{"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/tokenize","entry":"tokenize","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":176,"n_papers_ran":58,"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":147,"n_samples_ran":48,"n_samples_fingerprinted":14,"n_places":184,"n_places_pointer_only":62,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":17,"ran_fixture":0,"ran":31,"unverified":99},"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":"2609.15530","paper":"/paper/arxiv-2609-15530","title":"Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Kirscher/MedReason2026","path":"medreason_baseline/retrieval.py","file_url":"https://github.com/Kirscher/MedReason2026/blob/HEAD/medreason_baseline/retrieval.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":"39f7fdbe9ffb0f20","mcp_get_code":{"code_sha256":"39f7fdbe9ffb0f20"}},{"arxiv_id":"2609.13648","paper":"/paper/arxiv-2609-13648","title":"Solar Intelligence","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"jyotsnasingh11217/Solar-Intelligence","path":"build_bm25.py","file_url":"https://github.com/jyotsnasingh11217/Solar-Intelligence/blob/HEAD/build_bm25.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8d254f76a316ef23","mcp_get_code":{"code_sha256":"8d254f76a316ef23"}},{"arxiv_id":"2609.13611","paper":"/paper/arxiv-2609-13611","title":"In the Blind: Building Pseudo-References for MT Evaluation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"surrey-nlp/PseudoRef","path":"pseudoref/diagnostics.py","file_url":"https://github.com/surrey-nlp/PseudoRef/blob/HEAD/pseudoref/diagnostics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7a46793afd47ec22","mcp_get_code":{"code_sha256":"7a46793afd47ec22"}},{"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":"src/bite2text/eval/gc_metrics.py","file_url":"https://github.com/GIND123/ODIN_toothfairy4/blob/HEAD/src/bite2text/eval/gc_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb2d7f0fe0f03ad9","mcp_get_code":{"code_sha256":"bb2d7f0fe0f03ad9"}},{"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/evaluate_text_quality.py","file_url":"https://github.com/18277390221/EmoStance/blob/HEAD/src/latent_stance_control/evaluate_text_quality.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6e3fb7b29530122","mcp_get_code":{"code_sha256":"c6e3fb7b29530122"}},{"arxiv_id":"2608.21867","paper":"/paper/arxiv-2608-21867","title":"MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"whyyyyy123/MemGuard","path":"src/memguard/memory/governance.py","file_url":"https://github.com/whyyyyy123/MemGuard/blob/HEAD/src/memguard/memory/governance.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":"5f9acd760a957490","mcp_get_code":{"code_sha256":"5f9acd760a957490"}},{"arxiv_id":"2608.06589","paper":"/paper/arxiv-2608-06589","title":"Beyond \"AI Language\": The case for the idiolectal nature of LLM output","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"fsu-nlp/ai-idiolects","path":"src/aiidiolects/compare_fingerprints.py","file_url":"https://github.com/fsu-nlp/ai-idiolects/blob/HEAD/src/aiidiolects/compare_fingerprints.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2efd9cc21506b21","mcp_get_code":{"code_sha256":"e2efd9cc21506b21"}},{"arxiv_id":"2607.23588","paper":"/paper/arxiv-2607-23588","title":"JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"LYL1015/JarvisHub","path":"apps/agents-cli/emp_code/scrape/component_card_index.py","file_url":"https://github.com/LYL1015/JarvisHub/blob/HEAD/apps/agents-cli/emp_code/scrape/component_card_index.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":"722059afd24746a1","mcp_get_code":{"code_sha256":"722059afd24746a1"}},{"arxiv_id":"2607.20833","paper":"/paper/arxiv-2607-20833","title":"ReFact: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"NEUIR/REFACT","path":"verl/verl/utils/reward_score/evdience_reward.py","file_url":"https://github.com/NEUIR/REFACT/blob/HEAD/verl/verl/utils/reward_score/evdience_reward.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81a9940880b8ee28","mcp_get_code":{"code_sha256":"81a9940880b8ee28"}},{"arxiv_id":"2607.00605","paper":"/paper/arxiv-2607-00605","title":"Auditing Forgetting in Limited Memory Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"raeesiarya/LMLMAudit","path":"src/lmlm-audit/run_audit.py","file_url":"https://github.com/raeesiarya/LMLMAudit/blob/HEAD/src/lmlm-audit/run_audit.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56c931802f771660","mcp_get_code":{"code_sha256":"56c931802f771660"}},{"arxiv_id":"2606.26979","paper":"/paper/arxiv-2606-26979","title":"How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"mathieu0905/Code-Anchor","path":"evaluation/compute_lexical_similarity.py","file_url":"https://github.com/mathieu0905/Code-Anchor/blob/HEAD/evaluation/compute_lexical_similarity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0ec01bca2dc31602","mcp_get_code":{"code_sha256":"0ec01bca2dc31602"}},{"arxiv_id":"2606.25152","paper":"/paper/arxiv-2606-25152","title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"kkr36/llm_detection","path":"arxiv/inference_set_rewrite/analyze_ngram_overlap.py","file_url":"https://github.com/kkr36/llm_detection/blob/HEAD/arxiv/inference_set_rewrite/analyze_ngram_overlap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ebef45186043c5f8","mcp_get_code":{"code_sha256":"ebef45186043c5f8"}},{"arxiv_id":"2606.03391","paper":"/paper/arxiv-2606-03391","title":"When Model Merging Breaks Routing: Training-Free Calibration for MoE","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"huangcb01/HARC","path":"src/merge_method/fisher.py","file_url":"https://github.com/huangcb01/HARC/blob/HEAD/src/merge_method/fisher.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"839be7ab6b2364ee","mcp_get_code":{"code_sha256":"839be7ab6b2364ee"}},{"arxiv_id":"2605.27631","paper":"/paper/arxiv-2605-27631","title":"Poison with Style: A Practical Poisoning Attack on Code Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"khangtran2020/pws","path":"src/vllm_pred.py","file_url":"https://github.com/khangtran2020/pws/blob/HEAD/src/vllm_pred.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5bc6e69d2f799430","mcp_get_code":{"code_sha256":"5bc6e69d2f799430"}},{"arxiv_id":"2605.23826","paper":"/paper/arxiv-2605-23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"michalsr/ToolMerge","path":"toolmerge/merging.py","file_url":"https://github.com/michalsr/ToolMerge/blob/HEAD/toolmerge/merging.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bd94326a00de8bb4","mcp_get_code":{"code_sha256":"bd94326a00de8bb4"}},{"arxiv_id":"2605.22498","paper":"/paper/arxiv-2605-22498","title":"The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"sheneman/neural_compiler","path":"neural_compiler/parser/scheme_parser.py","file_url":"https://github.com/sheneman/neural_compiler/blob/HEAD/neural_compiler/parser/scheme_parser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe3db154d980e1cd","mcp_get_code":{"code_sha256":"fe3db154d980e1cd"}},{"arxiv_id":"2605.15467","paper":"/paper/arxiv-2605-15467","title":"MasonNLP at MEDIQA-SYNUR 2026: Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"AHMRezaul/MEDIQA-SYNUR-2026","path":"llama/rag.py","file_url":"https://github.com/AHMRezaul/MEDIQA-SYNUR-2026/blob/HEAD/llama/rag.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3c3053082b8a558","mcp_get_code":{"code_sha256":"d3c3053082b8a558"}},{"arxiv_id":"2605.11396","paper":"/paper/arxiv-2605-11396","title":"MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"YupengSu/MuonQ","path":"src/data_utils.py","file_url":"https://github.com/YupengSu/MuonQ/blob/HEAD/src/data_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":"55ccea02961066a2","mcp_get_code":{"code_sha256":"55ccea02961066a2"}},{"arxiv_id":"2605.08898","paper":"/paper/arxiv-2605-08898","title":"LLM-Agnostic Semantic Representation Attack","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"JiaweiLian/SRA","path":"baselines/sra/utils.py","file_url":"https://github.com/JiaweiLian/SRA/blob/HEAD/baselines/sra/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab33e2c8c310ea21","mcp_get_code":{"code_sha256":"ab33e2c8c310ea21"}},{"arxiv_id":"2605.07158","paper":"/paper/arxiv-2605-07158","title":"Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"junseon-yoo/topic-not-agenda","path":"code/eval/lexical_divergence.py","file_url":"https://github.com/junseon-yoo/topic-not-agenda/blob/HEAD/code/eval/lexical_divergence.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac9b1a0705cfa5b0","mcp_get_code":{"code_sha256":"ac9b1a0705cfa5b0"}},{"arxiv_id":"2604.11152","paper":"/paper/arxiv-2604-11152","title":"SHARE: Social-Humanities AI for Research and Education","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"allenai/s2_fos","path":"src/s2_fos/training/open_ai_prompts.py","file_url":"https://github.com/allenai/s2_fos/blob/HEAD/src/s2_fos/training/open_ai_prompts.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":"64b3241c045709a6","mcp_get_code":{"code_sha256":"64b3241c045709a6"}},{"arxiv_id":"2604.04518","paper":"/paper/arxiv-2604-04518","title":"Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional nonrobustness and how to fix them","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kohpangwei/group_DRO","path":"dataset_scripts/generate_multinli.py","file_url":"https://github.com/kohpangwei/group_DRO/blob/HEAD/dataset_scripts/generate_multinli.