256":"cf012a7a2172e41a"}},{"arxiv_id":"2609.12735","paper":"/paper/arxiv-2609-12735","title":"Physics-Guided Synthetic High-Frequency Ultrasound Generation for Skin Layer Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Finn-02/synthetic-hfus-skin-layer-segmentation","path":"code/make_sample.py","file_url":"https://github.com/Finn-02/synthetic-hfus-skin-layer-segmentation/blob/HEAD/code/make_sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"546bf32bcbbbce33","mcp_get_code":{"code_sha256":"546bf32bcbbbce33"}},{"arxiv_id":"2609.02133","paper":"/paper/arxiv-2609-02133","title":"EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"18277390221/EmoStance","path":"src/latent_stance_control/data.py","file_url":"https://github.com/18277390221/EmoStance/blob/HEAD/src/latent_stance_control/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7e52bef516b48b7","mcp_get_code":{"code_sha256":"f7e52bef516b48b7"}},{"arxiv_id":"2609.00918","paper":"/paper/arxiv-2609-00918","title":"RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"ZhongruChen/RPCBench","path":"src/step2_runner/_runner_common.py","file_url":"https://github.com/ZhongruChen/RPCBench/blob/HEAD/src/step2_runner/_runner_common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e68ad43a94bd7c9","mcp_get_code":{"code_sha256":"6e68ad43a94bd7c9"}},{"arxiv_id":"2609.00787","paper":"/paper/arxiv-2609-00787","title":"StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"thunlp/StudyBench","path":"filter/build_kp_guidance.py","file_url":"https://github.com/thunlp/StudyBench/blob/HEAD/filter/build_kp_guidance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"827fdd17ad5f2006","mcp_get_code":{"code_sha256":"827fdd17ad5f2006"}},{"arxiv_id":"2609.00787","paper":"/paper/arxiv-2609-00787","title":"StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"thunlp/StudyBench","path":"filter/build_targeted_guidance.py","file_url":"https://github.com/thunlp/StudyBench/blob/HEAD/filter/build_targeted_guidance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c12a8c71b4ffe271","mcp_get_code":{"code_sha256":"c12a8c71b4ffe271"}},{"arxiv_id":"2608.25655","paper":"/paper/arxiv-2608-25655","title":"Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LordTARN1SHED/SCALE-QA","path":"tsim_reference/src/eval/original_main_runner.py","file_url":"https://github.com/LordTARN1SHED/SCALE-QA/blob/HEAD/tsim_reference/src/eval/original_main_runner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2e822b681e022e86","mcp_get_code":{"code_sha256":"2e822b681e022e86"}},{"arxiv_id":"2608.25592","paper":"/paper/arxiv-2608-25592","title":"A Hierarchical Synergistic Deep Learning Framework Integrating Composition, Structure, and Ionic Transport for Solid-State Electrolyte Discovery","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"dhw059/MatCascade","path":"src/matcascade/io.py","file_url":"https://github.com/dhw059/MatCascade/blob/HEAD/src/matcascade/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8f6b001a42f48b78","mcp_get_code":{"code_sha256":"8f6b001a42f48b78"}},{"arxiv_id":"2607.26887","paper":"/paper/arxiv-2607-26887","title":"Conformalized Rate-Adaptive Sensing","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"jiawei-yang05/Conformalized_Rate_Adaptive_Sensing","path":"src/trajectory_cache.py","file_url":"https://github.com/jiawei-yang05/Conformalized_Rate_Adaptive_Sensing/blob/HEAD/src/trajectory_cache.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5afba1901d89e933","mcp_get_code":{"code_sha256":"5afba1901d89e933"}},{"arxiv_id":"2607.25886","paper":"/paper/arxiv-2607-25886","title":"RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"evolvent-ai/RSIBench-Data","path":"runner/lib/validate_final_selection.py","file_url":"https://github.com/evolvent-ai/RSIBench-Data/blob/HEAD/runner/lib/validate_final_selection.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60fefa17bbe708f9","mcp_get_code":{"code_sha256":"60fefa17bbe708f9"}},{"arxiv_id":"2607.20430","paper":"/paper/arxiv-2607-20430","title":"LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"LLM-Instruct-at-UZH-Shared-Task-2026/Method","path":"src/utils.py","file_url":"https://github.com/LLM-Instruct-at-UZH-Shared-Task-2026/Method/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bea9270cfacd05d3","mcp_get_code":{"code_sha256":"bea9270cfacd05d3"}},{"arxiv_id":"2606.29920","paper":"/paper/arxiv-2606-29920","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"THU-KEG/RuVerBench","path":"code/run_judges/deepresearch_runner.py","file_url":"https://github.com/THU-KEG/RuVerBench/blob/HEAD/code/run_judges/deepresearch_runner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e12708d522e088bc","mcp_get_code":{"code_sha256":"e12708d522e088bc"}},{"arxiv_id":"2606.29920","paper":"/paper/arxiv-2606-29920","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"THU-KEG/RuVerBench","path":"code/validate_package.py","file_url":"https://github.com/THU-KEG/RuVerBench/blob/HEAD/code/validate_package.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6c35031a84767386","mcp_get_code":{"code_sha256":"6c35031a84767386"}},{"arxiv_id":"2606.16535","paper":"/paper/arxiv-2606-16535","title":"Assessing Reliability of Symbol Detection in Concept Bottleneck Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Fuminides/cbm_sanity","path":"src/symbol_sanity/multihead.py","file_url":"https://github.com/Fuminides/cbm_sanity/blob/HEAD/src/symbol_sanity/multihead.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6194c9d9fea7914e","mcp_get_code":{"code_sha256":"6194c9d9fea7914e"}},{"arxiv_id":"2606.06333","paper":"/paper/arxiv-2606-06333","title":"Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"arshandalili/sasa","path":"common.py","file_url":"https://github.com/arshandalili/sasa/blob/HEAD/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e6084a3a5f0c07f","mcp_get_code":{"code_sha256":"7e6084a3a5f0c07f"}},{"arxiv_id":"2606.03980","paper":"/paper/arxiv-2606-03980","title":"Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Qwen-Applications/Skill-RM","path":"experiments/if_rewardbench/io_utils.py","file_url":"https://github.com/Qwen-Applications/Skill-RM/blob/HEAD/experiments/if_rewardbench/io_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8cd48bcf6faf53e6","mcp_get_code":{"code_sha256":"8cd48bcf6faf53e6"}},{"arxiv_id":"2605.30794","paper":"/paper/arxiv-2605-30794","title":"MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"xiaofengShi/MechVQA","path":"evaluation/mechvqa_eval/io_utils.py","file_url":"https://github.com/xiaofengShi/MechVQA/blob/HEAD/evaluation/mechvqa_eval/io_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3d41ae5289167635","mcp_get_code":{"code_sha256":"3d41ae5289167635"}},{"arxiv_id":"2605.26036","paper":"/paper/arxiv-2605-26036","title":"CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"inwind0212/CityRep","path":"urban_benchmark/io.py","file_url":"https://github.com/inwind0212/CityRep/blob/HEAD/urban_benchmark/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35b918ec22069b09","mcp_get_code":{"code_sha256":"35b918ec22069b09"}},{"arxiv_id":"2605.18591","paper":"/paper/arxiv-2605-18591","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"agent-lab/ICML2026-RAT","path":"utils/logger.py","file_url":"https://github.com/agent-lab/ICML2026-RAT/blob/HEAD/utils/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2605.11301","paper":"/paper/arxiv-2605-11301","title":"LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"LabRAI/LatentRouter","path":"src/latentrouter/io.py","file_url":"https://github.com/LabRAI/LatentRouter/blob/HEAD/src/latentrouter/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"578cfc781460c39a","mcp_get_code":{"code_sha256":"578cfc781460c39a"}},{"arxiv_id":"2605.08110","paper":"/paper/arxiv-2605-08110","title":"BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"AGI-Edgerunners/LLM-Adapters","path":"dataset/mawps/data_process.py","file_url":"https://github.com/AGI-Edgerunners/LLM-Adapters/blob/HEAD/dataset/mawps/data_process.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1266012e186b82e8","mcp_get_code":{"code_sha256":"1266012e186b82e8"}},{"arxiv_id":"2604.20043","paper":"/paper/arxiv-2604-20043","title":"TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Einsam1819/TriEx","path":"experiments/exp3a_oracle/3A_Ex.py","file_url":"https://github.com/Einsam1819/TriEx/blob/HEAD/experiments/exp3a_oracle/3A_Ex.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53f776d10872e81a","mcp_get_code":{"code_sha256":"53f776d10872e81a"}},{"arxiv_id":"2604.16665","paper":"/paper/arxiv-2604-16665","title":"CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"aaniksahaa/CBRS","path":"util.py","file_url":"https://github.com/aaniksahaa/CBRS/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b160d5084bf25c8","mcp_get_code":{"code_sha256":"8b160d5084bf25c8"}},{"arxiv_id":"2604.06834","paper":"/paper/arxiv-2604-06834","title":"On the Step Length Confounding in LLM Reasoning Data Selection","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wangbing1416/ASLEC","path":"batch_verify.py","file_url":"https://github.com/wangbing1416/ASLEC/blob/HEAD/batch_verify.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23fc7700a46c9d7a","mcp_get_code":{"code_sha256":"23fc7700a46c9d7a"}},{"arxiv_id":"2603.26680","paper":"/paper/arxiv-2603-26680","title":"AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ThisIsCosine/AlpsBench","path":"src/benchmark/data.py","file_url":"https://github.com/ThisIsCosine/AlpsBench/blob/HEAD/src/benchmark/data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa52501efd960421","mcp_get_code":{"code_sha256":"fa52501efd960421"}},{"arxiv_id":"2603.09714","paper":"/paper/arxiv-2603-09714","title":"MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"danielqwer/MUGEN","path":"evaluation/llm_judge.py","file_url":"https://github.com/danielqwer/MUGEN/blob/HEAD/evaluation/llm_judge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2362958b7e6a9591","mcp_get_code":{"code_sha256":"2362958b7e6a9591"}},{"arxiv_id":"2602.21492","paper":"/paper/arxiv-2602-21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"StigLidu/GradAlign","path":"sort_jsonl.py","file_url":"https://github.com/StigLidu/GradAlign/blob/HEAD/sort_jsonl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7c336680bdbe7af1","mcp_get_code":{"code_sha256":"7c336680bdbe7af1"}},{"arxiv_id":"2602.18064","paper":"/paper/arxiv-2602-18064","title":"3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis","date":"2026-02-20","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"jinlab-imvr/3DMedAgent","path":"Final_Test/memory.py","file_url":"https://github.com/jinlab-imvr/3DMedAgent/blob/HEAD/Final_Test/memory.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"038caf67087da5e3","mcp_get_code":{"code_sha256":"038caf67087da5e3"}},{"arxiv_id":"2601.21064","paper":"/paper/arxiv-2601-21064","title":"Textual Equilibrium Propagation for Deep Compound AI Systems","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"MinghuiChen43/TEP","path":"src/tep/runtime/split_utils.py","file_url":"https://github.com/MinghuiChen43/TEP/blob/HEAD/src/tep/runtime/split_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b813f8c08247898","mcp_get_code":{"code_sha256":"9b813f8c08247898"}},{"arxiv_id":"2601.09693","paper":"/paper/arxiv-2601-09693","title":"Contrastive Geometric Learning Unlocks Unified Structure-and Ligand-Based Drug Design","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ml-jku/conglude","path":"conglude/utils/common.py","file_url":"https://github.com/ml-jku/conglude/blob/HEAD/conglude/utils/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"fdd45b188bfa8349","mcp_get_code":{"code_sha256":"fdd45b188bfa8349"}},{"arxiv_id":"2601.09233","paper":"/paper/arxiv-2601-09233","title":"GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zzy1127/GIFT","path":"utils/data_utils.py","file_url":"https://github.com/zzy1127/GIFT/blob/HEAD/utils/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd9ca8cdc6aa690d","mcp_get_code":{"code_sha256":"dd9ca8cdc6aa690d"}},{"arxiv_id":"2601.01280","paper":"/paper/arxiv-2601-01280","title":"Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AvatarMemory/UnifiedMem","path":"evals/halu_graph_eval.py","file_url":"https://github.com/AvatarMemory/UnifiedMem/blob/HEAD/evals/halu_graph_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02472179dd90321e","mcp_get_code":{"code_sha256":"02472179dd90321e"}},{"arxiv_id":"2510.13183","paper":"/paper/arxiv-2510-13183","title":"DSCD: Large Language Model Detoxification with Self-Constrained Decoding","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"ZHANGJINKUI/DSCD","path":"run_dscd.py","file_url":"https://github.com/ZHANGJINKUI/DSCD/blob/HEAD/run_dscd.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2509.19003","paper":"/paper/arxiv-2509-19003","title":"Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"baaivision/CoS","path":"eval/mathvista/utilities.py","file_url":"https://github.com/baaivision/CoS/blob/HEAD/eval/mathvista/utilities.