{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/read-file","entry":"read_file","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":112,"n_papers_ran":54,"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":100,"n_samples_ran":41,"n_samples_fingerprinted":2,"n_places":118,"n_places_pointer_only":40,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":13,"ran_fixture":0,"ran":25,"unverified":59},"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":"2608.18082","paper":"/paper/arxiv-2608-18082","title":"LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"openai/tiktoken","path":"tiktoken/load.py","file_url":"https://github.com/openai/tiktoken/blob/HEAD/tiktoken/load.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9df58321185cc8d4","mcp_get_code":{"code_sha256":"9df58321185cc8d4"}},{"arxiv_id":"2607.25630","paper":"/paper/arxiv-2607-25630","title":"A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"faerber-lab/scientific-text-simplification-corpus","path":"evaluation/evaluate_simp.py","file_url":"https://github.com/faerber-lab/scientific-text-simplification-corpus/blob/HEAD/evaluation/evaluate_simp.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":"47f83b67a25a9c68","mcp_get_code":{"code_sha256":"47f83b67a25a9c68"}},{"arxiv_id":"2605.16198","paper":"/paper/arxiv-2605-16198","title":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"praal/llm-monitoring","path":"Monitoring/utils.py","file_url":"https://github.com/praal/llm-monitoring/blob/HEAD/Monitoring/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"47f83b67a25a9c68","mcp_get_code":{"code_sha256":"47f83b67a25a9c68"}},{"arxiv_id":"2605.14888","paper":"/paper/arxiv-2605-14888","title":"PROCESS-2: A Benchmark Speech Corpus for Early Cognitive Impairment Detection","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CognoSpeak/PROCESS-2","path":"codes/PROCESS2_BASELINE_class.py","file_url":"https://github.com/CognoSpeak/PROCESS-2/blob/HEAD/codes/PROCESS2_BASELINE_class.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":"f7f99c40d64ffbbf","mcp_get_code":{"code_sha256":"f7f99c40d64ffbbf"}},{"arxiv_id":"2604.19505","paper":"/paper/arxiv-2604-19505","title":"Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"xiangyi-njust/Highlight-KPE","path":"code/MDERank/mderank.py","file_url":"https://github.com/xiangyi-njust/Highlight-KPE/blob/HEAD/code/MDERank/mderank.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44bea4cd43fe906e","mcp_get_code":{"code_sha256":"44bea4cd43fe906e"}},{"arxiv_id":"2604.16625","paper":"/paper/arxiv-2604-16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"StigLidu/AdaExplore","path":"src/utils.py","file_url":"https://github.com/StigLidu/AdaExplore/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20ac9f8ab3912be1","mcp_get_code":{"code_sha256":"20ac9f8ab3912be1"}},{"arxiv_id":"2602.10793","paper":"/paper/arxiv-2602-10793","title":"Semi-Supervised Cross-Domain Imitation Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Div-Infinity/IQ-Learn","path":"iq_learn/dataset/expert_dataset.py","file_url":"https://github.com/Div-Infinity/IQ-Learn/blob/HEAD/iq_learn/dataset/expert_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b7720b032896d9e6","mcp_get_code":{"code_sha256":"b7720b032896d9e6"}},{"arxiv_id":"2601.05411","paper":"/paper/arxiv-2601-05411","title":"Glitter: Visualizing Lexical Surprisal for Readability in Administrative Texts","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ufal/Glitter","path":"src/ponk_glitter/glitter_cli.py","file_url":"https://github.com/ufal/Glitter/blob/HEAD/src/ponk_glitter/glitter_cli.