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ef9ae2541d2ae3e","mcp_get_code":{"code_sha256":"7ef9ae2541d2ae3e"}},{"arxiv_id":"2604.02215","paper":"/paper/arxiv-2604-02215","title":"Universal Hypernetworks for Arbitrary Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Xuanfeng-Zhou/UHN","path":"dataset/text_dataset.py","file_url":"https://github.com/Xuanfeng-Zhou/UHN/blob/HEAD/dataset/text_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"093adedba6fb6692","mcp_get_code":{"code_sha256":"093adedba6fb6692"}},{"arxiv_id":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"training/influence/get_validation_dataset.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/training/influence/get_validation_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d4f58c63866080e","mcp_get_code":{"code_sha256":"5d4f58c63866080e"}},{"arxiv_id":"2603.12478","paper":"/paper/arxiv-2603-12478","title":"Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"rujiewu/GDO","path":"gdo/extract_six_metrics.py","file_url":"https://github.com/rujiewu/GDO/blob/HEAD/gdo/extract_six_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50bcada7381a2399","mcp_get_code":{"code_sha256":"50bcada7381a2399"}},{"arxiv_id":"2602.08351","paper":"/paper/arxiv-2602-08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"princeton-nlp/LESS","path":"less/data_selection/get_validation_dataset.py","file_url":"https://github.com/princeton-nlp/LESS/blob/HEAD/less/data_selection/get_validation_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d4f58c63866080e","mcp_get_code":{"code_sha256":"5d4f58c63866080e"}},{"arxiv_id":"2602.02522","paper":"/paper/arxiv-2602-02522","title":"IMU-1: Sample-Efficient Pre-training of Small Language Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"thepowerfuldeez/sample_efficient_gpt","path":"sample_efficient_gpt/evals/chat_web.py","file_url":"https://github.com/thepowerfuldeez/sample_efficient_gpt/blob/HEAD/sample_efficient_gpt/evals/chat_web.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e22c143139d965f","mcp_get_code":{"code_sha256":"4e22c143139d965f"}},{"arxiv_id":"2602.01951","paper":"/paper/arxiv-2602-01951","title":"Enabling Progressive Whole-slide Image Analysis with Multi-scale Pyramidal Network","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"mahmoodlab/CONCH","path":"conch/open_clip_custom/custom_tokenizer.py","file_url":"https://github.com/mahmoodlab/CONCH/blob/HEAD/conch/open_clip_custom/custom_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"848bfe2419fbf48a","mcp_get_code":{"code_sha256":"848bfe2419fbf48a"}},{"arxiv_id":"2601.15429","paper":"/paper/arxiv-2601-15429","title":"Domain-Specific Knowledge Graphs in RAG-Enhanced Healthcare LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"sydneyanuyah/RAGComparison","path":"artifacts/csv_abstract_tokenizer.py","file_url":"https://github.com/sydneyanuyah/RAGComparison/blob/HEAD/artifacts/csv_abstract_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d44e9d4930fe69a","mcp_get_code":{"code_sha256":"6d44e9d4930fe69a"}},{"arxiv_id":"2601.06992","paper":"/paper/arxiv-2601-06992","title":"FINCARDS: Card-Based Analyst Reranking for Financial Document Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"XanderZhou2022/FINCARDS","path":"pipeline/stage1_lexical_bm25.py","file_url":"https://github.com/XanderZhou2022/FINCARDS/blob/HEAD/pipeline/stage1_lexical_bm25.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2ae5f9c473e7850b","mcp_get_code":{"code_sha256":"2ae5f9c473e7850b"}},{"arxiv_id":"2510.22860","paper":"/paper/arxiv-2510-22860","title":"Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"calclavia/tal-asrd","path":"tal/alignment/aeneas.py","file_url":"https://github.com/calclavia/tal-asrd/blob/HEAD/tal/alignment/aeneas.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0e80b855a08c984","mcp_get_code":{"code_sha256":"d0e80b855a08c984"}},{"arxiv_id":"2509.17289","paper":"/paper/arxiv-2509-17289","title":"Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"KaushikMahmud/CoDe-KG_EMNLP_2025","path":"CoDe-KG/tokenize_paper.py","file_url":"https://github.com/KaushikMahmud/CoDe-KG_EMNLP_2025/blob/HEAD/CoDe-KG/tokenize_paper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f407977ea730a68c","mcp_get_code":{"code_sha256":"f407977ea730a68c"}},{"arxiv_id":"2508.16867","paper":"/paper/arxiv-2508-16867","title":"QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgments","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"GRAAL-Research/QFrCoLA","path":"article_src/dataset_analysis_cola_datasets.py","file_url":"https://github.com/GRAAL-Research/QFrCoLA/blob/HEAD/article_src/dataset_analysis_cola_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ee8c55dae379f18f","mcp_get_code":{"code_sha256":"ee8c55dae379f18f"}},{"arxiv_id":"2505.22810","paper":"/paper/vidtext-towards-comprehensive-evaluation-for","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shuyansy/vidtext","path":"Evaluation/Evaluation.py","file_url":"https://github.com/shuyansy/vidtext/blob/HEAD/Evaluation/Evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"74cda7b9b94dbee6","mcp_get_code":{"code_sha256":"74cda7b9b94dbee6"}},{"arxiv_id":"2505.17063","paper":"/paper/synthetic-data-rl-task-definition-is-all-you","title":"Synthetic Data RL: Task Definition Is All You Need","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gydpku/data_synthesis_rl","path":"TinyZero/retriever.py","file_url":"https://github.com/gydpku/data_synthesis_rl/blob/HEAD/TinyZero/retriever.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":"41f93bba51be41cf","mcp_get_code":{"code_sha256":"41f93bba51be41cf"}},{"arxiv_id":"2505.14305","paper":"/paper/jolt-sql-joint-loss-tuning-of-text-to-sql","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Songjw133/JOLT-SQL","path":"test_suite_sql_eval/process_sql.py","file_url":"https://github.com/Songjw133/JOLT-SQL/blob/HEAD/test_suite_sql_eval/process_sql.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":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2505.13000","paper":"/paper/dualcodec-a-low-frame-rate-semantically-1","title":"DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":"archive","repo":"jiaqili3/DualCodec","path":"dualcodec/dataset/processor.py","file_url":"https://github.com/jiaqili3/DualCodec/blob/HEAD/dualcodec/dataset/processor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06cc7e2f6e744cda","mcp_get_code":{"code_sha256":"06cc7e2f6e744cda"}},{"arxiv_id":"2504.08600","paper":"/paper/sql-r1-training-natural-language-to-sql","title":"SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":"archive","repo":"IDEA-FinAI/SQL-R1","path":"src/evaluations/spider1_evaluations/src/process_sql.py","file_url":"https://github.com/IDEA-FinAI/SQL-R1/blob/HEAD/src/evaluations/spider1_evaluations/src/process_sql.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":"b72b76d185b39d84","mcp_get_code":{"code_sha256":"b72b76d185b39d84"}},{"arxiv_id":"2502.11191","paper":"/paper/primus-a-pioneering-collection-of-open-source","title":"Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training","date":"2025-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/cosmopedia","path":"decontamination/decontaminate.py","file_url":"https://github.com/huggingface/cosmopedia/blob/HEAD/decontamination/decontaminate.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":"9b49243ad0df4e21","mcp_get_code":{"code_sha256":"9b49243ad0df4e21"}},{"arxiv_id":"2412.17646","paper":"/paper/rate-of-model-collapse-in-recursive-training","title":"Rate of Model Collapse in Recursive Training","date":"2024-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"berserank/rate-of-model-collapse","path":"ngram_sim.py","file_url":"https://github.com/berserank/rate-of-model-collapse/blob/HEAD/ngram_sim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc84e4715773bdc9","mcp_get_code":{"code_sha256":"bc84e4715773bdc9"}},{"arxiv_id":"2412.16620","paper":"/paper/a-large-scale-empirical-study-on-fine-tuning","title":"A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"iSEngLab/LLM4UT_Empirical","path":"Finetune_Script/decoder_ag_main.py","file_url":"https://github.com/iSEngLab/LLM4UT_Empirical/blob/HEAD/Finetune_Script/decoder_ag_main.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":"cadd56f46fae79b8","mcp_get_code":{"code_sha256":"cadd56f46fae79b8"}},{"arxiv_id":"2412.07786","paper":"/paper/towards-agentic-schema-refinement","title":"Towards Agentic Schema Refinement","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agapiR/agentic-semantic-layer","path":"src/process_sql.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2411.15102","paper":"/paper/attribot-a-bag-of-tricks-for-efficiently","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","date":"2024-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"r-three/AttriBoT","path":"context_attribution/model_utils.py","file_url":"https://github.com/r-three/AttriBoT/blob/HEAD/context_attribution/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a40bf61a5a9fd27","mcp_get_code":{"code_sha256":"0a40bf61a5a9fd27"}},{"arxiv_id":"2411.06424","paper":"/paper/ablation-is-not-enough-to-emulate-dpo-how","title":"Beyond Toxic Neurons: A Mechanistic Analysis of DPO for Toxicity Reduction","date":"2024-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yushi-y/dpo-toxic-neurons","path":"evaluation/eval_utils.py","file_url":"https://github.com/yushi-y/dpo-toxic-neurons/blob/HEAD/evaluation/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a98f49d7c56acc9","mcp_get_code":{"code_sha256":"1a98f49d7c56acc9"}},{"arxiv_id":"2410.13175","paper":"/paper/tcp-diffusion-a-multi-modal-diffusion-model","title":"TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zjut-MultimediaPlus/TCP-Diffusion","path":"video_diffusion_pytorch/rainfall_diffusion_F4_E1ifs_0316.py","file_url":"https://github.com/Zjut-MultimediaPlus/TCP-Diffusion/blob/HEAD/video_diffusion_pytorch/rainfall_diffusion_F4_E1ifs_0316.