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"2509.16598","paper":"/paper/arxiv-2509-16598","title":"PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"hoeng4/PruneCD","path":"2_benchmark/triviaqa_util.py","file_url":"https://github.com/hoeng4/PruneCD/blob/HEAD/2_benchmark/triviaqa_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6622a686d1cedd19","mcp_get_code":{"code_sha256":"6622a686d1cedd19"}},{"arxiv_id":"2508.20700","paper":"/paper/arxiv-2508-20700","title":"Generative Annotation for ASR Named Entity Correction","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Amiannn/Dancer","path":"src/utils.py","file_url":"https://github.com/Amiannn/Dancer/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e62a446dcd7ecade","mcp_get_code":{"code_sha256":"e62a446dcd7ecade"}},{"arxiv_id":"2508.13037","paper":"/paper/arxiv-2508-13037","title":"Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Xinhe-Li/LoRID","path":"src/utils/file_utils.py","file_url":"https://github.com/Xinhe-Li/LoRID/blob/HEAD/src/utils/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"11d0beec8ee694e7","mcp_get_code":{"code_sha256":"11d0beec8ee694e7"}},{"arxiv_id":"2508.00518","paper":"/paper/arxiv-2508-00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"LaVi-Lab/EgoMask","path":"evaluation/common_utils.py","file_url":"https://github.com/LaVi-Lab/EgoMask/blob/HEAD/evaluation/common_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2362958b7e6a9591","mcp_get_code":{"code_sha256":"2362958b7e6a9591"}},{"arxiv_id":"2507.04701","paper":"/paper/xiyan-sql-a-novel-multi-generator-framework","title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","date":"2025-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XGenerationLab/M-Schema","path":"utils.py","file_url":"https://github.com/XGenerationLab/M-Schema/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aca120d846c7a603","mcp_get_code":{"code_sha256":"aca120d846c7a603"}},{"arxiv_id":"2506.12618","paper":"/paper/openunlearning-accelerating-llm-unlearning","title":"OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics","date":"2025-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"locuslab/open-unlearning","path":"community/methods/AltPO/generate.py","file_url":"https://github.com/locuslab/open-unlearning/blob/HEAD/community/methods/AltPO/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e72fd5056dda43a","mcp_get_code":{"code_sha256":"6e72fd5056dda43a"}},{"arxiv_id":"2506.10055","paper":"/paper/taskcraft-automated-generation-of-agentic","title":"TaskCraft: Automated Generation of Agentic Tasks","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oppo-personalai/taskcraft","path":"taskcraft/utils.py","file_url":"https://github.com/oppo-personalai/taskcraft/blob/HEAD/taskcraft/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47cc6a8298b927aa","mcp_get_code":{"code_sha256":"47cc6a8298b927aa"}},{"arxiv_id":"2506.02397","paper":"/paper/othink-r1-intrinsic-fast-slow-thinking-mode","title":"OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agenticir-lab/othink-r1","path":"OThinkR1Construct/construct/DataConstruct_3_Prune.py","file_url":"https://github.com/agenticir-lab/othink-r1/blob/HEAD/OThinkR1Construct/construct/DataConstruct_3_Prune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d4eb3b246cf389d","mcp_get_code":{"code_sha256":"0d4eb3b246cf389d"}},{"arxiv_id":"2505.18822","paper":"/paper/adactrl-towards-adaptive-and-controllable","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeying1019/adactrl","path":"utils/data_utils.py","file_url":"https://github.com/joeying1019/adactrl/blob/HEAD/utils/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dd9ca8cdc6aa690d","mcp_get_code":{"code_sha256":"dd9ca8cdc6aa690d"}},{"arxiv_id":"2505.18726","paper":"/paper/audio-geolocation-a-natural-sounds-benchmark","title":"Audio Geolocation: A Natural Sounds Benchmark","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvl-umass/nat-sound2loc-code","path":"src/utils.py","file_url":"https://github.com/cvl-umass/nat-sound2loc-code/blob/HEAD/src/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2505.18673","paper":"/paper/cross-lingual-pitfalls-automatic-probing","title":"Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xzx34/Cross-Lingual-Pitfalls","path":"visualization.py","file_url":"https://github.com/xzx34/Cross-Lingual-Pitfalls/blob/HEAD/visualization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee50a40e401c2b10","mcp_get_code":{"code_sha256":"ee50a40e401c2b10"}},{"arxiv_id":"2505.13886","paper":"/paper/code2logic-game-code-driven-data-synthesis","title":"Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tongjingqi/code2logic","path":"src/Code_for_text_data_derivative/PyramidChess_to_text_que.py","file_url":"https://github.com/tongjingqi/code2logic/blob/HEAD/src/Code_for_text_data_derivative/PyramidChess_to_text_que.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8bce38b2e33c7d8d","mcp_get_code":{"code_sha256":"8bce38b2e33c7d8d"}},{"arxiv_id":"2505.13886","paper":"/paper/code2logic-game-code-driven-data-synthesis","title":"Code2Logic: Game-Code-Driven Data Synthesis for Enhancing VLMs General Reasoning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tongjingqi/code2logic","path":"src/Code_for_text_data_derivative/convert_text_data.py","file_url":"https://github.com/tongjingqi/code2logic/blob/HEAD/src/Code_for_text_data_derivative/convert_text_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"968481e75edb953d","mcp_get_code":{"code_sha256":"968481e75edb953d"}},{"arxiv_id":"2504.05458","paper":"/paper/optimizing-4d-gaussians-for-dynamic-scene","title":"Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images","date":"2025-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvsp-lab/iclr2025_3d-mom","path":"train_motion.py","file_url":"https://github.com/cvsp-lab/iclr2025_3d-mom/blob/HEAD/train_motion.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1d2e6815b7f90e1","mcp_get_code":{"code_sha256":"c1d2e6815b7f90e1"}},{"arxiv_id":"2503.17267","paper":"/paper/physical-plausibility-aware-trajectory","title":"Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment","date":"2025-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ImIntheMiddle/EmLoco","path":"social-transmotion/load_jrdb_3dpose.py","file_url":"https://github.com/ImIntheMiddle/EmLoco/blob/HEAD/social-transmotion/load_jrdb_3dpose.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2362958b7e6a9591","mcp_get_code":{"code_sha256":"2362958b7e6a9591"}},{"arxiv_id":"2503.06881","paper":"/paper/resmoe-space-efficient-compression-of-mixture","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"idea-isail-lab-uiuc/resmoe","path":"mixtral/resmoe_mixtral/convert_mixtral_weights_to_hf.py","file_url":"https://github.com/idea-isail-lab-uiuc/resmoe/blob/HEAD/mixtral/resmoe_mixtral/convert_mixtral_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2502.18906","paper":"/paper/vem-environment-free-exploration-for-training","title":"VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/gui-agent-rl","path":"utils.py","file_url":"https://github.com/microsoft/gui-agent-rl/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf2b970192f06b31","mcp_get_code":{"code_sha256":"bf2b970192f06b31"}},{"arxiv_id":"2502.05567","paper":"/paper/2502-05567","title":"ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data","date":"2025-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiaoyangLiu-sjtu/ATLAS","path":"utils.py","file_url":"https://github.com/XiaoyangLiu-sjtu/ATLAS/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8bce38b2e33c7d8d","mcp_get_code":{"code_sha256":"8bce38b2e33c7d8d"}},{"arxiv_id":"2502.05374","paper":"/paper/towards-llm-unlearning-resilient-to","title":"Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optml-group/unlearn-smooth","path":"MUSE/utils.py","file_url":"https://github.com/optml-group/unlearn-smooth/blob/HEAD/MUSE/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16d37f44bb5f7c70","mcp_get_code":{"code_sha256":"16d37f44bb5f7c70"}},{"arxiv_id":"2502.02384","paper":"/paper/stair-improving-safety-alignment-with","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","date":"2025-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/stair","path":"src/utils.py","file_url":"https://github.com/thu-ml/stair/blob/HEAD/src/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2501.15595","paper":"/paper/sedareval-automated-evaluation-using-self","title":"SedarEval: Automated Evaluation using Self-Adaptive Rubrics","date":"2025-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wwn1233/sedareval","path":"src/infer.py","file_url":"https://github.com/wwn1233/sedareval/blob/HEAD/src/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d6afcb95ae21bea2","mcp_get_code":{"code_sha256":"d6afcb95ae21bea2"}},{"arxiv_id":"2501.12835","paper":"/paper/adaptive-retrieval-without-self-knowledge","title":"Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home","date":"2025-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"s-nlp/AdaRAGUE","path":"SeaKR/eval_utils.py","file_url":"https://github.com/s-nlp/AdaRAGUE/blob/HEAD/SeaKR/eval_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6017b412458e24f4","mcp_get_code":{"code_sha256":"6017b412458e24f4"}},{"arxiv_id":"2501.11425","paper":"/paper/agent-r-training-language-model-agents-to","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","date":"2025-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/agent-r","path":"mcts_utils/llm_server.py","file_url":"https://github.com/bytedance/agent-r/blob/HEAD/mcts_utils/llm_server.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fc1433d5441ae6d6","mcp_get_code":{"code_sha256":"fc1433d5441ae6d6"}},{"arxiv_id":"2412.11803","paper":"/paper/ualign-leveraging-uncertainty-estimations-for","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amourwaltz/ualign","path":"code/utils.py","file_url":"https://github.com/amourwaltz/ualign/blob/HEAD/code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8e230efd4b919022","mcp_get_code":{"code_sha256":"8e230efd4b919022"}},{"arxiv_id":"2412.11142","paper":"/paper/ad-llm-benchmarking-large-language-models-for","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","date":"2024-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"usc-fortis/ad-llm","path":"utils.py","file_url":"https://github.com/usc-fortis/ad-llm/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"772778f25f3bd45f","mcp_get_code":{"code_sha256":"772778f25f3bd45f"}},{"arxiv_id":"2412.09243","paper":"/paper/sprec-leveraging-self-play-to-debias","title":"SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"regionch/sprec","path":"baselines/Re-weighting/RW_SFT.py","file_url":"https://github.com/regionch/sprec/blob/HEAD/baselines/Re-weighting/RW_SFT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ae7eaf0f2d85dfdf","mcp_get_code":{"code_sha256":"ae7eaf0f2d85dfdf"}},{"arxiv_id":"2412.03017","paper":"/paper/pixel-level-and-semantic-level-adjustable","title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csslc/pisa-sr","path":"ram/models/utils.py","file_url":"https://github.com/csslc/pisa-sr/blob/HEAD/ram/models/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e1cf6464da33ec0c","mcp_get_code":{"code_sha256":"e1cf6464da33ec0c"}},{"arxiv_id":"2411.10275","paper":"/paper/4dpv-4d-pet-from-videos-by-coarse-to-fine-non","title":"4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smontode24/4dpv","path":"dataloader/vidbase.py","file_url":"https://github.com/smontode24/4dpv/blob/HEAD/dataloader/vidbase.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"150e51a9dd40d785","mcp_get_code":{"code_sha256":"150e51a9dd40d785"}},{"arxiv_id":"2410.23223","paper":"/paper/comal-a-convergent-meta-algorithm-for","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-nlp/comal","path":"utils.py","file_url":"https://github.com/yale-nlp/comal/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ab6ea4de9ffa9aa","mcp_get_code":{"code_sha256":"1ab6ea4de9ffa9aa"}},{"arxiv_id":"2410.21662","paper":"/paper/f-po-generalizing-preference-optimization","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minkaixu/fpo","path":"src/api.py","file_url":"https://github.com/minkaixu/fpo/blob/HEAD/src/api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2912713a5377070","mcp_get_code":{"code_sha256":"f2912713a5377070"}},{"arxiv_id":"2410.17885","paper":"/paper/r-cot-reverse-chain-of-thought-problem","title":"R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dle666/r-cot","path":"MathVista_eval/utilities.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/utilities.