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"17e42607ec525789","mcp_get_code":{"code_sha256":"17e42607ec525789"}},{"arxiv_id":"2508.20700","paper":"/paper/arxiv-2508-20700","title":"Generative Annotation for ASR Named Entity Correction","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Amiannn/Dancer","path":"src/utils.py","file_url":"https://github.com/Amiannn/Dancer/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e393c6b95fe32f0d","mcp_get_code":{"code_sha256":"e393c6b95fe32f0d"}},{"arxiv_id":"2507.10923","paper":"/paper/enhancing-safe-and-controllable-protein","title":"Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HICAI-ZJU/KPO","path":"TransE.py","file_url":"https://github.com/HICAI-ZJU/KPO/blob/HEAD/TransE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e43c371c2dabfe63","mcp_get_code":{"code_sha256":"e43c371c2dabfe63"}},{"arxiv_id":"2506.14448","paper":"/paper/how-far-can-llms-improve-from-experience","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alice1998/Test-time-Learning","path":"cumulative_setting/run_benchmark.py","file_url":"https://github.com/Alice1998/Test-time-Learning/blob/HEAD/cumulative_setting/run_benchmark.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":"1e510c4d97f6bcd0","mcp_get_code":{"code_sha256":"1e510c4d97f6bcd0"}},{"arxiv_id":"2506.14448","paper":"/paper/how-far-can-llms-improve-from-experience","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alice1998/Test-time-Learning","path":"cumulative_setting/run_benchmark_multiRound.py","file_url":"https://github.com/Alice1998/Test-time-Learning/blob/HEAD/cumulative_setting/run_benchmark_multiRound.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb7014cf8fc8729b","mcp_get_code":{"code_sha256":"bb7014cf8fc8729b"}},{"arxiv_id":"2506.09650","paper":"/paper/hopadiff-holistic-partial-aware-fourier","title":"HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KPeng9510/HopaDIFF","path":"utils.py","file_url":"https://github.com/KPeng9510/HopaDIFF/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":"2188327bf35280a1","mcp_get_code":{"code_sha256":"2188327bf35280a1"}},{"arxiv_id":"2504.20115","paper":"/paper/autop2c-an-llm-based-agent-framework-for-code","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","date":"2025-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shoushouyu/automated-paper-to-code","path":"code_gen/code_generate.py","file_url":"https://github.com/shoushouyu/automated-paper-to-code/blob/HEAD/code_gen/code_generate.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":"47f83b67a25a9c68","mcp_get_code":{"code_sha256":"47f83b67a25a9c68"}},{"arxiv_id":"2504.07952","paper":"/paper/dynamic-cheatsheet-test-time-learning-with","title":"Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"suzgunmirac/dynamic-cheatsheet","path":"run_benchmark.py","file_url":"https://github.com/suzgunmirac/dynamic-cheatsheet/blob/HEAD/run_benchmark.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":"1e510c4d97f6bcd0","mcp_get_code":{"code_sha256":"1e510c4d97f6bcd0"}},{"arxiv_id":"2412.14063","paper":"/paper/rango-adaptive-retrieval-augmented-proving","title":"Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rkthomps/coq-modeling","path":"src/data_management/line_dict.py","file_url":"https://github.com/rkthomps/coq-modeling/blob/HEAD/src/data_management/line_dict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd96465ac9f23efc","mcp_get_code":{"code_sha256":"cd96465ac9f23efc"}},{"arxiv_id":"2411.03292","paper":"/paper/interaction2code-how-far-are-we-from","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"webpai/interaction2code","path":"code/metric/metric_utils.py","file_url":"https://github.com/webpai/interaction2code/blob/HEAD/code/metric/metric_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce13f063f10284c1","mcp_get_code":{"code_sha256":"ce13f063f10284c1"}},{"arxiv_id":"2410.22660","paper":"/paper/linguistics-theory-meets-llm-code-switched","title":"Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gkuwanto/ezswitch","path":"src/utils.py","file_url":"https://github.com/gkuwanto/ezswitch/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45fb5d83e4f5edf1","mcp_get_code":{"code_sha256":"45fb5d83e4f5edf1"}},{"arxiv_id":"2410.20424","paper":"/paper/autokaggle-a-multi-agent-framework-for","title":"AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions","date":"2024-