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e202ebb26added6","mcp_get_code":{"code_sha256":"4e202ebb26added6"}},{"arxiv_id":"2410.09335","paper":"/paper/rethinking-data-selection-at-scale-random","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiatingyu/sft-dataselection-at-scale","path":"diverse/utils.py","file_url":"https://github.com/xiatingyu/sft-dataselection-at-scale/blob/HEAD/diverse/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8d1298ca322021e","mcp_get_code":{"code_sha256":"e8d1298ca322021e"}},{"arxiv_id":"2410.08113","paper":"/paper/robust-ai-generated-text-detection-by","title":"Robust AI-Generated Text Detection by Restricted Embeddings","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"silversolver/robustatd","path":"fit_eraser_probing_tasks.py","file_url":"https://github.com/silversolver/robustatd/blob/HEAD/fit_eraser_probing_tasks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e90d22f1d7af677","mcp_get_code":{"code_sha256":"6e90d22f1d7af677"}},{"arxiv_id":"2410.02694","paper":"/paper/helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/helmet","path":"model_utils.py","file_url":"https://github.com/princeton-nlp/helmet/blob/HEAD/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7257aebb0f11407a","mcp_get_code":{"code_sha256":"7257aebb0f11407a"}},{"arxiv_id":"2410.00263","paper":"/paper/procedure-aware-surgical-video-language","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CAMMA-public/SurgVLP","path":"surgvlp/surgvlp.py","file_url":"https://github.com/CAMMA-public/SurgVLP/blob/HEAD/surgvlp/surgvlp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c5a6406461abcfa","mcp_get_code":{"code_sha256":"2c5a6406461abcfa"}},{"arxiv_id":"2409.08258","paper":"/paper/improving-virtual-try-on-with-garment-focused","title":"Improving Virtual Try-On with Garment-focused Diffusion Models","date":"2024-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siqi0905/gardiff","path":"src/models/mask_attention.py","file_url":"https://github.com/siqi0905/gardiff/blob/HEAD/src/models/mask_attention.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"534b549a2186b672","mcp_get_code":{"code_sha256":"534b549a2186b672"}},{"arxiv_id":"2408.16345","paper":"/paper/the-unreasonable-ineffectiveness-of-nucleus","title":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","date":"2024-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukaborec/memorization-nucleus-sampling","path":"memorization/core/running_experiments.py","file_url":"https://github.com/lukaborec/memorization-nucleus-sampling/blob/HEAD/memorization/core/running_experiments.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23c893fd630bb704","mcp_get_code":{"code_sha256":"23c893fd630bb704"}},{"arxiv_id":"2408.11505","paper":"/paper/mscpt-few-shot-whole-slide-image","title":"MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanminghao/mscpt","path":"plot_heatmap.py","file_url":"https://github.com/hanminghao/mscpt/blob/HEAD/plot_heatmap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"046182617bffcc33","mcp_get_code":{"code_sha256":"046182617bffcc33"}},{"arxiv_id":"2408.07930","paper":"/paper/mag-sql-multi-agent-generative-approach-with","title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LancelotXWX/MAG-SQL","path":"evaluation/process_sql.py","file_url":"https://github.com/LancelotXWX/MAG-SQL/blob/HEAD/evaluation/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2408.03124","paper":"/paper/2408-03124","title":"CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI4Science-WestlakeU/CL_DiffPhyCon","path":"model/text.py","file_url":"https://github.com/AI4Science-WestlakeU/CL_DiffPhyCon/blob/HEAD/model/text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03dfcc33eeaff851","mcp_get_code":{"code_sha256":"03dfcc33eeaff851"}},{"arxiv_id":"2407.17011","paper":"/paper/unveiling-in-context-learning-a-coordinate","title":"Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism","date":"2024-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eit-nlp/2d-coordinate-system-for-icl","path":"task_recognition_pir.py","file_url":"https://github.com/eit-nlp/2d-coordinate-system-for-icl/blob/HEAD/task_recognition_pir.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b9aa70482de54509","mcp_get_code":{"code_sha256":"b9aa70482de54509"}},{"arxiv_id":"2407.15235","paper":"/paper/tagcos-task-agnostic-gradient-clustered","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2003pro/tagcos","path":"data_selection/get_validation_dataset.py","file_url":"https://github.com/2003pro/tagcos/blob/HEAD/data_selection/get_validation_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5d4f58c63866080e","mcp_get_code":{"code_sha256":"5d4f58c63866080e"}},{"arxiv_id":"2407.09835","paper":"/paper/investigating-low-rank-training-in","title":"Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis","date":"2024-07-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CLAIRE-Labo/StructuredFFN","path":"src/utils/refinedweb_llama.py","file_url":"https://github.com/CLAIRE-Labo/StructuredFFN/blob/HEAD/src/utils/refinedweb_llama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c25271fe6f1f40f","mcp_get_code":{"code_sha256":"6c25271fe6f1f40f"}},{"arxiv_id":"2407.03856","paper":"/paper/q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LAMDA-RL/Q-Adapter","path":"utils/datasets.py","file_url":"https://github.com/LAMDA-RL/Q-Adapter/blob/HEAD/utils/datasets.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":"6a216d37018e6479","mcp_get_code":{"code_sha256":"6a216d37018e6479"}},{"arxiv_id":"2407.03618","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xhluca/bm25s","path":"bm25s/tokenization.py","file_url":"https://github.com/xhluca/bm25s/blob/HEAD/bm25s/tokenization.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c70347879b998bf","mcp_get_code":{"code_sha256":"7c70347879b998bf"}},{"arxiv_id":"2406.20052","paper":"/paper/understanding-and-mitigating-language","title":"Understanding and Mitigating Language Confusion in LLMs","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"for-ai/language-confusion","path":"compute_metrics.py","file_url":"https://github.com/for-ai/language-confusion/blob/HEAD/compute_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3f7e1abc53ea4130","mcp_get_code":{"code_sha256":"3f7e1abc53ea4130"}},{"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/process_sql.py","file_url":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques/blob/HEAD/evaluations/src/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2406.07080","paper":"/paper/dara-decomposition-alignment-reasoning","title":"DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UKPLab/acl2024-DARA","path":"utils/data_utils.py","file_url":"https://github.com/UKPLab/acl2024-DARA/blob/HEAD/utils/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b51c2cec57bb498","mcp_get_code":{"code_sha256":"2b51c2cec57bb498"}},{"arxiv_id":"2406.05205","paper":"/paper/cplip-zero-shot-learning-for-histopathology","title":"CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iyyakuttiiyappan/CPLIP","path":"zeroshot_classification.py","file_url":"https://github.com/iyyakuttiiyappan/CPLIP/blob/HEAD/zeroshot_classification.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"046182617bffcc33","mcp_get_code":{"code_sha256":"046182617bffcc33"}},{"arxiv_id":"2405.04940","paper":"/paper/harnessing-the-power-of-mllms-for","title":"Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wentaotan/mllm4text-reid","path":"datasets/bases.py","file_url":"https://github.com/wentaotan/mllm4text-reid/blob/HEAD/datasets/bases.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3d862712396854e3","mcp_get_code":{"code_sha256":"3d862712396854e3"}},{"arxiv_id":"2404.18895","paper":"/paper/rscama-remote-sensing-image-change-captioning","title":"RSCaMa: Remote Sensing Image Change Captioning with State Space Model","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chen-yang-liu/rscama","path":"preprocess_data.py","file_url":"https://github.com/chen-yang-liu/rscama/blob/HEAD/preprocess_data.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":"c6e897c47140c3e2","mcp_get_code":{"code_sha256":"c6e897c47140c3e2"}},{"arxiv_id":"2404.16795","paper":"/paper/in-context-freeze-thaw-bayesian-optimization","title":"In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"automl/ifbo","path":"ifbo/surrogate.py","file_url":"https://github.com/automl/ifbo/blob/HEAD/ifbo/surrogate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2413f6e81b6146b","mcp_get_code":{"code_sha256":"d2413f6e81b6146b"}},{"arxiv_id":"2404.16789","paper":"/paper/continual-learning-of-large-language-models-a","title":"Continual Learning of Large Language Models: A Comprehensive Survey","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beyonderxx/trace","path":"metrics.py","file_url":"https://github.com/beyonderxx/trace/blob/HEAD/metrics.