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"2410.16454","paper":"/paper/does-your-llm-truly-unlearn-an-embarrassingly","title":"Catastrophic Failure of LLM Unlearning via Quantization","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzwjames/FailureLLMUnlearning","path":"utils.py","file_url":"https://github.com/zzwjames/FailureLLMUnlearning/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cdb6bfa6b75a7e0","mcp_get_code":{"code_sha256":"8cdb6bfa6b75a7e0"}},{"arxiv_id":"2410.14488","paper":"/paper/ant-adaptive-noise-schedule-for-time-series","title":"ANT: Adaptive Noise Schedule for Time Series Diffusion Models","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seunghan96/ANT","path":"ANT_utils.py","file_url":"https://github.com/seunghan96/ANT/blob/HEAD/ANT_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cb76168b3aef79f0","mcp_get_code":{"code_sha256":"cb76168b3aef79f0"}},{"arxiv_id":"2410.11842","paper":"/paper/moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-yuangroup/chat-univi","path":"ChatUniVi/eval/model_video_qa.py","file_url":"https://github.com/pku-yuangroup/chat-univi/blob/HEAD/ChatUniVi/eval/model_video_qa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c578a6846674ff45","mcp_get_code":{"code_sha256":"c578a6846674ff45"}},{"arxiv_id":"2410.10093","paper":"/paper/how-to-leverage-demonstration-data-in","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/GSIL","path":"gsil/combine.py","file_url":"https://github.com/tengxiao1/GSIL/blob/HEAD/gsil/combine.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d15e65c12916d1f1","mcp_get_code":{"code_sha256":"d15e65c12916d1f1"}},{"arxiv_id":"2410.09584","paper":"/paper/toward-general-instruction-following","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongguanting/FollowRAG","path":"FollowRAG/utils/util.py","file_url":"https://github.com/dongguanting/FollowRAG/blob/HEAD/FollowRAG/utils/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"621bb80a81f5a607","mcp_get_code":{"code_sha256":"621bb80a81f5a607"}},{"arxiv_id":"2410.08081","paper":"/paper/packing-analysis-packing-is-more-appropriate","title":"Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shuhewang1998/packing-analysis","path":"transfer_data.py","file_url":"https://github.com/shuhewang1998/packing-analysis/blob/HEAD/transfer_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e77ca7986aa53f0","mcp_get_code":{"code_sha256":"6e77ca7986aa53f0"}},{"arxiv_id":"2410.02184","paper":"/paper/codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VichyTong/CodeJudge","path":"evaluation/model/convert_llama_weights_to_hf.py","file_url":"https://github.com/VichyTong/CodeJudge/blob/HEAD/evaluation/model/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2409.17504","paper":"/paper/haloscope-harnessing-unlabeled-llm","title":"HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deeplearning-wisc/haloscope","path":"llama_iti/convert_llama_weights_to_hf.py","file_url":"https://github.com/deeplearning-wisc/haloscope/blob/HEAD/llama_iti/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2409.16783","paper":"/paper/holistic-automated-red-teaming-for-large","title":"Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jc-ryan/holistic_automated_red_teaming","path":"utils.py","file_url":"https://github.com/jc-ryan/holistic_automated_red_teaming/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"46122ace162507f6","mcp_get_code":{"code_sha256":"46122ace162507f6"}},{"arxiv_id":"2409.13474","paper":"/paper/alternate-preference-optimization-for","title":"Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"molereddy/Alternate-Preference-Optimization","path":"generate.py","file_url":"https://github.com/molereddy/Alternate-Preference-Optimization/blob/HEAD/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e72fd5056dda43a","mcp_get_code":{"code_sha256":"6e72fd5056dda43a"}},{"arxiv_id":"2409.12346","paper":"/paper/simultaneous-music-separation-and-generation","title":"Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2024-09","title_source":"archive","repo":"karchkha/msg-ld","path":"src/utilities/tools.py","file_url":"https://github.com/karchkha/msg-ld/blob/HEAD/src/utilities/tools.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a42cc3d7c42a043","mcp_get_code":{"code_sha256":"8a42cc3d7c42a043"}},{"arxiv_id":"2409.02076","paper":"/paper/spinning-the-golden-thread-benchmarking-long","title":"LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs","date":"2024-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mozhu621/SGT","path":"Evalution/API_Openai.py","file_url":"https://github.com/mozhu621/SGT/blob/HEAD/Evalution/API_Openai.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bb6d8575edb075c","mcp_get_code":{"code_sha256":"6bb6d8575edb075c"}},{"arxiv_id":"2409.06706","paper":"/paper/discovering-long-term-effects-on-parameter","title":"SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daviddaiiiii/san-peft","path":"utils/io_utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/io_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02603976c91a1244","mcp_get_code":{"code_sha256":"02603976c91a1244"}},{"arxiv_id":"2409.00147","paper":"/paper/multimath-bridging-visual-and-mathematical","title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pengshuai-rin/multimath","path":"eval_mathvista/utilities.py","file_url":"https://github.com/pengshuai-rin/multimath/blob/HEAD/eval_mathvista/utilities.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"2408.15556","paper":"/paper/divide-conquer-and-combine-a-training-free","title":"Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DreamMr/HR-Bench","path":"dc2_code/dc2/utils.py","file_url":"https://github.com/DreamMr/HR-Bench/blob/HEAD/dc2_code/dc2/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad9de8bcc2a0e90f","mcp_get_code":{"code_sha256":"ad9de8bcc2a0e90f"}},{"arxiv_id":"2408.15545","paper":"/paper/scilitllm-how-to-adapt-llms-for-scientific","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dptech-corp/Uni-SMART","path":"SciLitLLM/sft/helper/dedup.py","file_url":"https://github.com/dptech-corp/Uni-SMART/blob/HEAD/SciLitLLM/sft/helper/dedup.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7daf38d1d71fe676","mcp_get_code":{"code_sha256":"7daf38d1d71fe676"}},{"arxiv_id":"2408.15545","paper":"/paper/scilitllm-how-to-adapt-llms-for-scientific","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dptech-corp/Uni-SMART","path":"SciLitLLM/sft/helper/infer_sft.py","file_url":"https://github.com/dptech-corp/Uni-SMART/blob/HEAD/SciLitLLM/sft/helper/infer_sft.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"953b99c2358aec7b","mcp_get_code":{"code_sha256":"953b99c2358aec7b"}},{"arxiv_id":"2408.13533","paper":"/paper/pandora-s-box-or-aladdin-s-lamp-a","title":"Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinyangwu/NoiserBench","path":"pal/scripts/aqua_eval.py","file_url":"https://github.com/jinyangwu/NoiserBench/blob/HEAD/pal/scripts/aqua_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f15228f88695710","mcp_get_code":{"code_sha256":"0f15228f88695710"}},{"arxiv_id":"2408.04284","paper":"/paper/llm-detectaive-a-tool-for-fine-grained","title":"LLM-DetectAIve: a Tool for Fine-Grained Machine-Generated Text Detection","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mbzuai-nlp/llm-detectaive","path":"pipeline/dataset.py","file_url":"https://github.com/mbzuai-nlp/llm-detectaive/blob/HEAD/pipeline/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"473de1e7bbe1fd4b","mcp_get_code":{"code_sha256":"473de1e7bbe1fd4b"}},{"arxiv_id":"2408.02657","paper":"/paper/2408-02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","date":"2024-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpha-vllm/lumina-mgpt","path":"lumina_mgpt/model/chameleon/convert_chameleon_weights_to_hf.py","file_url":"https://github.com/alpha-vllm/lumina-mgpt/blob/HEAD/lumina_mgpt/model/chameleon/convert_chameleon_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2407.19672","paper":"/paper/seallms-3-open-foundation-and-chat","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/seallms","path":"evaluation/vmlu/vmlu_run.py","file_url":"https://github.com/damo-nlp-sg/seallms/blob/HEAD/evaluation/vmlu/vmlu_run.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19386545b88c6839","mcp_get_code":{"code_sha256":"19386545b88c6839"}},{"arxiv_id":"2407.18940","paper":"/paper/litsearch-a-retrieval-benchmark-for","title":"LitSearch: A Retrieval Benchmark for Scientific Literature Search","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/litsearch","path":"utils/utils.py","file_url":"https://github.com/princeton-nlp/litsearch/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"266ec98878d442f8","mcp_get_code":{"code_sha256":"266ec98878d442f8"}},{"arxiv_id":"2407.16695","paper":"/paper/stress-testing-long-context-language-models","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ink-usc/lifelong-icl","path":"dataloader/incremental_task.py","file_url":"https://github.com/ink-usc/lifelong-icl/blob/HEAD/dataloader/incremental_task.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ae221496d4ff083","mcp_get_code":{"code_sha256":"0ae221496d4ff083"}},{"arxiv_id":"2407.12857","paper":"/paper/automated-peer-reviewing-in-paper-sea","title":"Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ecnu-sea/SEA","path":"pdf_parser/utils.py","file_url":"https://github.com/ecnu-sea/SEA/blob/HEAD/pdf_parser/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"978a80a8938ffcd3","mcp_get_code":{"code_sha256":"978a80a8938ffcd3"}},{"arxiv_id":"2407.12504","paper":"/paper/case2code-learning-inductive-reasoning-with","title":"Case2Code: Learning Inductive Reasoning with Synthetic Data","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"choosewhatulike/case2code","path":"api_call_util.py","file_url":"https://github.com/choosewhatulike/case2code/blob/HEAD/api_call_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad5f98bba0c21929","mcp_get_code":{"code_sha256":"ad5f98bba0c21929"}},{"arxiv_id":"2407.09007","paper":"/paper/benchmarking-language-model-creativity-a-case","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JHU-CLSP/NeoCoder","path":"src/evaluators/evaluation_utils.py","file_url":"https://github.com/JHU-CLSP/NeoCoder/blob/HEAD/src/evaluators/evaluation_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d9ca0a9bcc504189","mcp_get_code":{"code_sha256":"d9ca0a9bcc504189"}},{"arxiv_id":"2407.05551","paper":"/paper/read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/rewas","path":"utils.py","file_url":"https://github.com/naver-ai/rewas/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a42cc3d7c42a043","mcp_get_code":{"code_sha256":"8a42cc3d7c42a043"}},{"arxiv_id":"2406.18200","paper":"/paper/seed-accelerating-reasoning-tree-construction","title":"SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Linking-ai/SEED","path":"src/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/Linking-ai/SEED/blob/HEAD/src/llama_tree_attn/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2406.12288","paper":"/paper/an-investigation-of-neuron-activation-as-a","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dakingrai/ood-generalization-semantic-boundary-techniques","path":"evaluations/src/token_preprocessing.py","file_url":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques/blob/HEAD/evaluations/src/token_preprocessing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fde2a650a2455e30","mcp_get_code":{"code_sha256":"fde2a650a2455e30"}},{"arxiv_id":"2406.11375","paper":"/paper/boosting-scientific-concepts-understanding","title":"Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models?","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyuyuan/SCUA","path":"util_func.py","file_url":"https://github.com/siyuyuan/SCUA/blob/HEAD/util_func.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc1433d5441ae6d6","mcp_get_code":{"code_sha256":"fc1433d5441ae6d6"}},{"arxiv_id":"2406.11317","paper":"/paper/guicourse-from-general-vision-language-models","title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiye3/guicourse","path":"data_load.py","file_url":"https://github.com/yiye3/guicourse/blob/HEAD/data_load.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"61ec4f7400ef2dac","mcp_get_code":{"code_sha256":"61ec4f7400ef2dac"}},{"arxiv_id":"2406.09279","paper":"/paper/unpacking-dpo-and-ppo-disentangling-best","title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamishivi/easylm","path":"EasyLM/models/llama/convert_easylm_to_hf.py","file_url":"https://github.com/hamishivi/easylm/blob/HEAD/EasyLM/models/llama/convert_easylm_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2406.05761","paper":"/paper/the-biggen-bench-a-principled-benchmark-for","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prometheus-eval/prometheus-eval","path":"BiGGen-Bench/make_report.py","file_url":"https://github.com/prometheus-eval/prometheus-eval/blob/HEAD/BiGGen-Bench/make_report.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1266012e186b82e8","mcp_get_code":{"code_sha256":"1266012e186b82e8"}},{"arxiv_id":"2406.05317","paper":"/paper/lococo-dropping-in-convolutions-for-long","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/LoCoCo","path":"llama/convert_llama_weights_to_hf.py","file_url":"https://github.com/VITA-Group/LoCoCo/blob/HEAD/llama/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2406.04197","paper":"/paper/dice-detecting-in-distribution-contamination","title":"DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2405.19298","paper":"/paper/adaptive-image-quality-assessment-via","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Compare2Score","path":"q_align/model/convert_mplug_owl2_weight_to_hf.py","file_url":"https://github.com/Q-Future/Compare2Score/blob/HEAD/q_align/model/convert_mplug_owl2_weight_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2405.17220","paper":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlhf-v/rlhf-v","path":"eval/change_mmhal_predict_template.py","file_url":"https://github.com/rlhf-v/rlhf-v/blob/HEAD/eval/change_mmhal_predict_template.