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"multimodal-art-projection/AutoKaggle","path":"utils.py","file_url":"https://github.com/multimodal-art-projection/AutoKaggle/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"85c8a669541e5326","mcp_get_code":{"code_sha256":"85c8a669541e5326"}},{"arxiv_id":"2410.12381","paper":"/paper/humaneval-v-evaluating-visual-understanding","title":"HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HumanEval-V/HumanEval-V-Benchmark","path":"utils.py","file_url":"https://github.com/HumanEval-V/HumanEval-V-Benchmark/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":"c0e3e76bb71a2cc8","mcp_get_code":{"code_sha256":"c0e3e76bb71a2cc8"}},{"arxiv_id":"2410.11061","paper":"/paper/learning-to-optimize-for-mixed-integer-non","title":"Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pnnl/neuromancer","path":"src/neuromancer/dataset.py","file_url":"https://github.com/pnnl/neuromancer/blob/HEAD/src/neuromancer/dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a41bf9e7cfefab28","mcp_get_code":{"code_sha256":"a41bf9e7cfefab28"}},{"arxiv_id":"2409.13989","paper":"/paper/2409-13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","date":"2024-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ustc-starteam/chemeval","path":"Multimodel/3_code_evaluate/1Extract.py","file_url":"https://github.com/ustc-starteam/chemeval/blob/HEAD/Multimodel/3_code_evaluate/1Extract.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d23978079d307710","mcp_get_code":{"code_sha256":"d23978079d307710"}},{"arxiv_id":"2409.03797","paper":"/paper/nestful-a-benchmark-for-evaluating-llms-on","title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/nestful","path":"src/utils.py","file_url":"https://github.com/ibm/nestful/blob/HEAD/src/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":"ba6cfefa8094dcb6","mcp_get_code":{"code_sha256":"ba6cfefa8094dcb6"}},{"arxiv_id":"2407.18078","paper":"/paper/peft-u-parameter-efficient-fine-tuning-for","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","date":"2024-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChrisIsKing/Parameter-Efficient-Personalization","path":"user_context/generate_user_profiles_n.py","file_url":"https://github.com/ChrisIsKing/Parameter-Efficient-Personalization/blob/HEAD/user_context/generate_user_profiles_n.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fded598915486828","mcp_get_code":{"code_sha256":"fded598915486828"}},{"arxiv_id":"2407.10299","paper":"/paper/follow-the-rules-reasoning-for-video-anomaly","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yuchen413/AnomalyRuler","path":"majority_smooth.py","file_url":"https://github.com/Yuchen413/AnomalyRuler/blob/HEAD/majority_smooth.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":"8e8b17d957510da6","mcp_get_code":{"code_sha256":"8e8b17d957510da6"}},{"arxiv_id":"2406.19371","paper":"/paper/suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chtmp223/suri","path":"eval/automatic/ranking.py","file_url":"https://github.com/chtmp223/suri/blob/HEAD/eval/automatic/ranking.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8f7c20be180ad75b","mcp_get_code":{"code_sha256":"8f7c20be180ad75b"}},{"arxiv_id":"2406.18846","paper":"/paper/afbench-a-large-scale-benchmark-for-airfoil","title":"AFBench: A Large-scale Benchmark for Airfoil Design","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"hitcslj/Xfoil-cal","path":"check_valid_geo.py","file_url":"https://github.com/hitcslj/Xfoil-cal/blob/HEAD/check_valid_geo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54b2c1ba109bdef5","mcp_get_code":{"code_sha256":"54b2c1ba109bdef5"}},{"arxiv_id":"2406.18533","paper":"/paper/on-scaling-up-3d-gaussian-splatting-training","title":"On Scaling Up 3D Gaussian Splatting Training","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-systems/grendel-gs","path":"analyze_statistic.py","file_url":"https://github.com/nyu-systems/grendel-gs/blob/HEAD/analyze_statistic.