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":"e605721addd552ac","mcp_get_code":{"code_sha256":"e605721addd552ac"}},{"arxiv_id":"2404.04671","paper":"/paper/inferring-the-phylogeny-of-large-language","title":"PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hrl-team/PhyloLM","path":"lanlab/core/module/models/hf_models.py","file_url":"https://github.com/hrl-team/PhyloLM/blob/HEAD/lanlab/core/module/models/hf_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"02b77fb08ddcae25","mcp_get_code":{"code_sha256":"02b77fb08ddcae25"}},{"arxiv_id":"2404.04232","paper":"/paper/benchmarking-and-improving-compositional","title":"Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tqzhong/cg4mctg","path":"meta-mctg/contrastive_prefix_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/contrastive_prefix_meta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9dbd25c2cddac479","mcp_get_code":{"code_sha256":"9dbd25c2cddac479"}},{"arxiv_id":"2404.04232","paper":"/paper/benchmarking-and-improving-compositional","title":"Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tqzhong/cg4mctg","path":"meta-mctg/ctrl_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/ctrl_meta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ac6441acc40e2e","mcp_get_code":{"code_sha256":"59ac6441acc40e2e"}},{"arxiv_id":"2404.04232","paper":"/paper/benchmarking-and-improving-compositional","title":"Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tqzhong/cg4mctg","path":"meta-mctg/dcg_meta.py","file_url":"https://github.com/tqzhong/cg4mctg/blob/HEAD/meta-mctg/dcg_meta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c3ca0db0954ed64","mcp_get_code":{"code_sha256":"6c3ca0db0954ed64"}},{"arxiv_id":"2403.19654","paper":"/paper/rsmamba-remote-sensing-image-classification","title":"RSMamba: Remote Sensing Image Classification with State Space Model","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chen-yang-liu/change-agent","path":"Multi_change/preprocess_data.py","file_url":"https://github.com/chen-yang-liu/change-agent/blob/HEAD/Multi_change/preprocess_data.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":"c6e897c47140c3e2","mcp_get_code":{"code_sha256":"c6e897c47140c3e2"}},{"arxiv_id":"2403.18684","paper":"/paper/scaling-laws-for-dense-retrieval","title":"Scaling Laws For Dense Retrieval","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingtaozhan/drscale","path":"dataset.py","file_url":"https://github.com/jingtaozhan/drscale/blob/HEAD/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8927edacebe2572","mcp_get_code":{"code_sha256":"c8927edacebe2572"}},{"arxiv_id":"2403.07384","paper":"/paper/smalltolarge-s2l-scalable-data-selection-for","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigml-cs-ucla/s2l","path":"utils.py","file_url":"https://github.com/bigml-cs-ucla/s2l/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":"e8d1298ca322021e","mcp_get_code":{"code_sha256":"e8d1298ca322021e"}},{"arxiv_id":"2403.04784","paper":"/paper/analysis-of-privacy-leakage-in-federated","title":"Analysis of Privacy Leakage in Federated Large Language Models","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vunhatminh/fl_attacks","path":"LLMs/layers_attn_ldp.py","file_url":"https://github.com/vunhatminh/fl_attacks/blob/HEAD/LLMs/layers_attn_ldp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73b18550fdf42bdb","mcp_get_code":{"code_sha256":"73b18550fdf42bdb"}},{"arxiv_id":"2403.04706","paper":"/paper/common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jerrywu-code/susgen","path":"src/finetune.py","file_url":"https://github.com/jerrywu-code/susgen/blob/HEAD/src/finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"448dfa384a102a35","mcp_get_code":{"code_sha256":"448dfa384a102a35"}},{"arxiv_id":"2402.18150","paper":"/paper/unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xsc1234/info-rag","path":"training/train_info_rag.py","file_url":"https://github.com/xsc1234/info-rag/blob/HEAD/training/train_info_rag.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f49089050af8bfda","mcp_get_code":{"code_sha256":"f49089050af8bfda"}},{"arxiv_id":"2402.14903","paper":"/paper/tokenization-counts-the-impact-of","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aadityasingh/tokenizationcounts","path":"utils.py","file_url":"https://github.com/aadityasingh/tokenizationcounts/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":"06f72a4bbe59fa49","mcp_get_code":{"code_sha256":"06f72a4bbe59fa49"}},{"arxiv_id":"2402.11399","paper":"/paper/k-semstamp-a-clustering-based-semantic","title":"k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bohanhou14/semstamp","path":"paraphrase_gen_utils.py","file_url":"https://github.com/bohanhou14/semstamp/blob/HEAD/paraphrase_gen_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eed1c0b474e01b4a","mcp_get_code":{"code_sha256":"eed1c0b474e01b4a"}},{"arxiv_id":"2402.09391","paper":"/paper/llasmol-advancing-large-language-models-for","title":"LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-nlp-group/llm4chem","path":"generation.py","file_url":"https://github.com/osu-nlp-group/llm4chem/blob/HEAD/generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"adcef27608cdbd15","mcp_get_code":{"code_sha256":"adcef27608cdbd15"}},{"arxiv_id":"2402.04494","paper":"/paper/grandmaster-level-chess-without-search","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","date":"2024-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/searchless_chess","path":"src/tokenizer.py","file_url":"https://github.com/google-deepmind/searchless_chess/blob/HEAD/src/tokenizer.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":"441d1203a85b9ca6","mcp_get_code":{"code_sha256":"441d1203a85b9ca6"}},{"arxiv_id":"2402.04333","paper":"/paper/less-selecting-influential-data-for-targeted","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/less","path":"less/data_selection/get_validation_dataset.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/data_selection/get_validation_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d4f58c63866080e","mcp_get_code":{"code_sha256":"5d4f58c63866080e"}},{"arxiv_id":"2401.10353","paper":"/paper/inconsistent-dialogue-responses-and-how-to","title":"Inconsistent dialogue responses and how to recover from them","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mianzhang/cider","path":"src/utils.py","file_url":"https://github.com/mianzhang/cider/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac28a2d89a01c888","mcp_get_code":{"code_sha256":"ac28a2d89a01c888"}},{"arxiv_id":"2401.01967","paper":"/paper/a-mechanistic-understanding-of-alignment","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ajyl/dpo_toxic","path":"toxicity/eval_interventions/eval_utils.py","file_url":"https://github.com/ajyl/dpo_toxic/blob/HEAD/toxicity/eval_interventions/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":"9727f348a587c477","mcp_get_code":{"code_sha256":"9727f348a587c477"}},{"arxiv_id":"2401.01529","paper":"/paper/glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ByZ0e/Glance-Focus","path":"dataset/nextqa.py","file_url":"https://github.com/ByZ0e/Glance-Focus/blob/HEAD/dataset/nextqa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c31fe80a1b2ba813","mcp_get_code":{"code_sha256":"c31fe80a1b2ba813"}},{"arxiv_id":"2312.15698","paper":"/paper/repairllama-efficient-representations-and","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","date":"2023-12-25","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":"cadd56f46fae79b8","mcp_get_code":{"code_sha256":"cadd56f46fae79b8"}},{"arxiv_id":"2311.18681","paper":"/paper/radialog-a-large-vision-language-model-for","title":"RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chantalmp/radialog","path":"chexbert/src/bert_tokenizer.py","file_url":"https://github.com/chantalmp/radialog/blob/HEAD/chexbert/src/bert_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c98cb8be7d52c5c5","mcp_get_code":{"code_sha256":"c98cb8be7d52c5c5"}},{"arxiv_id":"2311.14109","paper":"/paper/boosting-the-power-of-small-multimodal","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","date":"2023-11-23","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":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e605721addd552ac","mcp_get_code":{"code_sha256":"e605721addd552ac"}},{"arxiv_id":"2311.08182","paper":"/paper/self-evolved-diverse-data-sampling-for","title":"Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ofa-sys/diverseevol","path":"utils.py","file_url":"https://github.com/ofa-sys/diverseevol/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":"e8d1298ca322021e","mcp_get_code":{"code_sha256":"e8d1298ca322021e"}},{"arxiv_id":"2311.01373","paper":"/paper/recognize-any-regions","title":"Recognize Any Regions","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Surrey-UPLab/Recognize-Any-Regions","path":"regionspot/modeling/clip/clip.py","file_url":"https://github.com/Surrey-UPLab/Recognize-Any-Regions/blob/HEAD/regionspot/modeling/clip/clip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fda70a3344a4ff1d","mcp_get_code":{"code_sha256":"fda70a3344a4ff1d"}},{"arxiv_id":"2310.17342","paper":"/paper/act-sql-in-context-learning-for-text-to-sql","title":"ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-lance/text2sql-gpt","path":"eval/process_sql.py","file_url":"https://github.com/x-lance/text2sql-gpt/blob/HEAD/eval/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2310.13012","paper":"/paper/h2o-open-ecosystem-for-state-of-the-art-large","title":"H2O Open Ecosystem for State-of-the-art Large Language Models","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"h2oai/h2ogpt","path":"finetune.py","file_url":"https://github.com/h2oai/h2ogpt/blob/HEAD/finetune.