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2405.16273","paper":"/paper/m-3-gpt-an-advanced-multimodal-multitask","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","date":"2024-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luomingshuang/M3GPT","path":"m3gpt/utils.py","file_url":"https://github.com/luomingshuang/M3GPT/blob/HEAD/m3gpt/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"2405.13382","paper":"/paper/vtg-llm-integrating-timestamp-knowledge-into","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gyxxyg/vtg-llm","path":"utils/format_dvc.py","file_url":"https://github.com/gyxxyg/vtg-llm/blob/HEAD/utils/format_dvc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7aad81b5c188085c","mcp_get_code":{"code_sha256":"7aad81b5c188085c"}},{"arxiv_id":"2405.13053","paper":"/paper/meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","date":"2024-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paragonlight/meteor-of-lora","path":"base_model/llama/convert_llama_meteor_weights_to_hf.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/convert_llama_meteor_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2405.12617","paper":"/paper/quantifying-emergence-in-large-language","title":"Quantifying Semantic Emergence in Language Models","date":"2024-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zodiark-ch/emergence-of-llms","path":"GEMMA/utils.py","file_url":"https://github.com/zodiark-ch/emergence-of-llms/blob/HEAD/GEMMA/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"76791810a73ce23a","mcp_get_code":{"code_sha256":"76791810a73ce23a"}},{"arxiv_id":"2405.10640","paper":"/paper/comet-nft-price-prediction-with-wallet","title":"COMET: NFT Price Prediction with Wallet Profiling","date":null,"month_inferred_from_arxiv_id":"2024-05","title_source":"archive","repo":"GeminiLight/nft-data-collection-comet","path":"data_collection/nft_alchemy_scraper.py","file_url":"https://github.com/GeminiLight/nft-data-collection-comet/blob/HEAD/data_collection/nft_alchemy_scraper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"740eae14936cab18","mcp_get_code":{"code_sha256":"740eae14936cab18"}},{"arxiv_id":"2405.10640","paper":"/paper/comet-nft-price-prediction-with-wallet","title":"COMET: NFT Price Prediction with Wallet Profiling","date":null,"month_inferred_from_arxiv_id":"2024-05","title_source":"archive","repo":"GeminiLight/nft-data-collection-comet","path":"data_collection/nft_asset_querier.py","file_url":"https://github.com/GeminiLight/nft-data-collection-comet/blob/HEAD/data_collection/nft_asset_querier.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7b66e04d794c340","mcp_get_code":{"code_sha256":"e7b66e04d794c340"}},{"arxiv_id":"2405.06680","paper":"/paper/exploring-the-compositional-deficiency-of","title":"Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tongjingqi/MathTrap","path":"GPT4_eval/get_response_example.py","file_url":"https://github.com/tongjingqi/MathTrap/blob/HEAD/GPT4_eval/get_response_example.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0bb621c7242d2fbe","mcp_get_code":{"code_sha256":"0bb621c7242d2fbe"}},{"arxiv_id":"2405.05949","paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shi-labs/cumo","path":"cumo/eval/calculate_score.py","file_url":"https://github.com/shi-labs/cumo/blob/HEAD/cumo/eval/calculate_score.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"2404.18253","paper":"/paper/efficient-remote-sensing-with-harmonized","title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seekerhuang/harma","path":"models/model_retrieval.py","file_url":"https://github.com/seekerhuang/harma/blob/HEAD/models/model_retrieval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e1cf6464da33ec0c","mcp_get_code":{"code_sha256":"e1cf6464da33ec0c"}},{"arxiv_id":"2404.11553","paper":"/paper/quantifying-multilingual-performance-of-large","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lizh9885/language-ranker","path":"utils.py","file_url":"https://github.com/lizh9885/language-ranker/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f68b87da75ea3dd3","mcp_get_code":{"code_sha256":"f68b87da75ea3dd3"}},{"arxiv_id":"2404.11109","paper":"/paper/consistency-training-by-synthetic-question","title":"Consistency Training by Synthetic Question Generation for Conversational Question Answering","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HamedHematian/SynCQG","path":"utils.py","file_url":"https://github.com/HamedHematian/SynCQG/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ebd247765d3afd43","mcp_get_code":{"code_sha256":"ebd247765d3afd43"}},{"arxiv_id":"2404.04042","paper":"/paper/teaching-llama-a-new-language-through-cross","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tartunlp/llammas","path":"scripts/chat_data/instructions_to_chat.py","file_url":"https://github.com/tartunlp/llammas/blob/HEAD/scripts/chat_data/instructions_to_chat.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8bead2bc8cb5aff4","mcp_get_code":{"code_sha256":"8bead2bc8cb5aff4"}},{"arxiv_id":"2404.03539","paper":"/paper/is-clip-the-main-roadblock-for-fine-grained","title":"Is CLIP the main roadblock for fine-grained open-world perception?","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0be4cd21574acdc0","mcp_get_code":{"code_sha256":"0be4cd21574acdc0"}},{"arxiv_id":"2404.03539","paper":"/paper/is-clip-the-main-roadblock-for-fine-grained","title":"Is CLIP the main roadblock for fine-grained open-world perception?","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lorebianchi98/fg-clip","path":"src/utilities.py","file_url":"https://github.com/lorebianchi98/fg-clip/blob/HEAD/src/utilities.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5840bed4f36dd3fb","mcp_get_code":{"code_sha256":"5840bed4f36dd3fb"}},{"arxiv_id":"2404.03196","paper":"/paper/okay-let-s-do-this-modeling-event-coreference","title":"Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csu-signal/llama_cdcr","path":"convert_llama_weights_to_hf.py","file_url":"https://github.com/csu-signal/llama_cdcr/blob/HEAD/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2403.17710","paper":"/paper/optimization-based-prompt-injection-attack-to","title":"Optimization-based Prompt Injection Attack to LLM-as-a-Judge","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shijiawenwen/judgedeceiver","path":"experiments/case_study/evaluate_casestudy.py","file_url":"https://github.com/shijiawenwen/judgedeceiver/blob/HEAD/experiments/case_study/evaluate_casestudy.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bb6d8575edb075c","mcp_get_code":{"code_sha256":"6bb6d8575edb075c"}},{"arxiv_id":"2403.13372","paper":"/paper/llamafactory-unified-efficient-fine-tuning-of","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rcrossmeister/RLQG","path":"model/converter.py","file_url":"https://github.com/Rcrossmeister/RLQG/blob/HEAD/model/converter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"147f30501936b7f3","mcp_get_code":{"code_sha256":"147f30501936b7f3"}},{"arxiv_id":"2403.10145","paper":"/paper/rcooper-a-real-world-large-scale-dataset-for","title":"RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AIR-THU/DAIR-RCooper","path":"codes/ab3dmot_plugin/data_convert/coop_label_dair2kitti.py","file_url":"https://github.com/AIR-THU/DAIR-RCooper/blob/HEAD/codes/ab3dmot_plugin/data_convert/coop_label_dair2kitti.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4dd25e68caa95a28","mcp_get_code":{"code_sha256":"4dd25e68caa95a28"}},{"arxiv_id":"2402.17840","paper":"/paper/follow-my-instruction-and-spill-the-beans","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhentingqi/rag-privacy","path":"utils/helpers.py","file_url":"https://github.com/zhentingqi/rag-privacy/blob/HEAD/utils/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94371f783375881f","mcp_get_code":{"code_sha256":"94371f783375881f"}},{"arxiv_id":"2402.16379","paper":"/paper/improving-llm-based-machine-translation-with","title":"TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fzp0424/self_correct_mt","path":"run_file.py","file_url":"https://github.com/fzp0424/self_correct_mt/blob/HEAD/run_file.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"2402.16061","paper":"/paper/how-large-language-models-encode-context","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jometeorie/probing_llama","path":"code/custom_llama/convert_llama_weights_to_hf.py","file_url":"https://github.com/jometeorie/probing_llama/blob/HEAD/code/custom_llama/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2402.13125","paper":"/paper/treeeval-benchmark-free-evaluation-of-large","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ashura5/treeeval","path":"score.py","file_url":"https://github.com/ashura5/treeeval/blob/HEAD/score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ed9d41af1f323ef","mcp_get_code":{"code_sha256":"0ed9d41af1f323ef"}},{"arxiv_id":"2402.11845","paper":"/paper/modularized-networks-for-few-shot-hateful","title":"Modularized Networks for Few-shot Hateful Meme Detection","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"social-ai-studio/mod_hate","path":"src/gen_dataset.py","file_url":"https://github.com/social-ai-studio/mod_hate/blob/HEAD/src/gen_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e08fac5d795bf1c2","mcp_get_code":{"code_sha256":"e08fac5d795bf1c2"}},{"arxiv_id":"2402.11457","paper":"/paper/when-do-llms-need-retrieval-augmentation","title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shiyunee/when-to-retrieve","path":"utils/utils.py","file_url":"https://github.com/shiyunee/when-to-retrieve/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6017b412458e24f4","mcp_get_code":{"code_sha256":"6017b412458e24f4"}},{"arxiv_id":"2402.10104","paper":"/paper/geoeval-benchmark-for-evaluating-llms-and","title":"GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geoeval/geoeval","path":"tool/merge_data.py","file_url":"https://github.com/geoeval/geoeval/blob/HEAD/tool/merge_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ee50a40e401c2b10","mcp_get_code":{"code_sha256":"ee50a40e401c2b10"}},{"arxiv_id":"2402.06221","paper":"/paper/resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ztrimus/job-llm","path":"zlm/utils/utils.py","file_url":"https://github.com/Ztrimus/job-llm/blob/HEAD/zlm/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5cdad5fbd8223f5f","mcp_get_code":{"code_sha256":"5cdad5fbd8223f5f"}},{"arxiv_id":"2402.03720","paper":"/paper/similarity-based-neighbor-selection-for-graph","title":"Similarity-based Neighbor Selection for Graph LLMs","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruili33/sns","path":"utils.py","file_url":"https://github.com/ruili33/sns/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"75d557b7ddcec540","mcp_get_code":{"code_sha256":"75d557b7ddcec540"}},{"arxiv_id":"2402.02823","paper":"/paper/evading-data-contamination-detection-for","title":"Evading Data Contamination Detection for Language Models is (too) Easy","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2402.02104","paper":"/paper/learning-structure-aware-representations-of","title":"Learning Structure-Aware Representations of Dependent Types","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konstantinosKokos/neural-agda","path":"src/quill/api/schemas.py","file_url":"https://github.com/konstantinosKokos/neural-agda/blob/HEAD/src/quill/api/schemas.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd87777d88dfb303","mcp_get_code":{"code_sha256":"bd87777d88dfb303"}},{"arxiv_id":"2402.01618","paper":"/paper/style-vectors-for-steering-generative-large","title":"Style Vectors for Steering Generative Large Language Model","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dlr-sc/style-vectors-for-steering-llms","path":"utils/convert_llama_weights_to_hf.py","file_url":"https://github.com/dlr-sc/style-vectors-for-steering-llms/blob/HEAD/utils/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2401.12554","paper":"/paper/can-large-language-models-write-parallel-code","title":"Can Large Language Models Write Parallel Code?","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parallelcodefoundry/ParEval","path":"analysis/bin-the-stack.py","file_url":"https://github.com/parallelcodefoundry/ParEval/blob/HEAD/analysis/bin-the-stack.