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":"93438892eb42697d","mcp_get_code":{"code_sha256":"93438892eb42697d"}},{"arxiv_id":"2406.12384","paper":"/paper/vrsbench-a-versatile-vision-language","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lx709/vrsbench","path":"extract_patch_json.py","file_url":"https://github.com/lx709/vrsbench/blob/HEAD/extract_patch_json.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"990ff33e4c206334","mcp_get_code":{"code_sha256":"990ff33e4c206334"}},{"arxiv_id":"2406.04601","paper":"/paper/enhancing-size-generalization-in-graph-neural","title":"Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graphminddartmouth/disgen","path":"src/graphsst2_dataset.py","file_url":"https://github.com/graphminddartmouth/disgen/blob/HEAD/src/graphsst2_dataset.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60ccd1c98038811b","mcp_get_code":{"code_sha256":"60ccd1c98038811b"}},{"arxiv_id":"2405.16584","paper":"/paper/mentalmanip-a-dataset-for-fine-grained","title":"MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"audreycs/MentalManip","path":"statistic_analysis/statistics_comparison.py","file_url":"https://github.com/audreycs/MentalManip/blob/HEAD/statistic_analysis/statistics_comparison.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"efea318b5b12f44f","mcp_get_code":{"code_sha256":"efea318b5b12f44f"}},{"arxiv_id":"2403.18447","paper":"/paper/can-language-beat-numerical-regression","title":"Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"inhwanbae/LMTrajectory","path":"utils/dataloader.py","file_url":"https://github.com/inhwanbae/LMTrajectory/blob/HEAD/utils/dataloader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"123c2031d3127cc9","mcp_get_code":{"code_sha256":"123c2031d3127cc9"}},{"arxiv_id":"2403.06833","paper":"/paper/can-llms-separate-instructions-from-data-and","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egozverev/Shold-It-Be-Executed-Or-Processed","path":"SEP_dataset/utils.py","file_url":"https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed/blob/HEAD/SEP_dataset/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e08792f2a461b463","mcp_get_code":{"code_sha256":"e08792f2a461b463"}},{"arxiv_id":"2403.06467","paper":"/paper/point-mamba-a-novel-point-cloud-backbone","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"irmvlab/point-mamba","path":"datasets/modelnet40.py","file_url":"https://github.com/irmvlab/point-mamba/blob/HEAD/datasets/modelnet40.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ddbad7728b2f62f","mcp_get_code":{"code_sha256":"1ddbad7728b2f62f"}},{"arxiv_id":"2402.16187","paper":"/paper/attacking-llm-watermarks-by-exploiting-their","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qi-pang/llm-watermark-attacks","path":"Exp-Watermark/experiments/attack_multiple_keys.py","file_url":"https://github.com/qi-pang/llm-watermark-attacks/blob/HEAD/Exp-Watermark/experiments/attack_multiple_keys.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":"fc9d1d8c92c8dd16","mcp_get_code":{"code_sha256":"fc9d1d8c92c8dd16"}},{"arxiv_id":"2402.16187","paper":"/paper/attacking-llm-watermarks-by-exploiting-their","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qi-pang/llm-watermark-attacks","path":"KGW-Watermark/attack_multiple_keys.py","file_url":"https://github.com/qi-pang/llm-watermark-attacks/blob/HEAD/KGW-Watermark/attack_multiple_keys.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":"48e3a03b6b0feb73","mcp_get_code":{"code_sha256":"48e3a03b6b0feb73"}},{"arxiv_id":"2402.15491","paper":"/paper/api-blend-a-comprehensive-corpora-for","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/api-blend","path":"grammar-based-generation/SeqSNIPS_SeqATIS-data-gen.py","file_url":"https://github.com/ibm/api-blend/blob/HEAD/grammar-based-generation/SeqSNIPS_SeqATIS-data-gen.