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":"38cae2d1ced7906a","mcp_get_code":{"code_sha256":"38cae2d1ced7906a"}},{"arxiv_id":"2310.11237","paper":"/paper/watermarking-llms-with-weight-quantization","title":"Watermarking LLMs with Weight Quantization","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"twilight92z/quantize-watermark","path":"code/sft_data.py","file_url":"https://github.com/twilight92z/quantize-watermark/blob/HEAD/code/sft_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79e4422d6f6bff4e","mcp_get_code":{"code_sha256":"79e4422d6f6bff4e"}},{"arxiv_id":"2310.11237","paper":"/paper/watermarking-llms-with-weight-quantization","title":"Watermarking LLMs with Weight Quantization","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"twilight92z/quantize-watermark","path":"code/maintain_fp32/data_processor.py","file_url":"https://github.com/twilight92z/quantize-watermark/blob/HEAD/code/maintain_fp32/data_processor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd30351922015b11","mcp_get_code":{"code_sha256":"dd30351922015b11"}},{"arxiv_id":"2310.09754","paper":"/paper/ex-fever-a-dataset-for-multi-hop-explainable","title":"EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification","date":"2023-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"77535ec3fc559506","mcp_get_code":{"code_sha256":"77535ec3fc559506"}},{"arxiv_id":"2310.04793","paper":"/paper/fingpt-instruction-tuning-benchmark-for-open","title":"FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI4Finance-Foundation/FinGPT","path":"fingpt/FinGPT_Benchmark/utils.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Benchmark/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8301984bfcfdc76","mcp_get_code":{"code_sha256":"a8301984bfcfdc76"}},{"arxiv_id":"2308.15930","paper":"/paper/llasm-large-language-and-speech-model","title":"LLaSM: Large Language and Speech Model","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linksoul-ai/llasm","path":"infer_tokenize.py","file_url":"https://github.com/linksoul-ai/llasm/blob/HEAD/infer_tokenize.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":"b2f9ced00c0053ba","mcp_get_code":{"code_sha256":"b2f9ced00c0053ba"}},{"arxiv_id":"2308.09911","paper":"/paper/noisy-correspondence-learning-for-text-to","title":"Noisy-Correspondence Learning for Text-to-Image Person Re-identification","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QinYang79/RDE","path":"2024-CVPR-RDE/datasets/bases.py","file_url":"https://github.com/QinYang79/RDE/blob/HEAD/2024-CVPR-RDE/datasets/bases.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3d862712396854e3","mcp_get_code":{"code_sha256":"3d862712396854e3"}},{"arxiv_id":"2307.12626","paper":"/paper/enhancing-human-like-multi-modal-reasoning-a","title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weijingxuan/COCO-MMR","path":"evaluations.py","file_url":"https://github.com/weijingxuan/COCO-MMR/blob/HEAD/evaluations.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e605721addd552ac","mcp_get_code":{"code_sha256":"e605721addd552ac"}},{"arxiv_id":"2307.02276","paper":"/paper/first-explore-then-exploit-meta-learning","title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"btnorman/First-Explore","path":"tiny_world/tiny_world_first_explore.py","file_url":"https://github.com/btnorman/First-Explore/blob/HEAD/tiny_world/tiny_world_first_explore.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6deaee162fc9967d","mcp_get_code":{"code_sha256":"6deaee162fc9967d"}},{"arxiv_id":"2307.00398","paper":"/paper/probvlm-probabilistic-adapter-for-frozen","title":"ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models","date":"2023-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/probvlm","path":"src/ds/_transforms.py","file_url":"https://github.com/explainableml/probvlm/blob/HEAD/src/ds/_transforms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"841979de2ba28e2f","mcp_get_code":{"code_sha256":"841979de2ba28e2f"}},{"arxiv_id":"2306.08891","paper":"/paper/interleaving-pre-trained-language-models-and","title":"Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruc-datalab/zeronl2sql","path":"get_colval_map.py","file_url":"https://github.com/ruc-datalab/zeronl2sql/blob/HEAD/get_colval_map.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d9b155996a531f8","mcp_get_code":{"code_sha256":"2d9b155996a531f8"}},{"arxiv_id":"2306.07111","paper":"/paper/linear-classifier-an-often-forgotten-baseline","title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ASUS-AICS/LibMultiLabel","path":"libmultilabel/nn/data_utils.py","file_url":"https://github.com/ASUS-AICS/LibMultiLabel/blob/HEAD/libmultilabel/nn/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":"64d887c8cf8c806c","mcp_get_code":{"code_sha256":"64d887c8cf8c806c"}},{"arxiv_id":"2305.19204","paper":"/paper/swipe-a-dataset-for-document-level","title":"SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Salesforce/simplification","path":"utils_diff.py","file_url":"https://github.com/Salesforce/simplification/blob/HEAD/utils_diff.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":"92405e3ea7567dda","mcp_get_code":{"code_sha256":"92405e3ea7567dda"}},{"arxiv_id":"2305.13921","paper":"/paper/compositional-text-to-image-synthesis-with","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPPO-Mente-Lab/attention-mask-control","path":"train_boxnet.py","file_url":"https://github.com/OPPO-Mente-Lab/attention-mask-control/blob/HEAD/train_boxnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"534b549a2186b672","mcp_get_code":{"code_sha256":"534b549a2186b672"}},{"arxiv_id":"2305.13788","paper":"/paper/can-large-language-models-infer-and-disagree","title":"Can Large Language Models Capture Dissenting Human Voices?","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/FLAN","path":"flan/preprocessors.py","file_url":"https://github.com/google-research/FLAN/blob/HEAD/flan/preprocessors.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":"a0c365753489d524","mcp_get_code":{"code_sha256":"a0c365753489d524"}},{"arxiv_id":"2305.09645","paper":"/paper/structgpt-a-general-framework-for-large","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","date":"2023-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/structgpt","path":"process_sql.py","file_url":"https://github.com/rucaibox/structgpt/blob/HEAD/process_sql.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":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2304.03307","paper":"/paper/vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","date":"2023-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TalalWasim/Vita-CLIP","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65edded4bd70a9ab","mcp_get_code":{"code_sha256":"65edded4bd70a9ab"}},{"arxiv_id":"2304.01196","paper":"/paper/baize-an-open-source-chat-model-with","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilyagusev/rulm","path":"rulm/preprocess.py","file_url":"https://github.com/ilyagusev/rulm/blob/HEAD/rulm/preprocess.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":"c02b4d79f99f3178","mcp_get_code":{"code_sha256":"c02b4d79f99f3178"}},{"arxiv_id":"2304.01091","paper":"/paper/changes-to-captions-an-attentive-network-for","title":"Changes to Captions: An Attentive Network for Remote Sensing Change Captioning","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shizhenchang/chg2cap","path":"preprocess_data.py","file_url":"https://github.com/shizhenchang/chg2cap/blob/HEAD/preprocess_data.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":"c6e897c47140c3e2","mcp_get_code":{"code_sha256":"c6e897c47140c3e2"}},{"arxiv_id":"2303.13839","paper":"/paper/hrdoc-dataset-and-baseline-method-toward","title":"HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jfma-USTC/HRDoc","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59c421bb1bb38e71","mcp_get_code":{"code_sha256":"59c421bb1bb38e71"}},{"arxiv_id":"2303.13744","paper":"/paper/conditional-image-to-video-generation-with","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","date":"2023-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nihaomiao/CVPR23_LFDM","path":"DM/modules/text.py","file_url":"https://github.com/nihaomiao/CVPR23_LFDM/blob/HEAD/DM/modules/text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"03dfcc33eeaff851","mcp_get_code":{"code_sha256":"03dfcc33eeaff851"}},{"arxiv_id":"2302.13971","paper":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntunlplab/traditional-chinese-alpaca","path":"code/finetune.py","file_url":"https://github.com/ntunlplab/traditional-chinese-alpaca/blob/HEAD/code/finetune.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":"f54de390493549bb","mcp_get_code":{"code_sha256":"f54de390493549bb"}},{"arxiv_id":"2302.13668","paper":"/paper/contrastive-video-question-answering-via","title":"Contrastive Video Question Answering via Video Graph Transformer","date":"2023-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"doc-doc/covgt","path":"util.py","file_url":"https://github.com/doc-doc/covgt/blob/HEAD/util.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":"8f17fcc079e21653","mcp_get_code":{"code_sha256":"8f17fcc079e21653"}},{"arxiv_id":"2302.00923","paper":"/paper/multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chengtan9907/mc-cot","path":"evaluation.py","file_url":"https://github.com/chengtan9907/mc-cot/blob/HEAD/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e605721addd552ac","mcp_get_code":{"code_sha256":"e605721addd552ac"}},{"arxiv_id":"2207.03509","paper":"/paper/meta-learning-the-difference-preparing-large","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","date":"2022-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/meta-learning-the-difference","path":"abstractive_summarization/src/inference.py","file_url":"https://github.com/amazon-research/meta-learning-the-difference/blob/HEAD/abstractive_summarization/src/inference.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":"966f63a47c20ae79","mcp_get_code":{"code_sha256":"966f63a47c20ae79"}},{"arxiv_id":"2206.04730","paper":"/paper/a-neural-network-architecture-for-program-1","title":"A Neural Network Architecture for Program Understanding Inspired by Human Behaviors","date":"2022-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"c2nes/javalang","path":"javalang/tokenizer.py","file_url":"https://github.com/c2nes/javalang/blob/HEAD/javalang/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"74e056a2350fa629","mcp_get_code":{"code_sha256":"74e056a2350fa629"}},{"arxiv_id":"2205.05849","paper":"/paper/e-care-a-new-dataset-for-exploring-1","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","date":"2022-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Waste-Wood/e-CARE","path":"CEQ/CEQ.py","file_url":"https://github.com/Waste-Wood/e-CARE/blob/HEAD/CEQ/CEQ.