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"24736464e5b48a38","mcp_get_code":{"code_sha256":"24736464e5b48a38"}},{"arxiv_id":"2401.10215","paper":"/paper/gpavatar-generalizable-and-precise-head","title":"GPAvatar: Generalizable and Precise Head Avatar from Image(s)","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xg-chu/gpavatar","path":"core/utils/utils.py","file_url":"https://github.com/xg-chu/gpavatar/blob/HEAD/core/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d7a228e78ecf8b6c","mcp_get_code":{"code_sha256":"d7a228e78ecf8b6c"}},{"arxiv_id":"2401.09840","paper":"/paper/freed-improving-rl-agents-for-fragment-based","title":"FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"airi-institute/ffreed","path":"ffreed/utils.py","file_url":"https://github.com/airi-institute/ffreed/blob/HEAD/ffreed/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0cf9a70a462ead4","mcp_get_code":{"code_sha256":"b0cf9a70a462ead4"}},{"arxiv_id":"2401.07950","paper":"/paper/sciglm-training-scientific-language-models","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","date":"2024-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/SciGLM","path":"self_reflective_annotation/reflective_generation/api_gen_gpt.py","file_url":"https://github.com/THUDM/SciGLM/blob/HEAD/self_reflective_annotation/reflective_generation/api_gen_gpt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dae309af08c4bf0a","mcp_get_code":{"code_sha256":"dae309af08c4bf0a"}},{"arxiv_id":"2401.07950","paper":"/paper/sciglm-training-scientific-language-models","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","date":"2024-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/sciglm","path":"self_reflective_annotation/reflective_generation/api_gen_gpt_revise.py","file_url":"https://github.com/thudm/sciglm/blob/HEAD/self_reflective_annotation/reflective_generation/api_gen_gpt_revise.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb4b23e8ddc8bc80","mcp_get_code":{"code_sha256":"fb4b23e8ddc8bc80"}},{"arxiv_id":"2401.07950","paper":"/paper/sciglm-training-scientific-language-models","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","date":"2024-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/sciglm","path":"self_reflective_annotation/data_classifier/rm_eval.py","file_url":"https://github.com/thudm/sciglm/blob/HEAD/self_reflective_annotation/data_classifier/rm_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b94a0e33c0124ec","mcp_get_code":{"code_sha256":"8b94a0e33c0124ec"}},{"arxiv_id":"2401.06706","paper":"/paper/multi-candidate-speculative-decoding","title":"Multi-Candidate Speculative Decoding","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"njunlp/mcsd","path":"MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","file_url":"https://github.com/njunlp/mcsd/blob/HEAD/MCSD/model/llama_tree_attn/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2401.04518","paper":"/paper/the-critique-of-critique","title":"The Critique of Critique","date":"2024-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/metacritique","path":"meta_critique/utils.py","file_url":"https://github.com/gair-nlp/metacritique/blob/HEAD/meta_critique/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"851a9d51cc072ba2","mcp_get_code":{"code_sha256":"851a9d51cc072ba2"}},{"arxiv_id":"2401.02460","paper":"/paper/improved-zero-shot-classification-by-adapting","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","date":"2024-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvl-umass/AdaptCLIPZS","path":"vdt_utils.py","file_url":"https://github.com/cvl-umass/AdaptCLIPZS/blob/HEAD/vdt_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"2312.10091","paper":"/paper/look-before-you-leap-a-universal-emergent","title":"Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models","date":"2023-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"avariengien/causal-checker","path":"causal_checker/datasets/factual_recall.py","file_url":"https://github.com/avariengien/causal-checker/blob/HEAD/causal_checker/datasets/factual_recall.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04716e8e8ec93bf1","mcp_get_code":{"code_sha256":"04716e8e8ec93bf1"}},{"arxiv_id":"2312.05742","paper":"/paper/the-generalization-gap-in-offline","title":"The Generalization Gap in Offline Reinforcement Learning","date":"2023-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/gen_dgrl","path":"webShop/baseline_models/logger.py","file_url":"https://github.com/facebookresearch/gen_dgrl/blob/HEAD/webShop/baseline_models/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2311.17518","paper":"/paper/the-devil-is-in-the-fine-grained-details","title":"The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lorebianchi98/fg-ovd","path":"NoctOWL/eval/fg-ovd/evaluate_map.py","file_url":"https://github.com/lorebianchi98/fg-ovd/blob/HEAD/NoctOWL/eval/fg-ovd/evaluate_map.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0be4cd21574acdc0","mcp_get_code":{"code_sha256":"0be4cd21574acdc0"}},{"arxiv_id":"2311.09000","paper":"/paper/factcheck-gpt-end-to-end-fine-grained","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuxiaw/factcheck-gpt","path":"annotation_tool/example/generate_screen3_input.py","file_url":"https://github.com/yuxiaw/factcheck-gpt/blob/HEAD/annotation_tool/example/generate_screen3_input.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f658f5c499d963bf","mcp_get_code":{"code_sha256":"f658f5c499d963bf"}},{"arxiv_id":"2311.04284","paper":"/paper/crab-assessing-the-strength-of-causal","title":"CRAB: Assessing the Strength of Causal Relationships Between Real-world Events","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agromanou/crab","path":"src/graded_causality.py","file_url":"https://github.com/agromanou/crab/blob/HEAD/src/graded_causality.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2310.15664","paper":"/paper/expression-syntax-information-bottleneck-for","title":"Expression Syntax Information Bottleneck for Math Word Problems","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"menik1126/math_esib","path":"run_seq2tree_bert_ultimate_comp.py","file_url":"https://github.com/menik1126/math_esib/blob/HEAD/run_seq2tree_bert_ultimate_comp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1c0882e1c2c8f49","mcp_get_code":{"code_sha256":"c1c0882e1c2c8f49"}},{"arxiv_id":"2310.15239","paper":"/paper/crow-benchmarking-commonsense-reasoning-in","title":"CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mismayil/crow","path":"utils.py","file_url":"https://github.com/mismayil/crow/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8c65c92ec213846","mcp_get_code":{"code_sha256":"f8c65c92ec213846"}},{"arxiv_id":"2310.14985","paper":"/paper/llm-based-agent-society-investigation","title":"LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"3DAgentWorld/LLM-Game-Agent","path":"evaluation/Identify_merlin.py","file_url":"https://github.com/3DAgentWorld/LLM-Game-Agent/blob/HEAD/evaluation/Identify_merlin.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ca898eecc6043ff","mcp_get_code":{"code_sha256":"9ca898eecc6043ff"}},{"arxiv_id":"2310.12426","paper":"/paper/maf-multi-aspect-feedback-for-improving","title":"MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepakn97/maf","path":"src/gsm_maf/gsm_selfref_eval.py","file_url":"https://github.com/deepakn97/maf/blob/HEAD/src/gsm_maf/gsm_selfref_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0f15228f88695710","mcp_get_code":{"code_sha256":"0f15228f88695710"}},{"arxiv_id":"2310.10628","paper":"/paper/data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abacusai/to-the-cutoff","path":"eval/chronological_evaluation/chronological_evaluation_utils.py","file_url":"https://github.com/abacusai/to-the-cutoff/blob/HEAD/eval/chronological_evaluation/chronological_evaluation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1070d7029c9edba2","mcp_get_code":{"code_sha256":"1070d7029c9edba2"}},{"arxiv_id":"2310.10158","paper":"/paper/character-llm-a-trainable-agent-for-role","title":"Character-LLM: A Trainable Agent for Role-Playing","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"choosewhatulike/trainable-agents","path":"eval_utils.py","file_url":"https://github.com/choosewhatulike/trainable-agents/blob/HEAD/eval_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ad5f98bba0c21929","mcp_get_code":{"code_sha256":"ad5f98bba0c21929"}},{"arxiv_id":"2310.07659","paper":"/paper/well-begun-is-half-done-generator-agnostic","title":"Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinlang14/GATE","path":"KnowledgeSelection/GATEModel/model.py","file_url":"https://github.com/qinlang14/GATE/blob/HEAD/KnowledgeSelection/GATEModel/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"51af59393a7deade","mcp_get_code":{"code_sha256":"51af59393a7deade"}},{"arxiv_id":"2310.07652","paper":"/paper/llm4vis-explainable-visualization","title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"demoleiwang/LLM4Vis","path":"utils.py","file_url":"https://github.com/demoleiwang/LLM4Vis/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"005bceded2b9a9c6","mcp_get_code":{"code_sha256":"005bceded2b9a9c6"}},{"arxiv_id":"2310.04900","paper":"/paper/howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ninatu/howtocaption","path":"howtocaption/parse_config.py","file_url":"https://github.com/ninatu/howtocaption/blob/HEAD/howtocaption/parse_config.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5aca268f4b79732e","mcp_get_code":{"code_sha256":"5aca268f4b79732e"}},{"arxiv_id":"2308.16137","paper":"/paper/lm-infinite-simple-on-the-fly-length","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Glaciohound/LM-Infinite","path":"models/get_llama2/convert_llama_weights_to_hf.py","file_url":"https://github.com/Glaciohound/LM-Infinite/blob/HEAD/models/get_llama2/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2308.12674","paper":"/paper/improving-translation-faithfulness-of-large","title":"Improving Translation Faithfulness of Large Language Models via Augmenting Instructions","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pppa2019/swie_overmiss_llm4mt","path":"utils/convert_alpaca_to_hf.py","file_url":"https://github.com/pppa2019/swie_overmiss_llm4mt/blob/HEAD/utils/convert_alpaca_to_hf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a90bcd4fe56ecc9f","mcp_get_code":{"code_sha256":"a90bcd4fe56ecc9f"}},{"arxiv_id":"2308.07146","paper":"/paper/ctp-towards-vision-language-continual","title":"CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kevinlight831/ctp","path":"product_evaluation.py","file_url":"https://github.com/kevinlight831/ctp/blob/HEAD/product_evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9cfe36eb8375795","mcp_get_code":{"code_sha256":"a9cfe36eb8375795"}},{"arxiv_id":"2308.01546","paper":"/paper/musicldm-enhancing-novelty-in-text-to-music","title":"MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies","date":"2023-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"retrocirce/musicldm","path":"interface/src/utilities/tools.py","file_url":"https://github.com/retrocirce/musicldm/blob/HEAD/interface/src/utilities/tools.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a42cc3d7c42a043","mcp_get_code":{"code_sha256":"8a42cc3d7c42a043"}},{"arxiv_id":"2307.15055","paper":"/paper/pointodyssey-a-large-scale-synthetic-dataset","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","date":"2023-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"y-zheng18/point_odyssey","path":"utils/file_io.py","file_url":"https://github.com/y-zheng18/point_odyssey/blob/HEAD/utils/file_io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"21dd9ba5d9e47a8f","mcp_get_code":{"code_sha256":"21dd9ba5d9e47a8f"}},{"arxiv_id":"2307.08072","paper":"/paper/do-emergent-abilities-exist-in-quantized","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","date":"2023-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/quantizedempirical","path":"convert_llama_weights_to_hf.py","file_url":"https://github.com/rucaibox/quantizedempirical/blob/HEAD/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2307.03170","paper":"/paper/focused-transformer-contrastive-training-for","title":"Focused Transformer: Contrastive Training for Context Scaling","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CStanKonrad/long_llama","path":"fot_continued_pretraining/EasyLM/models/llama/convert_easylm_to_hf.py","file_url":"https://github.com/CStanKonrad/long_llama/blob/HEAD/fot_continued_pretraining/EasyLM/models/llama/convert_easylm_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2306.09200","paper":"/paper/chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"waterhorse1/ChessGPT","path":"chessgpt/train/clm_training/finetune_pp_peft_trainer.py","file_url":"https://github.com/waterhorse1/ChessGPT/blob/HEAD/chessgpt/train/clm_training/finetune_pp_peft_trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2306.06874","paper":"/paper/villandiffusion-a-unified-backdoor-attack-1","title":"VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/VillanDiffusion","path":"VillanDiffusion.py","file_url":"https://github.com/IBM/VillanDiffusion/blob/HEAD/VillanDiffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"410e560ea7b3decb","mcp_get_code":{"code_sha256":"410e560ea7b3decb"}},{"arxiv_id":"2306.02224","paper":"/paper/auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"younghuman/llmagent","path":"webshop/baseline_models/logger.py","file_url":"https://github.com/younghuman/llmagent/blob/HEAD/webshop/baseline_models/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2305.18153","paper":"/paper/do-large-language-models-know-what-they-don-t","title":"Do Large Language Models Know What They Don't Know?","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinzhangyue/selfaware","path":"code/run_model.py","file_url":"https://github.com/yinzhangyue/selfaware/blob/HEAD/code/run_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"cd3c7b096ad71ffc","mcp_get_code":{"code_sha256":"cd3c7b096ad71ffc"}},{"arxiv_id":"2305.13718","paper":"/paper/logicllm-exploring-self-supervised-logic","title":"Exploring Self-supervised Logic-enhanced Training for Large Language Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sparkjiao/logicllm","path":"convert2hf.py","file_url":"https://github.com/sparkjiao/logicllm/blob/HEAD/convert2hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2304.14454","paper":"/paper/pmc-llama-further-finetuning-llama-on-medical","title":"PMC-LLaMA: Towards Building Open-source Language Models for Medicine","date":"2023-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaoyi-wu/pmc-llama","path":"Pretrain/training.py","file_url":"https://github.com/chaoyi-wu/pmc-llama/blob/HEAD/Pretrain/training.