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":"5523c76f12760fc3","mcp_get_code":{"code_sha256":"5523c76f12760fc3"}},{"arxiv_id":"2402.06221","paper":"/paper/resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ztrimus/job-llm","path":"zlm/utils/utils.py","file_url":"https://github.com/Ztrimus/job-llm/blob/HEAD/zlm/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f5c9579ef0582c29","mcp_get_code":{"code_sha256":"f5c9579ef0582c29"}},{"arxiv_id":"2402.00254","paper":"/paper/vertical-symbolic-regression-via-deep-policy","title":"Vertical Symbolic Regression via Deep Policy Gradient","date":"2024-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangnanhugo/VSR-DPG","path":"E2E/evaluate.py","file_url":"https://github.com/jiangnanhugo/VSR-DPG/blob/HEAD/E2E/evaluate.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":"40b1a20fe12de364","mcp_get_code":{"code_sha256":"40b1a20fe12de364"}},{"arxiv_id":"2402.01729","paper":"/paper/contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"David-Li0406/Contextulization-Distillation","path":"CSProm-KG/helper.py","file_url":"https://github.com/David-Li0406/Contextulization-Distillation/blob/HEAD/CSProm-KG/helper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9537cf81348be25","mcp_get_code":{"code_sha256":"f9537cf81348be25"}},{"arxiv_id":"2402.01729","paper":"/paper/contextualization-distillation-from-large","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","date":"2024-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"David-Li0406/Contextulization-Distillation","path":"KG-S2S/helper.py","file_url":"https://github.com/David-Li0406/Contextulization-Distillation/blob/HEAD/KG-S2S/helper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c005f30ead3132ac","mcp_get_code":{"code_sha256":"c005f30ead3132ac"}},{"arxiv_id":"2401.03082","paper":"/paper/umie-unified-multimodal-information","title":"UMIE: Unified Multimodal Information Extraction with Instruction Tuning","date":"2024-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZUCC-AI/UMIE","path":"src/eval_extraction.py","file_url":"https://github.com/ZUCC-AI/UMIE/blob/HEAD/src/eval_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e3a4228db43496b","mcp_get_code":{"code_sha256":"9e3a4228db43496b"}},{"arxiv_id":"2312.17120","paper":"/paper/generative-ai-for-math-part-i-mathpile-a","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","date":"2023-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GAIR-NLP/MathPile","path":"src/global_data_processing/utils.py","file_url":"https://github.com/GAIR-NLP/MathPile/blob/HEAD/src/global_data_processing/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":"b40e45d2f17838f2","mcp_get_code":{"code_sha256":"b40e45d2f17838f2"}},{"arxiv_id":"2312.11598","paper":"/paper/skilldiffuser-interpretable-hierarchical","title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","date":"2023-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liang-ZX/SkillDiffuser","path":"skilldiffuser/hrl/expert_dataset.py","file_url":"https://github.com/Liang-ZX/SkillDiffuser/blob/HEAD/skilldiffuser/hrl/expert_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15eab9eebd751706","mcp_get_code":{"code_sha256":"15eab9eebd751706"}},{"arxiv_id":"2312.03612","paper":"/paper/physical-symbolic-optimization","title":"Physical Symbolic Optimization","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cavalab/srbench","path":"experiment/read_file.py","file_url":"https://github.com/cavalab/srbench/blob/HEAD/experiment/read_file.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":"134b6bd44843ddc1","mcp_get_code":{"code_sha256":"134b6bd44843ddc1"}},{"arxiv_id":"2311.15781","paper":"/paper/increasing-coverage-and-precision-of-textual","title":"Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-kge","path":"src/evaluation/evaluate_precision.py","file_url":"https://github.com/apple/ml-kge/blob/HEAD/src/evaluation/evaluate_precision.