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18181b762f463b24","mcp_get_code":{"code_sha256":"18181b762f463b24"}},{"arxiv_id":"2204.11454","paper":"/paper/natural-language-to-code-translation-with","title":"Natural Language to Code Translation with Execution","date":"2022-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/mbr-exec","path":"process_sql.py","file_url":"https://github.com/facebookresearch/mbr-exec/blob/HEAD/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"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/tokenizer.py","file_url":"https://github.com/siddharthverma314/chai-naacl-2022/blob/HEAD/cocoa/core/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"702b27974999a98a","mcp_get_code":{"code_sha256":"702b27974999a98a"}},{"arxiv_id":"2110.01799","paper":"/paper/contractnli-a-dataset-for-document-level","title":"ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stanfordnlp/contract-nli-bert","path":"contract_nli/dataset/encoder.py","file_url":"https://github.com/stanfordnlp/contract-nli-bert/blob/HEAD/contract_nli/dataset/encoder.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":"e6cc06f761aa91b0","mcp_get_code":{"code_sha256":"e6cc06f761aa91b0"}},{"arxiv_id":"2109.11797","paper":"/paper/cpt-colorful-prompt-tuning-for-pre-trained","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","date":"2021-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/cpt","path":"Oscar/oscar/datasets/refcoco_fsl_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/refcoco_fsl_cpt_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ab756d02fb91e21","mcp_get_code":{"code_sha256":"7ab756d02fb91e21"}},{"arxiv_id":"2109.11797","paper":"/paper/cpt-colorful-prompt-tuning-for-pre-trained","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","date":"2021-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/cpt","path":"Oscar/oscar/datasets/vg_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/vg_cpt_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a1867725d8d31b1","mcp_get_code":{"code_sha256":"0a1867725d8d31b1"}},{"arxiv_id":"2109.07263","paper":"/paper/end-to-end-learning-of-flowchart-grounded","title":"End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs","date":"2021-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dair-iitd/flonet","path":"code/flonet.py","file_url":"https://github.com/dair-iitd/flonet/blob/HEAD/code/flonet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d475f3f7be3b7523","mcp_get_code":{"code_sha256":"d475f3f7be3b7523"}},{"arxiv_id":"2109.04008","paper":"/paper/graph-based-network-with-contextualized","title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blacknoodle/tucore-gcn","path":"data.py","file_url":"https://github.com/blacknoodle/tucore-gcn/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bdbef35e308fc67","mcp_get_code":{"code_sha256":"3bdbef35e308fc67"}},{"arxiv_id":"2109.03158","paper":"/paper/idiosyncratic-but-not-arbitrary-learning","title":"Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles","date":"2021-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lingjzhu/idiolect","path":"model_roberta_self_attention.py","file_url":"https://github.com/lingjzhu/idiolect/blob/HEAD/model_roberta_self_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35b4200a9d6d89aa","mcp_get_code":{"code_sha256":"35b4200a9d6d89aa"}},{"arxiv_id":"2107.05330","paper":"/paper/personalized-federated-learning-via","title":"Sparse Personalized Federated Learning","date":"2021-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenh06/fl-sim","path":"fl_sim/models/tokenizers.py","file_url":"https://github.com/wenh06/fl-sim/blob/HEAD/fl_sim/models/tokenizers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4e470b6aa2608392","mcp_get_code":{"code_sha256":"4e470b6aa2608392"}},{"arxiv_id":"2106.14463","paper":"/paper/radgraph-extracting-clinical-entities-and","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","date":"2021-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rajpurkarlab/cxr-report-metric","path":"CXRMetric/CheXbert/src/bert_tokenizer.py","file_url":"https://github.com/rajpurkarlab/cxr-report-metric/blob/HEAD/CXRMetric/CheXbert/src/bert_tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c98cb8be7d52c5c5","mcp_get_code":{"code_sha256":"c98cb8be7d52c5c5"}},{"arxiv_id":"2106.02227","paper":"/paper/conversations-are-not-flat-modeling-the","title":"Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictnlp/DialoFlow","path":"FlowScore/flow_score.py","file_url":"https://github.com/ictnlp/DialoFlow/blob/HEAD/FlowScore/flow_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac28a2d89a01c888","mcp_get_code":{"code_sha256":"ac28a2d89a01c888"}},{"arxiv_id":"2106.01561","paper":"/paper/can-generative-pre-trained-language-models","title":"Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangcunxiang/Can-PLM-Serve-as-KB-for-CBQA","path":"evals/rank_cor-ques_in_train.py","file_url":"https://github.com/wangcunxiang/Can-PLM-Serve-as-KB-for-CBQA/blob/HEAD/evals/rank_cor-ques_in_train.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":"352a0a2908125997","mcp_get_code":{"code_sha256":"352a0a2908125997"}},{"arxiv_id":"2106.01093","paper":"/paper/lgesql-line-graph-enhanced-text-to-sql-model","title":"LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rhythmcao/text2sql-lgesql","path":"process_sql.py","file_url":"https://github.com/rhythmcao/text2sql-lgesql/blob/HEAD/process_sql.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":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2105.12655","paper":"/paper/project-codenet-a-large-scale-ai-for-code","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","date":"2021-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/Project_CodeNet","path":"model-experiments/masked-language-model/infer.py","file_url":"https://github.com/IBM/Project_CodeNet/blob/HEAD/model-experiments/masked-language-model/infer.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":"2eea921b0bf4fe00","mcp_get_code":{"code_sha256":"2eea921b0bf4fe00"}},{"arxiv_id":"2102.08633","paper":"/paper/open-retrieval-conversational-machine-reading","title":"Open-Retrieval Conversational Machine Reading","date":"2021-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"77535ec3fc559506","mcp_get_code":{"code_sha256":"77535ec3fc559506"}},{"arxiv_id":"2010.10042","paper":"/paper/improving-factual-completeness-and","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","date":"2020-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ysmiura/ifcc","path":"eval_prf.py","file_url":"https://github.com/ysmiura/ifcc/blob/HEAD/eval_prf.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":"0b1d99654ca7d814","mcp_get_code":{"code_sha256":"0b1d99654ca7d814"}},{"arxiv_id":"2010.09954","paper":"/paper/generating-strategic-dialogue-for-negotiation","title":"Improving Dialog Systems for Negotiation with Personality Modeling","date":"2020-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/NegotiationToM","path":"cocoa/core/tokenizer.py","file_url":"https://github.com/princeton-nlp/NegotiationToM/blob/HEAD/cocoa/core/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"702b27974999a98a","mcp_get_code":{"code_sha256":"702b27974999a98a"}},{"arxiv_id":"2010.03790","paper":"/paper/text-based-rl-agents-with-commonsense","title":"Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/commonsense-rl","path":"utils/extractor.py","file_url":"https://github.com/IBM/commonsense-rl/blob/HEAD/utils/extractor.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":"250f091f8f3d5d75","mcp_get_code":{"code_sha256":"250f091f8f3d5d75"}},{"arxiv_id":"2006.15955","paper":"/paper/a-transformer-based-joint-encoding-for-1","title":"A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis","date":"2020-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jbdel/MOSEI_UMONS","path":"utils/tokenize.py","file_url":"https://github.com/jbdel/MOSEI_UMONS/blob/HEAD/utils/tokenize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4bb9800aadeac37f","mcp_get_code":{"code_sha256":"4bb9800aadeac37f"}},{"arxiv_id":"2005.09067","paper":"/paper/question-driven-summarization-of-answers-to","title":"Question-Driven Summarization of Answers to Consumer Health Questions","date":"2020-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saverymax/qdriven-chiqa-summarization","path":"evaluation/summarization_evaluation.py","file_url":"https://github.com/saverymax/qdriven-chiqa-summarization/blob/HEAD/evaluation/summarization_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"dce7bc6407c7785b","mcp_get_code":{"code_sha256":"dce7bc6407c7785b"}},{"arxiv_id":"2004.08056","paper":"/paper/dialogue-based-relation-extraction","title":"Dialogue-Based Relation Extraction","date":"2020-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpdata/dialogre","path":"bert/run_classifier.py","file_url":"https://github.com/nlpdata/dialogre/blob/HEAD/bert/run_classifier.