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2304.13861","paper":"/paper/is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AGMoller/worker_vs_gpt","path":"src/worker_vs_gpt/utils.py","file_url":"https://github.com/AGMoller/worker_vs_gpt/blob/HEAD/src/worker_vs_gpt/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd66b2a0f811f16d","mcp_get_code":{"code_sha256":"dd66b2a0f811f16d"}},{"arxiv_id":"2304.08177","paper":"/paper/efficient-and-effective-text-encoding-for","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","date":"2023-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neukg/techgpt-2.0","path":"ckpt_weight_convert/convert_weight.py","file_url":"https://github.com/neukg/techgpt-2.0/blob/HEAD/ckpt_weight_convert/convert_weight.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2304.03153","paper":"/paper/zero-shot-next-item-recommendation-using","title":"Zero-Shot Next-Item Recommendation using Large Pretrained Language Models","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agi-edgerunners/llm-next-item-rec","path":"three_stage_0_NIR.py","file_url":"https://github.com/agi-edgerunners/llm-next-item-rec/blob/HEAD/three_stage_0_NIR.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"338f36e51a3f8e75","mcp_get_code":{"code_sha256":"338f36e51a3f8e75"}},{"arxiv_id":"2304.01904","paper":"/paper/refiner-reasoning-feedback-on-intermediate","title":"REFINER: Reasoning Feedback on Intermediate Representations","date":"2023-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"debjitpaul/refiner","path":"data_preprocessing/utils.py","file_url":"https://github.com/debjitpaul/refiner/blob/HEAD/data_preprocessing/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f345dec5bbd964bd","mcp_get_code":{"code_sha256":"f345dec5bbd964bd"}},{"arxiv_id":"2302.04831","paper":"/paper/cooperative-open-ended-learning-framework-for","title":"Cooperative Open-ended Learning Framework for Zero-shot Coordination","date":"2023-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-Alignment/ProAgent","path":"lib/stable-baselines/stable_baselines/logger.py","file_url":"https://github.com/PKU-Alignment/ProAgent/blob/HEAD/lib/stable-baselines/stable_baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64647496a3527b7b","mcp_get_code":{"code_sha256":"64647496a3527b7b"}},{"arxiv_id":"2302.03668","paper":"/paper/hard-prompts-made-easy-gradient-based-1","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","date":"2023-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuxinWenRick/hard-prompts-made-easy","path":"optim_utils.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/optim_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bf4874e1d9eed03","mcp_get_code":{"code_sha256":"0bf4874e1d9eed03"}},{"arxiv_id":"2302.02299","paper":"/paper/sample-dropout-a-simple-yet-effective","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","date":"2023-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzichuan/sdpo","path":"baselines/logger.py","file_url":"https://github.com/linzichuan/sdpo/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2301.06387","paper":"/paper/pecan-leveraging-policy-ensemble-for-context","title":"PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination","date":"2023-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LxzGordon/pecan_human_AI_coordination","path":"overcookedgym/human_aware_rl/baselines/baselines/logger.py","file_url":"https://github.com/LxzGordon/pecan_human_AI_coordination/blob/HEAD/overcookedgym/human_aware_rl/baselines/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2212.10534","paper":"/paper/disco-distilling-phrasal-counterfactuals-with","title":"DISCO: Distilling Counterfactuals with Large Language Models","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric11eca/disco","path":"distiller/utils.py","file_url":"https://github.com/eric11eca/disco/blob/HEAD/distiller/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56ab26e03a4cb497","mcp_get_code":{"code_sha256":"56ab26e03a4cb497"}},{"arxiv_id":"2212.10264","paper":"/paper/recode-robustness-evaluation-of-code","title":"ReCode: Robustness Evaluation of Code Generation Models","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/recode","path":"run_robust.py","file_url":"https://github.com/amazon-science/recode/blob/HEAD/run_robust.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aabb21de20501ffe","mcp_get_code":{"code_sha256":"aabb21de20501ffe"}},{"arxiv_id":"2212.02098","paper":"/paper/a-machine-with-short-term-episodic-and","title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","date":"2022-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humemai/agent-room-env-v1","path":"agent/utils.py","file_url":"https://github.com/humemai/agent-room-env-v1/blob/HEAD/agent/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60c58b20152f06b8","mcp_get_code":{"code_sha256":"60c58b20152f06b8"}},{"arxiv_id":"2211.09374","paper":"/paper/execution-based-evaluation-for-data-science","title":"Execution-based Evaluation for Data Science Code Generation Models","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jun-jie-huang/exeds","path":"codegpt/dataset.py","file_url":"https://github.com/jun-jie-huang/exeds/blob/HEAD/codegpt/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81b829e58d63ebb4","mcp_get_code":{"code_sha256":"81b829e58d63ebb4"}},{"arxiv_id":"2211.09374","paper":"/paper/execution-based-evaluation-for-data-science","title":"Execution-based Evaluation for Data Science Code Generation Models","date":"2022-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jun-jie-huang/exeds","path":"evaluation/evaluate_execution.py","file_url":"https://github.com/jun-jie-huang/exeds/blob/HEAD/evaluation/evaluate_execution.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"327db3228bc36b13","mcp_get_code":{"code_sha256":"327db3228bc36b13"}},{"arxiv_id":"2210.07316","paper":"/paper/mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"basf/chemteb","path":"chem_eval.py","file_url":"https://github.com/basf/chemteb/blob/HEAD/chem_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2210.05197","paper":"/paper/mixed-modality-representation-learning-and","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","date":"2022-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jun-jie-huang/otter","path":"preprocessing/utils_preprocess.py","file_url":"https://github.com/jun-jie-huang/otter/blob/HEAD/preprocessing/utils_preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"327db3228bc36b13","mcp_get_code":{"code_sha256":"327db3228bc36b13"}},{"arxiv_id":"2210.03501","paper":"/paper/towards-multi-modal-sarcasm-detection-via","title":"Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement","date":"2022-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"less-and-less-bugs/hkemodel","path":"utils/data_utils.py","file_url":"https://github.com/less-and-less-bugs/hkemodel/blob/HEAD/utils/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"621248420b870218","mcp_get_code":{"code_sha256":"621248420b870218"}},{"arxiv_id":"2210.00881","paper":"/paper/predicting-the-future-of-ai-with-ai-high","title":"Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network","date":"2022-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mariokrenn6240/futureofaiviaai","path":"all_models/M1/file_utils.py","file_url":"https://github.com/mariokrenn6240/futureofaiviaai/blob/HEAD/all_models/M1/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9faa55b49581385","mcp_get_code":{"code_sha256":"c9faa55b49581385"}},{"arxiv_id":"2207.12080","paper":"/paper/intention-conditioned-long-term-human","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","date":"2022-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evm7/ego4dlta-icvae","path":"create_prediction.py","file_url":"https://github.com/evm7/ego4dlta-icvae/blob/HEAD/create_prediction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4aabffaf2e69d2fc","mcp_get_code":{"code_sha256":"4aabffaf2e69d2fc"}},{"arxiv_id":"2207.12080","paper":"/paper/intention-conditioned-long-term-human","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","date":"2022-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evm7/ego4dlta-icvae","path":"preprocess_dataset.py","file_url":"https://github.com/evm7/ego4dlta-icvae/blob/HEAD/preprocess_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"98d8d8a38530a126","mcp_get_code":{"code_sha256":"98d8d8a38530a126"}},{"arxiv_id":"2206.00093","paper":"/paper/easy-variational-inference-for-categorical","title":"Easy Variational Inference for Categorical Models via an Independent Binary Approximation","date":"2022-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tufts-ml/categorical-from-binary","path":"src/categorical_from_binary/io.py","file_url":"https://github.com/tufts-ml/categorical-from-binary/blob/HEAD/src/categorical_from_binary/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4111075441a4120b","mcp_get_code":{"code_sha256":"4111075441a4120b"}},{"arxiv_id":"2205.14495","paper":"/paper/task-agnostic-continual-reinforcement","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","date":"2022-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/replay-based-recurrent-rl","path":"code/oailibs/logger.py","file_url":"https://github.com/amazon-research/replay-based-recurrent-rl/blob/HEAD/code/oailibs/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2204.08790","paper":"/paper/elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","date":"2022-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/pevit","path":"read_results.py","file_url":"https://github.com/eric-ai-lab/pevit/blob/HEAD/read_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e6ec58f35d0977b","mcp_get_code":{"code_sha256":"4e6ec58f35d0977b"}},{"arxiv_id":"2204.08790","paper":"/paper/elevater-a-benchmark-and-toolkit-for","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","date":"2022-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/pevit","path":"read_txt.py","file_url":"https://github.com/eric-ai-lab/pevit/blob/HEAD/read_txt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f28aa08fa3d16f1","mcp_get_code":{"code_sha256":"5f28aa08fa3d16f1"}},{"arxiv_id":"2204.08426","paper":"/paper/chai-a-chatbot-ai-for-task-oriented-dialogue","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","date":"2022-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siddharthverma314/chai-naacl-2022","path":"cocoa/core/util.py","file_url":"https://github.com/siddharthverma314/chai-naacl-2022/blob/HEAD/cocoa/core/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51b941b0a4c27d3d","mcp_get_code":{"code_sha256":"51b941b0a4c27d3d"}},{"arxiv_id":"2203.08597","paper":"/paper/less-is-more-summary-of-long-instructions-is","title":"Less is More: Summary of Long Instructions is Better for Program Synthesis","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kurbster/prompt-summarization","path":"src/lib/run_results.py","file_url":"https://github.com/kurbster/prompt-summarization/blob/HEAD/src/lib/run_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c26950f1affe1579","mcp_get_code":{"code_sha256":"c26950f1affe1579"}},{"arxiv_id":"2203.01282","paper":"/paper/texttt-py-irt-a-scalable-item-response-theory","title":"py-irt: A Scalable Item Response Theory Library for Python","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nd-ball/py-irt","path":"py_irt/io.py","file_url":"https://github.com/nd-ball/py-irt/blob/HEAD/py_irt/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b8fe10303ae293f8","mcp_get_code":{"code_sha256":"b8fe10303ae293f8"}},{"arxiv_id":"2203.01044","paper":"/paper/selfkg-self-supervised-entity-alignment-in","title":"SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs","date":"2022-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/SelfKG","path":"settings.py","file_url":"https://github.com/THUDM/SelfKG/blob/HEAD/settings.