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":"13b53a25d8f585b1","mcp_get_code":{"code_sha256":"13b53a25d8f585b1"}},{"arxiv_id":"2311.10057","paper":"/paper/the-song-describer-dataset-a-corpus-of-audio","title":"The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilaria-manco/song-describer","path":"annotation_tool/backend/utils.py","file_url":"https://github.com/ilaria-manco/song-describer/blob/HEAD/annotation_tool/backend/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"658cbcdf12d20ff3","mcp_get_code":{"code_sha256":"658cbcdf12d20ff3"}},{"arxiv_id":"2311.04934","paper":"/paper/prompt-cache-modular-attention-reuse-for-low","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-sys/prompt-cache","path":"promptcache/prompt.py","file_url":"https://github.com/yale-sys/prompt-cache/blob/HEAD/promptcache/prompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09ee7b4dcf62d65d","mcp_get_code":{"code_sha256":"09ee7b4dcf62d65d"}},{"arxiv_id":"2311.03748","paper":"/paper/unified-low-resource-sequence-labeling-by","title":"Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"psunlpgroup/fish-dip","path":"preprocess_multiwoz/extract_examples.py","file_url":"https://github.com/psunlpgroup/fish-dip/blob/HEAD/preprocess_multiwoz/extract_examples.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":"c6855e904db1e7ca","mcp_get_code":{"code_sha256":"c6855e904db1e7ca"}},{"arxiv_id":"2310.19906","paper":"/paper/interpretable-prototype-based-graph-1","title":"Interpretable Prototype-based Graph Information Bottleneck","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sang-woo-seo/pgib","path":"models/train_gnns.py","file_url":"https://github.com/sang-woo-seo/pgib/blob/HEAD/models/train_gnns.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"60ccd1c98038811b","mcp_get_code":{"code_sha256":"60ccd1c98038811b"}},{"arxiv_id":"2310.18738","paper":"/paper/tlm-token-level-masking-for-transformers","title":"TLM: Token-Level Masking for Transformers","date":"2023-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blcuicall/CCL2022-CLTC","path":"baselines/track1/eval_sent_level.py","file_url":"https://github.com/blcuicall/CCL2022-CLTC/blob/HEAD/baselines/track1/eval_sent_level.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"40a3d4e153df98ef","mcp_get_code":{"code_sha256":"40a3d4e153df98ef"}},{"arxiv_id":"2310.06245","paper":"/paper/we-are-what-we-repeatedly-do-inducing-and","title":"We are what we repeatedly do: Inducing and deploying habitual schemas in persona-based responses","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bkane2/habitual-response-generation","path":"src/util.py","file_url":"https://github.com/bkane2/habitual-response-generation/blob/HEAD/src/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2042d0318c6bf2e9","mcp_get_code":{"code_sha256":"2042d0318c6bf2e9"}},{"arxiv_id":"2310.02227","paper":"/paper/snip-bridging-mathematical-symbolic-and","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","date":"2023-10-03","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":"40b1a20fe12de364","mcp_get_code":{"code_sha256":"40b1a20fe12de364"}},{"arxiv_id":"2307.01878","paper":"/paper/kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yumeng5/WeSTClass","path":"load_data.py","file_url":"https://github.com/yumeng5/WeSTClass/blob/HEAD/load_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":"d38d5642834c1922","mcp_get_code":{"code_sha256":"d38d5642834c1922"}},{"arxiv_id":"2306.17439","paper":"/paper/provable-robust-watermarking-for-ai-generated","title":"Provable Robust Watermarking for AI-Generated Text","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuandongzhao/unigram-watermark","path":"run_generate.py","file_url":"https://github.com/xuandongzhao/unigram-watermark/blob/HEAD/run_generate.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":"f150aa699a80fbdb","mcp_get_code":{"code_sha256":"f150aa699a80fbdb"}},{"arxiv_id":"2306.03209","paper":"/paper/end-to-end-differentiable-clustering-with","title":"End-to-end Differentiable Clustering with Associative Memories","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bsaha205/clam","path":"parser.py","file_url":"https://github.com/bsaha205/clam/blob/HEAD/parser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06620495a0b9b97e","mcp_get_code":{"code_sha256":"06620495a0b9b97e"}},{"arxiv_id":"2305.18409","paper":"/paper/direction-oriented-multi-objective-learning","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","date":"2023-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-opt-lab/sdmgrad","path":"experiments/mean_rank.py","file_url":"https://github.com/ml-opt-lab/sdmgrad/blob/HEAD/experiments/mean_rank.