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1af3bee20f833832","mcp_get_code":{"code_sha256":"1af3bee20f833832"}},{"arxiv_id":"2002.00163","paper":"/paper/bridging-text-and-video-a-universal","title":"Bridging Text and Video: A Universal Multimodal Transformer for Video-Audio Scene-Aware Dialog","date":"2020-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ictnlp/DSTC8-AVSD","path":"dataset.py","file_url":"https://github.com/ictnlp/DSTC8-AVSD/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a891e00701aa131","mcp_get_code":{"code_sha256":"6a891e00701aa131"}},{"arxiv_id":"1911.12986","paper":"/paper/merging-weak-and-active-supervision-for","title":"Merging Weak and Active Supervision for Semantic Parsing","date":"2019-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"niansong1996/wassp","path":"nsm/nlp_utils.py","file_url":"https://github.com/niansong1996/wassp/blob/HEAD/nsm/nlp_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":"4fb20ccedc18c760","mcp_get_code":{"code_sha256":"4fb20ccedc18c760"}},{"arxiv_id":"1911.06311","paper":"/paper/sato-contextual-semantic-type-detection-in","title":"Sato: Contextual Semantic Type Detection in Tables","date":"2019-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megagonlabs/sato","path":"topic_model/train_LDA.py","file_url":"https://github.com/megagonlabs/sato/blob/HEAD/topic_model/train_LDA.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":"b8dfe1a304802343","mcp_get_code":{"code_sha256":"b8dfe1a304802343"}},{"arxiv_id":"1911.04942","paper":"/paper/rat-sql-relation-aware-schema-encoding-and-1","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","date":"2019-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Microsoft/rat-sql","path":"ratsql/datasets/spider_lib/process_sql.py","file_url":"https://github.com/Microsoft/rat-sql/blob/HEAD/ratsql/datasets/spider_lib/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"1911.02896","paper":"/paper/contextualized-sparse-representation-with-1","title":"Contextualized Sparse Representations for Real-Time Open-Domain Question Answering","date":"2019-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhyuklee/sparc","path":"build_tfidf.py","file_url":"https://github.com/jhyuklee/sparc/blob/HEAD/build_tfidf.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":"77535ec3fc559506","mcp_get_code":{"code_sha256":"77535ec3fc559506"}},{"arxiv_id":"1911.01545","paper":"/paper/memory-augmented-recursive-neural-networks","title":"Compositional Generalization with Tree Stack Memory Units","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maxwells-daemons/compositional-learning-experiments","path":"compositional_learning_experiments/data.py","file_url":"https://github.com/maxwells-daemons/compositional-learning-experiments/blob/HEAD/compositional_learning_experiments/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":"c4a020fd6fb7b54b","mcp_get_code":{"code_sha256":"c4a020fd6fb7b54b"}},{"arxiv_id":"1907.09190","paper":"/paper/eli5-long-form-question-answering","title":"ELI5: Long Form Question Answering","date":"2019-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ivabojic/sleepqa","path":"utils/f1_score.py","file_url":"https://github.com/ivabojic/sleepqa/blob/HEAD/utils/f1_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"30cc0698334579ce","mcp_get_code":{"code_sha256":"30cc0698334579ce"}},{"arxiv_id":"1906.06606","paper":"/paper/multi-hop-paragraph-retrieval-for-open-domain","title":"Multi-Hop Paragraph Retrieval for Open-Domain Question Answering","date":"2019-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yairf11/MUPPET","path":"hotpot/encoding/iterative_encoding_retrieval_batch.py","file_url":"https://github.com/yairf11/MUPPET/blob/HEAD/hotpot/encoding/iterative_encoding_retrieval_batch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"77535ec3fc559506","mcp_get_code":{"code_sha256":"77535ec3fc559506"}},{"arxiv_id":"1904.03971","paper":"/paper/jointly-measuring-diversity-and-quality-in","title":"Jointly Measuring Diversity and Quality in Text Generation Models","date":"2019-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Danial-Alh/fast-bleu","path":"old_metrics/utils.py","file_url":"https://github.com/Danial-Alh/fast-bleu/blob/HEAD/old_metrics/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba61bc7fc6c3ca92","mcp_get_code":{"code_sha256":"ba61bc7fc6c3ca92"}},{"arxiv_id":"1902.00038","paper":"/paper/block-bilinear-superdiagonal-fusion-for","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","date":"2019-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cadene/block.bootstrap.pytorch","path":"block/datasets/vqa_utils.py","file_url":"https://github.com/Cadene/block.bootstrap.pytorch/blob/HEAD/block/datasets/vqa_utils.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":"88ff7954b60fad9c","mcp_get_code":{"code_sha256":"88ff7954b60fad9c"}},{"arxiv_id":"1808.09637","paper":"/paper/decoupling-strategy-and-generation-in","title":"Decoupling Strategy and Generation in Negotiation Dialogues","date":"2018-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stanfordnlp/cocoa","path":"cocoa/core/tokenizer.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/core/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"702b27974999a98a","mcp_get_code":{"code_sha256":"702b27974999a98a"}},{"arxiv_id":"1807.02322","paper":"/paper/memory-augmented-policy-optimization-for","title":"Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing","date":"2018-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crazydonkey200/neural-symbolic-machines","path":"nsm/nlp_utils.py","file_url":"https://github.com/crazydonkey200/neural-symbolic-machines/blob/HEAD/nsm/nlp_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":"4fb20ccedc18c760","mcp_get_code":{"code_sha256":"4fb20ccedc18c760"}},{"arxiv_id":"1806.02847","paper":"/paper/a-simple-method-for-commonsense-reasoning","title":"A Simple Method for Commonsense Reasoning","date":"2018-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gabimelo/portuguese_wsc","path":"src/datasets_manipulation/wikidump.py","file_url":"https://github.com/gabimelo/portuguese_wsc/blob/HEAD/src/datasets_manipulation/wikidump.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"571ae1b8d8a82808","mcp_get_code":{"code_sha256":"571ae1b8d8a82808"}},{"arxiv_id":"1806.00807","paper":"/paper/learning-semantic-sentence-embeddings-using-1","title":"Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator","date":"2018-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dev-chauhan/PQG-pytorch","path":"prepro/prepro_quora.py","file_url":"https://github.com/dev-chauhan/PQG-pytorch/blob/HEAD/prepro/prepro_quora.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88ff7954b60fad9c","mcp_get_code":{"code_sha256":"88ff7954b60fad9c"}},{"arxiv_id":"1806.00692","paper":"/paper/stress-test-evaluation-for-natural-language","title":"Stress Test Evaluation for Natural Language Inference","date":"2018-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AbhilashaRavichander/NLI_StressTest","path":"gen_num_test.py","file_url":"https://github.com/AbhilashaRavichander/NLI_StressTest/blob/HEAD/gen_num_test.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e57b85ad9e2d8ee","mcp_get_code":{"code_sha256":"5e57b85ad9e2d8ee"}},{"arxiv_id":"1710.07300","paper":"/paper/figureqa-an-annotated-figure-dataset-for","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","date":"2017-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vmichals/FigureQA-baseline","path":"util/text_tools.py","file_url":"https://github.com/vmichals/FigureQA-baseline/blob/HEAD/util/text_tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"b1e4cb8f46241066","mcp_get_code":{"code_sha256":"b1e4cb8f46241066"}},{"arxiv_id":"1705.09296","paper":"/paper/neural-models-for-documents-with-metadata","title":"Neural Models for Documents with Metadata","date":"2017-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dallascard/scholar","path":"preprocess_data.py","file_url":"https://github.com/dallascard/scholar/blob/HEAD/preprocess_data.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":"9bbb1555c4d9140d","mcp_get_code":{"code_sha256":"9bbb1555c4d9140d"}},{"arxiv_id":"1612.03969","paper":"/paper/tracking-the-world-state-with-recurrent","title":"Tracking the World State with Recurrent Entity Networks","date":"2016-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jimfleming/recurrent-entity-networks","path":"entity_networks/prep_data.py","file_url":"https://github.com/jimfleming/recurrent-entity-networks/blob/HEAD/entity_networks/prep_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"118f16bd1bc27cd3","mcp_get_code":{"code_sha256":"118f16bd1bc27cd3"}},{"arxiv_id":"1611.01599","paper":"/paper/lipnet-end-to-end-sentence-level-lipreading","title":"LipNet: End-to-End Sentence-level Lipreading","date":"2016-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pjenpoomjai/LipNet","path":"core/decoding/spell.py","file_url":"https://github.com/pjenpoomjai/LipNet/blob/HEAD/core/decoding/spell.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":"9108c44188636656","mcp_get_code":{"code_sha256":"9108c44188636656"}},{"arxiv_id":"1610.04211","paper":"/paper/gated-end-to-end-memory-networks","title":"Gated End-to-End Memory Networks","date":"2016-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cstghitpku/GateMemN2N","path":"data_utils.py","file_url":"https://github.com/cstghitpku/GateMemN2N/blob/HEAD/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":"6d27ce4e6c139f45","mcp_get_code":{"code_sha256":"6d27ce4e6c139f45"}},{"arxiv_id":"1606.07772","paper":"/paper/the-emotional-arcs-of-stories-are-dominated","title":"The emotional arcs of stories are dominated by six basic shapes","date":"2016-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andyreagan/core-stories","path":"src/build_csvs.py","file_url":"https://github.com/andyreagan/core-stories/blob/HEAD/src/build_csvs.