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"211e2d48b56f6b5c","mcp_get_code":{"code_sha256":"211e2d48b56f6b5c"}},{"arxiv_id":"2202.01273","paper":"/paper/beyond-images-label-noise-transition-matrix","title":"Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features","date":"2022-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ucsc-real/est-t-mi","path":"utils/logger.py","file_url":"https://github.com/ucsc-real/est-t-mi/blob/HEAD/utils/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2111.07117","paper":"/paper/learning-object-centric-representations-of-1","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","date":"2021-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NanboLi/MulMON","path":"utils.py","file_url":"https://github.com/NanboLi/MulMON/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a52cdb9371e301f2","mcp_get_code":{"code_sha256":"a52cdb9371e301f2"}},{"arxiv_id":"2111.03583","paper":"/paper/data-driven-discovery-of-dimensionless","title":"Data-driven discovery of dimensionless numbers and scaling laws from experimental measurements","date":null,"month_inferred_from_arxiv_id":"2021-11","title_source":"archive","repo":"xiaoyuxie-vico/PyDimension","path":"pydimension/common/io.py","file_url":"https://github.com/xiaoyuxie-vico/PyDimension/blob/HEAD/pydimension/common/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5c24b5500c82204b","mcp_get_code":{"code_sha256":"5c24b5500c82204b"}},{"arxiv_id":"2109.15310","paper":"/paper/width-based-planning-and-active-learning-for","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","date":"2021-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/atari-active-learning","path":"aggregate_pandas.py","file_url":"https://github.com/ibm/atari-active-learning/blob/HEAD/aggregate_pandas.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e50712b6aa876b2","mcp_get_code":{"code_sha256":"8e50712b6aa876b2"}},{"arxiv_id":"2109.08535","paper":"/paper/simple-entity-centric-questions-challenge","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","date":"2021-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/EntityQuestions","path":"utils/ion.py","file_url":"https://github.com/princeton-nlp/EntityQuestions/blob/HEAD/utils/ion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ad3e5e941b7cf41","mcp_get_code":{"code_sha256":"9ad3e5e941b7cf41"}},{"arxiv_id":"2107.13435","paper":"/paper/mwp-bert-a-strong-baseline-for-math-word","title":"MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving","date":"2021-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzhenwen/mwp-bert","path":"Fine-tuning/Math23k/math23k.py","file_url":"https://github.com/lzhenwen/mwp-bert/blob/HEAD/Fine-tuning/Math23k/math23k.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c31a919f85cca48c","mcp_get_code":{"code_sha256":"c31a919f85cca48c"}},{"arxiv_id":"2107.09106","paper":"/paper/separating-skills-and-concepts-for-novel-1","title":"Separating Skills and Concepts for Novel Visual Question Answering","date":"2021-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MalvinaNikandrou/contvqa","path":"src/contvqa/common.py","file_url":"https://github.com/MalvinaNikandrou/contvqa/blob/HEAD/src/contvqa/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5e5d18d0c38ef2a","mcp_get_code":{"code_sha256":"a5e5d18d0c38ef2a"}},{"arxiv_id":"2104.06770","paper":"/paper/graph-based-person-signature-for-person-re","title":"Graph-based Person Signature for Person Re-Identifications","date":"2021-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aioz-ai/CVPRW21_GPS","path":"utils/iotools.py","file_url":"https://github.com/aioz-ai/CVPRW21_GPS/blob/HEAD/utils/iotools.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"2010.07916","paper":"/paper/multi-agent-trust-region-policy-optimization","title":"Multi-Agent Trust Region Policy Optimization","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hepengli/matrpo","path":"matrpo/common/logger.py","file_url":"https://github.com/hepengli/matrpo/blob/HEAD/matrpo/common/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2009.01027","paper":"/paper/darts-robustly-stepping-out-of-performance","title":"DARTS-: Robustly Stepping out of Performance Collapse Without Indicators","date":"2020-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Meituan-AutoML/DARTS-","path":"plots/plot_beta_vs_valid_loss.py","file_url":"https://github.com/Meituan-AutoML/DARTS-/blob/HEAD/plots/plot_beta_vs_valid_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"35394520b14b68c3","mcp_get_code":{"code_sha256":"35394520b14b68c3"}},{"arxiv_id":"2008.11790","paper":"/paper/mutagan-a-seq2seq-gan-framework-to-predict","title":"MutaGAN: A Seq2seq GAN Framework to Predict Mutations of Evolving Protein Populations","date":"2020-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"1hachem/mutaGAN","path":"utils/utils.py","file_url":"https://github.com/1hachem/mutaGAN/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc880616a10bffc7","mcp_get_code":{"code_sha256":"dc880616a10bffc7"}},{"arxiv_id":"2008.11790","paper":"/paper/mutagan-a-seq2seq-gan-framework-to-predict","title":"MutaGAN: A Seq2seq GAN Framework to Predict Mutations of Evolving Protein Populations","date":"2020-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anuprulez/clade_prediction","path":"comparison_with_wuhan.py","file_url":"https://github.com/anuprulez/clade_prediction/blob/HEAD/comparison_with_wuhan.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2ab6cedad111e4d","mcp_get_code":{"code_sha256":"b2ab6cedad111e4d"}},{"arxiv_id":"2008.10292","paper":"/paper/automated-search-for-resource-efficient","title":"Automated Search for Resource-Efficient Branched Multi-Task Networks","date":"2020-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brdav/bmtas","path":"src/utils.py","file_url":"https://github.com/brdav/bmtas/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb3e67ec54bb65e3","mcp_get_code":{"code_sha256":"bb3e67ec54bb65e3"}},{"arxiv_id":"2007.08459","paper":"/paper/pc-pg-policy-cover-directed-exploration-for","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","date":"2020-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mbhenaff/pcpg","path":"baselines/logger.py","file_url":"https://github.com/mbhenaff/pcpg/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2006.09043","paper":"/paper/improved-deep-point-cloud-geometry","title":"Improved Deep Point Cloud Geometry Compression","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mauriceqch/pcc_geo_cnn_v2","path":"src/ev_compare.py","file_url":"https://github.com/mauriceqch/pcc_geo_cnn_v2/blob/HEAD/src/ev_compare.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9cc30d373e78edd4","mcp_get_code":{"code_sha256":"9cc30d373e78edd4"}},{"arxiv_id":"2006.07409","paper":"/paper/how-to-avoid-being-eaten-by-a-grue-structured","title":"How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajammanabrolu/Q-BERT","path":"qbert/logger.py","file_url":"https://github.com/rajammanabrolu/Q-BERT/blob/HEAD/qbert/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2006.04061","paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/logger.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2005.08526","paper":"/paper/unconditional-audio-generation-with","title":"Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization","date":"2020-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ciaua/unagan","path":"src/training_manager.py","file_url":"https://github.com/ciaua/unagan/blob/HEAD/src/training_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"437ac0d0b7649768","mcp_get_code":{"code_sha256":"437ac0d0b7649768"}},{"arxiv_id":"2005.03420","paper":"/paper/curious-hierarchical-actor-critic","title":"Curious Hierarchical Actor-Critic Reinforcement Learning","date":"2020-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knowledgetechnologyuhh/goal_conditioned_RL_baselines","path":"baselines/logger.py","file_url":"https://github.com/knowledgetechnologyuhh/goal_conditioned_RL_baselines/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"2004.10924","paper":"/paper/polylanenet-lane-estimation-via-deep","title":"PolyLaneNet: Lane Estimation via Deep Polynomial Regression","date":"2020-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucastabelini/PolyLaneNet","path":"lib/datasets/llamas.py","file_url":"https://github.com/lucastabelini/PolyLaneNet/blob/HEAD/lib/datasets/llamas.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1cf08d93a9b54189","mcp_get_code":{"code_sha256":"1cf08d93a9b54189"}},{"arxiv_id":"2004.06165","paper":"/paper/oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ThanThoai/Visual-Question-Answering_Vietnamese","path":"merge_raw_data.py","file_url":"https://github.com/ThanThoai/Visual-Question-Answering_Vietnamese/blob/HEAD/merge_raw_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ecf115f3542eefd4","mcp_get_code":{"code_sha256":"ecf115f3542eefd4"}},{"arxiv_id":"2001.04193","paper":"/paper/deep-learning-for-person-re-identification-a","title":"Deep Learning for Person Re-identification: A Survey and Outlook","date":"2020-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zion-king/Deep-Learning-for-Person-Re-identification","path":"utils/iotools.py","file_url":"https://github.com/zion-king/Deep-Learning-for-Person-Re-identification/blob/HEAD/utils/iotools.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"1912.03966","paper":"/paper/efficient-object-detection-in-large-images","title":"Efficient Object Detection in Large Images using Deep Reinforcement Learning","date":"2019-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uzkent/EfficientObjectDetection","path":"utils/utils.py","file_url":"https://github.com/uzkent/EfficientObjectDetection/blob/HEAD/utils/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"493730f7f6da28dd","mcp_get_code":{"code_sha256":"493730f7f6da28dd"}},{"arxiv_id":"1910.12154","paper":"/paper/zpd-teaching-strategies-for-deep","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","date":"2019-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RevanMacQueen/LearningFromHumans","path":"lfh/utils/io.py","file_url":"https://github.com/RevanMacQueen/LearningFromHumans/blob/HEAD/lfh/utils/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c8ce2af5b547951","mcp_get_code":{"code_sha256":"0c8ce2af5b547951"}},{"arxiv_id":"1910.05512","paper":"/paper/influence-based-multi-agent-exploration","title":"Influence-Based Multi-Agent Exploration","date":"2019-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TonghanWang/EITI-EDTI","path":"baselines/logger.py","file_url":"https://github.com/TonghanWang/EITI-EDTI/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1909.06639","paper":"/paper/tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itzpankajpanwar/Tree-transform","path":"utils.py","file_url":"https://github.com/itzpankajpanwar/Tree-transform/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c204acb9ea9e761d","mcp_get_code":{"code_sha256":"c204acb9ea9e761d"}},{"arxiv_id":"1909.05398","paper":"/paper/interactive-fiction-games-a-colossal","title":"Interactive Fiction Games: A Colossal Adventure","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/tdqn","path":"tdqn/logger.py","file_url":"https://github.com/microsoft/tdqn/blob/HEAD/tdqn/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1908.11421","paper":"/paper/learning-latent-parameters-without-human","title":"Learning Latent Parameters without Human Response Patterns: Item Response Theory with Artificial Crowds","date":"2019-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jplalor/py-irt","path":"py_irt/io.py","file_url":"https://github.com/jplalor/py-irt/blob/HEAD/py_irt/io.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b8fe10303ae293f8","mcp_get_code":{"code_sha256":"b8fe10303ae293f8"}},{"arxiv_id":"1906.05841","paper":"/paper/deep-reinforcement-learning-for-industrial","title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","date":"2019-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mizolotu/SmartExcavator","path":"baselines/logger.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1905.11946","paper":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamilyasedunov/key_word_spotting","path":"logger/utils.py","file_url":"https://github.com/iamilyasedunov/key_word_spotting/blob/HEAD/logger/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08352c8175b8893c","mcp_get_code":{"code_sha256":"08352c8175b8893c"}},{"arxiv_id":"1905.06750","paper":"/paper/random-expert-distillation-imitation-learning","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","date":"2019-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RuohanW/RED","path":"baselines/logger.py","file_url":"https://github.com/RuohanW/RED/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/logger.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1903.11306","paper":"/paper/linkage-based-face-clustering-via-graph","title":"Linkage Based Face Clustering via Graph Convolution Network","date":"2019-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhongdao/gcn_clustering","path":"utils/serialization.py","file_url":"https://github.com/Zhongdao/gcn_clustering/blob/HEAD/utils/serialization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"1905.04100","paper":"/paper/190504100","title":"Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization","date":"2019-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aralab-unr/ReinforcementLearningWithGA","path":"baselines/logger.py","file_url":"https://github.com/aralab-unr/ReinforcementLearningWithGA/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1901.05555","paper":"/paper/class-balanced-loss-based-on-effective-number","title":"Class-Balanced Loss Based on Effective Number of Samples","date":"2019-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"richardaecn/class-balanced-loss","path":"src/data_utils.py","file_url":"https://github.com/richardaecn/class-balanced-loss/blob/HEAD/src/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35ae8c0dce858108","mcp_get_code":{"code_sha256":"35ae8c0dce858108"}},{"arxiv_id":"1810.02851","paper":"/paper/learning-to-encode-text-as-human-readable","title":"Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks","date":"2018-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yaushian/Unparalleled-Text-Summarization-using-GAN","path":"make_pretrain.py","file_url":"https://github.com/yaushian/Unparalleled-Text-Summarization-using-GAN/blob/HEAD/make_pretrain.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c204acb9ea9e761d","mcp_get_code":{"code_sha256":"c204acb9ea9e761d"}},{"arxiv_id":"1806.07857","paper":"/paper/rudder-return-decomposition-for-delayed","title":"RUDDER: Return Decomposition for Delayed Rewards","date":"2018-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/baselines-rudder","path":"baselines/logger.py","file_url":"https://github.com/ml-jku/baselines-rudder/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1806.02473","paper":"/paper/graph-convolutional-policy-network-for-goal","title":"Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation","date":"2018-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bowenliu16/rl_graph_generation","path":"rl-baselines/baselines/logger.py","file_url":"https://github.com/bowenliu16/rl_graph_generation/blob/HEAD/rl-baselines/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1804.06459","paper":"/paper/on-learning-intrinsic-rewards-for-policy","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","date":"2018-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hwhitetooth/lirpg","path":"baselines/logger.py","file_url":"https://github.com/Hwhitetooth/lirpg/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1711.00123","paper":"/paper/backpropagation-through-the-void-optimizing","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","date":"2017-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wgrathwohl/BackpropThroughTheVoidRL","path":"baselines/logger.py","file_url":"https://github.com/wgrathwohl/BackpropThroughTheVoidRL/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1612.05601","paper":"/paper/sononet-real-time-detection-and-localisation","title":"SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound","date":"2016-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lorna-Liu/ultrasound_vsumm_RL","path":"utils/file_process.py","file_url":"https://github.com/Lorna-Liu/ultrasound_vsumm_RL/blob/HEAD/utils/file_process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"1611.05763","paper":"/paper/learning-to-reinforcement-learn","title":"Learning to reinforcement learn","date":"2016-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gomerudo/openai-baselines","path":"baselines/logger.py","file_url":"https://github.com/gomerudo/openai-baselines/blob/HEAD/baselines/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"88ef5a17fc986d9a","mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"arxiv_id":"1611.01989","paper":"/paper/deepcoder-learning-to-write-programs","title":"DeepCoder: Learning to Write Programs","date":"2016-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lcary/io-generation","path":"iogen/iogen.py","file_url":"https://github.com/lcary/io-generation/blob/HEAD/iogen/iogen.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7cd9850de8c20aa3","mcp_get_code":{"code_sha256":"7cd9850de8c20aa3"}},{"arxiv_id":"1406.7758","paper":"/paper/theoretical-analysis-of-bayesian-optimisation","title":"Theoretical Analysis of Bayesian Optimisation with Unknown Gaussian Process Hyper-Parameters","date":"2014-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weepingwillowben/hyperparam-opt","path":"add_point.py","file_url":"https://github.com/weepingwillowben/hyperparam-opt/blob/HEAD/add_point.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f9dfaecff7419d8","mcp_get_code":{"code_sha256":"9f9dfaecff7419d8"}},{"arxiv_id":"ijcai2025_0509","paper":null,"title":"arXiv:ijcai2025_0509","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CLMASP/CLMASP","path":"code/clmasp/utils_tool.py","file_url":"https://github.com/CLMASP/CLMASP/blob/HEAD/code/clmasp/utils_tool.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a2f0f95c90f6c0c1","mcp_get_code":{"code_sha256":"a2f0f95c90f6c0c1"}},{"arxiv_id":"aaai_19899","paper":null,"title":"arXiv:aaai_19899","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"DeanChan/KeypointMessagePassing","path":"lib/utils/serialization.py","file_url":"https://github.com/DeanChan/KeypointMessagePassing/blob/HEAD/lib/utils/serialization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"Yang_Beyond_Walking_A_Large-Scale_Image-Text_Benchmark_for_Text-based_Person_Anomaly_ICCV_2025_paper","paper":null,"title":"arXiv:Yang_Beyond_Walking_A_Large-Scale_Image-Text_Benchmark_for_Text-based_Person_Anomaly_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Shuyu-XJTU/CMP","path":"utils.py","file_url":"https://github.com/Shuyu-XJTU/CMP/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1cf6464da33ec0c","mcp_get_code":{"code_sha256":"e1cf6464da33ec0c"}},{"arxiv_id":"Jin_Chat-UniVi_Unified_Visual_Representation_Empowers_Large_Language_Models_with_Image_CVPR_2024_paper","paper":null,"title":"arXiv:Jin_Chat-UniVi_Unified_Visual_Representation_Empowers_Large_Language_Models_with_Image_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PKU-YuanGroup/Chat-UniVi","path":"ChatUniVi/eval/model_video_qa.py","file_url":"https://github.com/PKU-YuanGroup/Chat-UniVi/blob/HEAD/ChatUniVi/eval/model_video_qa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c578a6846674ff45","mcp_get_code":{"code_sha256":"c578a6846674ff45"}},{"arxiv_id":"Han_UIBDiffusion_Universal_Imperceptible_Backdoor_Attack_for_Diffusion_Models_CVPR_2025_paper","paper":null,"title":"arXiv:Han_UIBDiffusion_Universal_Imperceptible_Backdoor_Attack_for_Diffusion_Models_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TheLaoLab/UIBDiffusion","path":"UIBDiffusion.py","file_url":"https://github.com/TheLaoLab/UIBDiffusion/blob/HEAD/UIBDiffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"410e560ea7b3decb","mcp_get_code":{"code_sha256":"410e560ea7b3decb"}},{"arxiv_id":"Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","paper":null,"title":"arXiv:Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guozix/DVLR","path":"eval/MathVerse/utilities.py","file_url":"https://github.com/guozix/DVLR/blob/HEAD/eval/MathVerse/utilities.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ffa907555068ff3","mcp_get_code":{"code_sha256":"9ffa907555068ff3"}},{"arxiv_id":"Chou_How_to_Backdoor_Diffusion_Models_CVPR_2023_paper","paper":null,"title":"arXiv:Chou_How_to_Backdoor_Diffusion_Models_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IBM/BadDiffusion","path":"baddiffusion.py","file_url":"https://github.com/IBM/BadDiffusion/blob/HEAD/baddiffusion.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"410e560ea7b3decb","mcp_get_code":{"code_sha256":"410e560ea7b3decb"}},{"arxiv_id":"Bai_Salient-to-Broad_Transition_for_Video_Person_Re-Identification_CVPR_2022_paper","paper":null,"title":"arXiv:Bai_Salient-to-Broad_Transition_for_Video_Person_Re-Identification_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"baist/SINet","path":"utils/utils.py","file_url":"https://github.com/baist/SINet/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"2025.naacl-long.327","paper":null,"title":"arXiv:2025.naacl-long.327","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ljyflores/simplification-project","path":"preprocess/preprocess.py","file_url":"https://github.com/ljyflores/simplification-project/blob/HEAD/preprocess/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfed25e4686138b1","mcp_get_code":{"code_sha256":"dfed25e4686138b1"}},{"arxiv_id":"2025.findings-emnlp.435","paper":null,"title":"arXiv:2025.findings-emnlp.435","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nguyenngocbaocmt02/OT-Intervention","path":"lofit_models/convert_llama_weights_to_hf.py","file_url":"https://github.com/nguyenngocbaocmt02/OT-Intervention/blob/HEAD/lofit_models/convert_llama_weights_to_hf.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5bcf01d18bba63d","mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"arxiv_id":"2025.findings-acl.923","paper":null,"title":"arXiv:2025.findings-acl.923","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LCS2-IIITD/KD_generalization","path":"generative/dataset/mawps/data_process.py","file_url":"https://github.com/LCS2-IIITD/KD_generalization/blob/HEAD/generative/dataset/mawps/data_process.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1266012e186b82e8","mcp_get_code":{"code_sha256":"1266012e186b82e8"}},{"arxiv_id":"2025.findings-acl.79","paper":null,"title":"arXiv:2025.findings-acl.79","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"USC-FORTIS/AD-LLM","path":"utils.py","file_url":"https://github.com/USC-FORTIS/AD-LLM/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"772778f25f3bd45f","mcp_get_code":{"code_sha256":"772778f25f3bd45f"}},{"arxiv_id":"2025.findings-acl.589","paper":null,"title":"arXiv:2025.findings-acl.589","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LiYichen99/FairSteer","path":"evaluate.py","file_url":"https://github.com/LiYichen99/FairSteer/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"517204663b146dc0","mcp_get_code":{"code_sha256":"517204663b146dc0"}},{"arxiv_id":"2025.findings-acl.318","paper":null,"title":"arXiv:2025.findings-acl.318","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SCUNLP/BAR","path":"bar/utils/util_box.py","file_url":"https://github.com/SCUNLP/BAR/blob/HEAD/bar/utils/util_box.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7c19a5590a906e28","mcp_get_code":{"code_sha256":"7c19a5590a906e28"}},{"arxiv_id":"2025.emnlp-industry.133","paper":null,"title":"arXiv:2025.emnlp-industry.133","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"endeavorXx/Mind-the-Query","path":"utils/utilities.py","file_url":"https://github.com/endeavorXx/Mind-the-Query/blob/HEAD/utils/utilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1329cce3b2fa921d","mcp_get_code":{"code_sha256":"1329cce3b2fa921d"}},{"arxiv_id":"2024.acl-long.719","paper":null,"title":"arXiv:2024.acl-long.719","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SilasTHU/AdMul","path":"utils.py","file_url":"https://github.com/SilasTHU/AdMul/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7d6e263caea8e963","mcp_get_code":{"code_sha256":"7d6e263caea8e963"}},{"arxiv_id":"2022.findings-naacl.188","paper":null,"title":"arXiv:2022.findings-naacl.188","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ShusenWang/NAACL2022-RCL","path":"utils.py","file_url":"https://github.com/ShusenWang/NAACL2022-RCL/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c10bf1ea56c58e14","mcp_get_code":{"code_sha256":"c10bf1ea56c58e14"}},{"arxiv_id":"2022.findings-emnlp.24","paper":null,"title":"arXiv:2022.findings-emnlp.24","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"StanLei52/TQVSR","path":"utils/basic_utils.py","file_url":"https://github.com/StanLei52/TQVSR/blob/HEAD/utils/basic_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62a29d660a30b012","mcp_get_code":{"code_sha256":"62a29d660a30b012"}},{"arxiv_id":"2022.findings-acl.116","paper":null,"title":"arXiv:2022.findings-acl.116","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"vistec-AI/Thai-NNER","path":"thai_nner/utils/util.py","file_url":"https://github.com/vistec-AI/Thai-NNER/blob/HEAD/thai_nner/utils/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb3e67ec54bb65e3","mcp_get_code":{"code_sha256":"bb3e67ec54bb65e3"}},{"arxiv_id":"2022.emnlp-demos.25","paper":null,"title":"arXiv:2022.emnlp-demos.25","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LogiTorch/logitorch","path":"src/logitorch/datasets/utils.py","file_url":"https://github.com/LogiTorch/logitorch/blob/HEAD/src/logitorch/datasets/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1f22a0b83aa1ec88","mcp_get_code":{"code_sha256":"1f22a0b83aa1ec88"}},{"arxiv_id":"136950719","paper":null,"title":"arXiv:136950719","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Suo-Wei/SRCF","path":"src/utils/read_write_data.py","file_url":"https://github.com/Suo-Wei/SRCF/blob/HEAD/src/utils/read_write_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0fe25b6e95ab69ed","mcp_get_code":{"code_sha256":"0fe25b6e95ab69ed"}},{"arxiv_id":"00668","paper":null,"title":"arXiv:00668","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lliai/Auto-GAS","path":"exps/get_model_info.py","file_url":"https://github.com/lliai/Auto-GAS/blob/HEAD/exps/get_model_info.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eef30bd0f7820804","mcp_get_code":{"code_sha256":"eef30bd0f7820804"}}]}