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d17d19029a89f927","mcp_get_code":{"code_sha256":"d17d19029a89f927"}},{"arxiv_id":"1606.07356","paper":"/paper/analyzing-the-behavior-of-visual-question","title":"Analyzing the Behavior of Visual Question Answering Models","date":"2016-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akirafukui/vqa-mcb","path":"preprocess/vg_preprocessing.py","file_url":"https://github.com/akirafukui/vqa-mcb/blob/HEAD/preprocess/vg_preprocessing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"e2c645c25e14ea4b","mcp_get_code":{"code_sha256":"e2c645c25e14ea4b"}},{"arxiv_id":"1605.07683","paper":"/paper/learning-end-to-end-goal-oriented-dialog","title":"Learning End-to-End Goal-Oriented Dialog","date":"2016-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaitjo/personalized-dialog","path":"MemN2N-split-memory/data_utils.py","file_url":"https://github.com/chaitjo/personalized-dialog/blob/HEAD/MemN2N-split-memory/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":"51650307118d8e13","mcp_get_code":{"code_sha256":"51650307118d8e13"}},{"arxiv_id":"1605.07683","paper":"/paper/learning-end-to-end-goal-oriented-dialog","title":"Learning End-to-End Goal-Oriented Dialog","date":"2016-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaitjo/personalized-dialog","path":"MemN2N/data_utils.py","file_url":"https://github.com/chaitjo/personalized-dialog/blob/HEAD/MemN2N/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":"c07fae3bf9c1a51c","mcp_get_code":{"code_sha256":"c07fae3bf9c1a51c"}},{"arxiv_id":"1503.08895","paper":"/paper/end-to-end-memory-networks","title":"End-To-End Memory Networks","date":"2015-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6d27ce4e6c139f45","mcp_get_code":{"code_sha256":"6d27ce4e6c139f45"}},{"arxiv_id":"1503.08895","paper":"/paper/end-to-end-memory-networks","title":"End-To-End Memory Networks","date":"2015-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dare0021/MemN2N_Bench","path":"data_process.py","file_url":"https://github.com/dare0021/MemN2N_Bench/blob/HEAD/data_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a8a4fc29963cfdd9","mcp_get_code":{"code_sha256":"a8a4fc29963cfdd9"}},{"arxiv_id":"1503.08895","paper":"/paper/end-to-end-memory-networks","title":"End-To-End Memory Networks","date":"2015-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dare0021/MemN2N_Bench","path":"kerasTeam.py","file_url":"https://github.com/dare0021/MemN2N_Bench/blob/HEAD/kerasTeam.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dbf39005cc117d57","mcp_get_code":{"code_sha256":"dbf39005cc117d57"}},{"arxiv_id":"1503.08895","paper":"/paper/end-to-end-memory-networks","title":"End-To-End Memory Networks","date":"2015-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dare0021/MemN2N_Bench","path":"src/single_layer_v5.py","file_url":"https://github.com/dare0021/MemN2N_Bench/blob/HEAD/src/single_layer_v5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ec1ed5d99153049","mcp_get_code":{"code_sha256":"8ec1ed5d99153049"}},{"arxiv_id":"1502.05698","paper":"/paper/towards-ai-complete-question-answering-a-set","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","date":"2015-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prashil2792/Question-Answering-System-Deep-Learning","path":"memorynetwork.py","file_url":"https://github.com/prashil2792/Question-Answering-System-Deep-Learning/blob/HEAD/memorynetwork.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d27ce4e6c139f45","mcp_get_code":{"code_sha256":"6d27ce4e6c139f45"}},{"arxiv_id":"1502.03044","paper":"/paper/show-attend-and-tell-neural-image-caption","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","date":"2015-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yurayli/image_caption_pytorch","path":"tokenize_caption.py","file_url":"https://github.com/yurayli/image_caption_pytorch/blob/HEAD/tokenize_caption.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d85980a56655da31","mcp_get_code":{"code_sha256":"d85980a56655da31"}},{"arxiv_id":"1408.5882","paper":"/paper/convolutional-neural-networks-for-sentence","title":"Convolutional Neural Networks for Sentence Classification","date":"2014-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"svjan5/CNN-for-text-classification","path":"SVM/SVM-1ofVEncoding.py","file_url":"https://github.com/svjan5/CNN-for-text-classification/blob/HEAD/SVM/SVM-1ofVEncoding.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"79c1b7c0f8e87a6b","mcp_get_code":{"code_sha256":"79c1b7c0f8e87a6b"}},{"arxiv_id":"ijcai2024_0666","paper":null,"title":"arXiv:ijcai2024_0666","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"MolecularTeam/DyMol","path":"main/reinvent_cl/data_structs.py","file_url":"https://github.com/MolecularTeam/DyMol/blob/HEAD/main/reinvent_cl/data_structs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"edf6cca4482c2ae8","mcp_get_code":{"code_sha256":"edf6cca4482c2ae8"}},{"arxiv_id":"aaai_26541","paper":null,"title":"arXiv:aaai_26541","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"senticnet/SKIER","path":"dataloader_10.py","file_url":"https://github.com/senticnet/SKIER/blob/HEAD/dataloader_10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7cfb7c74fa06cfbc","mcp_get_code":{"code_sha256":"7cfb7c74fa06cfbc"}},{"arxiv_id":"aaai_26259","paper":null,"title":"arXiv:aaai_26259","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"stxupengyu/LSFA","path":"preprocess.py","file_url":"https://github.com/stxupengyu/LSFA/blob/HEAD/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19af68d67b24b2e7","mcp_get_code":{"code_sha256":"19af68d67b24b2e7"}},{"arxiv_id":"Jing_Maintaining_Reasoning_Consistency_in_Compositional_Visual_Question_Answering_CVPR_2022_paper","paper":null,"title":"arXiv:Jing_Maintaining_Reasoning_Consistency_in_Compositional_Visual_Question_Answering_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jingchenchen/ReasoningConsistency-VQA","path":"DLR/util/text_processing.py","file_url":"https://github.com/jingchenchen/ReasoningConsistency-VQA/blob/HEAD/DLR/util/text_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f487a07d02aed3ed","mcp_get_code":{"code_sha256":"f487a07d02aed3ed"}},{"arxiv_id":"2025.findings-acl.111","paper":null,"title":"arXiv:2025.findings-acl.111","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Jemoka/dropfree","path":"data.py","file_url":"https://github.com/Jemoka/dropfree/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"44a808bdf66c8e57","mcp_get_code":{"code_sha256":"44a808bdf66c8e57"}},{"arxiv_id":"2025.emnlp-main.178","paper":null,"title":"arXiv:2025.emnlp-main.178","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jieshi10/orm-sql","path":"process_sql.py","file_url":"https://github.com/jieshi10/orm-sql/blob/HEAD/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2025.acl-long.274","paper":null,"title":"arXiv:2025.acl-long.274","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HKUST-KnowComp/TEGA","path":"model/dataloader.py","file_url":"https://github.com/HKUST-KnowComp/TEGA/blob/HEAD/model/dataloader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aabb26d195a74653","mcp_get_code":{"code_sha256":"aabb26d195a74653"}},{"arxiv_id":"2024.findings-emnlp.33","paper":null,"title":"arXiv:2024.findings-emnlp.33","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"boudinfl/silk","path":"evaluate2.py","file_url":"https://github.com/boudinfl/silk/blob/HEAD/evaluate2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"caa1f9a90312ad51","mcp_get_code":{"code_sha256":"caa1f9a90312ad51"}},{"arxiv_id":"2023.findings-emnlp.1050","paper":null,"title":"arXiv:2023.findings-emnlp.1050","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nuochenpku/Orca","path":"utils/ConversationalQA_benchmark.py","file_url":"https://github.com/nuochenpku/Orca/blob/HEAD/utils/ConversationalQA_benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf3e92284eebadb9","mcp_get_code":{"code_sha256":"bf3e92284eebadb9"}},{"arxiv_id":"2023.acl-srw.19","paper":null,"title":"arXiv:2023.acl-srw.19","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nyuolab/text2table","path":"text2table/models/tokenizer.py","file_url":"https://github.com/nyuolab/text2table/blob/HEAD/text2table/models/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d61c94bb73a93185","mcp_get_code":{"code_sha256":"d61c94bb73a93185"}},{"arxiv_id":"2021.acl-long.164","paper":null,"title":"arXiv:2021.acl-long.164","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thunlp/OpenQA","path":"src/reader/predictor.py","file_url":"https://github.com/thunlp/OpenQA/blob/HEAD/src/reader/predictor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77535ec3fc559506","mcp_get_code":{"code_sha256":"77535ec3fc559506"}},{"arxiv_id":"2020.emnlp-main.697","paper":null,"title":"arXiv:2020.emnlp-main.697","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wenhuchen/KGPT","path":"preprocess/step1.py","file_url":"https://github.com/wenhuchen/KGPT/blob/HEAD/preprocess/step1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ea94455615acb971","mcp_get_code":{"code_sha256":"ea94455615acb971"}},{"arxiv_id":"2020.emnlp-main.564","paper":null,"title":"arXiv:2020.emnlp-main.564","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"WING-NUS/slsql","path":"model/process_sql.py","file_url":"https://github.com/WING-NUS/slsql/blob/HEAD/model/process_sql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a906f5de1f5971b0","mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}},{"arxiv_id":"2020.emnlp-main.315","paper":null,"title":"arXiv:2020.emnlp-main.315","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mrpeerat/SEFR_CUT","path":"sefr_cut/deepcut/deepcut.py","file_url":"https://github.com/mrpeerat/SEFR_CUT/blob/HEAD/sefr_cut/deepcut/deepcut.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f07a94fb90721993","mcp_get_code":{"code_sha256":"f07a94fb90721993"}}]}