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1cb4b9ddd1f0d15b","mcp_get_code":{"code_sha256":"1cb4b9ddd1f0d15b"}},{"arxiv_id":"2305.03045","paper":"/paper/octformer-octree-based-transformers-for-3d","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"octree-nn/octformer","path":"datasets/modelnet40.py","file_url":"https://github.com/octree-nn/octformer/blob/HEAD/datasets/modelnet40.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ddbad7728b2f62f","mcp_get_code":{"code_sha256":"1ddbad7728b2f62f"}},{"arxiv_id":"2304.14636","paper":"/paper/prenas-preferred-one-shot-learning-towards","title":"PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search","date":null,"month_inferred_from_arxiv_id":"2023-04","title_source":"archive","repo":"alibaba/lightweight-neural-architecture-search","path":"modelscope/utils/file_utils.py","file_url":"https://github.com/alibaba/lightweight-neural-architecture-search/blob/HEAD/modelscope/utils/file_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0531c04dd4901504","mcp_get_code":{"code_sha256":"0531c04dd4901504"}},{"arxiv_id":"2304.07590","paper":"/paper/self-collaboration-code-generation-via","title":"Self-collaboration Code Generation via ChatGPT","date":null,"month_inferred_from_arxiv_id":"2023-04","title_source":"archive","repo":"YihongDong/Self-collaboration-Code-Generation","path":"core/repo_tools.py","file_url":"https://github.com/YihongDong/Self-collaboration-Code-Generation/blob/HEAD/core/repo_tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bac44134ee8d1581","mcp_get_code":{"code_sha256":"bac44134ee8d1581"}},{"arxiv_id":"2304.04521","paper":"/paper/zero-shot-in-distribution-detection-in-multi","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"atsumiyai/gl-mcm","path":"utils/common.py","file_url":"https://github.com/atsumiyai/gl-mcm/blob/HEAD/utils/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65aed69fd9c43272","mcp_get_code":{"code_sha256":"65aed69fd9c43272"}},{"arxiv_id":"2302.08635","paper":"/paper/generative-causal-representation-learning-for","title":"Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting","date":"2023-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sshirahmad/GCRL","path":"trajectories.py","file_url":"https://github.com/sshirahmad/GCRL/blob/HEAD/trajectories.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"123c2031d3127cc9","mcp_get_code":{"code_sha256":"123c2031d3127cc9"}},{"arxiv_id":"2212.10140","paper":"/paper/tackling-ambiguity-with-images-improved","title":"Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthieufp/commute","path":"evaluate.py","file_url":"https://github.com/matthieufp/commute/blob/HEAD/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC-BY-SA-4.0","inline_ok":false,"code_sha256_prefix":"da8b0d32e86624aa","mcp_get_code":{"code_sha256":"da8b0d32e86624aa"}},{"arxiv_id":"2212.09713","paper":"/paper/a-probabilistic-framework-for-lifelong-test","title":"A Probabilistic Framework for Lifelong Test-Time Adaptation","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhanajitb/petal","path":"imagenet/eval_corruptionwise.py","file_url":"https://github.com/dhanajitb/petal/blob/HEAD/imagenet/eval_corruptionwise.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"253c745e2e017386","mcp_get_code":{"code_sha256":"253c745e2e017386"}},{"arxiv_id":"2212.09713","paper":"/paper/a-probabilistic-framework-for-lifelong-test","title":"A Probabilistic Framework for Lifelong Test-Time Adaptation","date":"2022-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhanajitb/petal","path":"imagenet/eval_corruptionwise_img3d.py","file_url":"https://github.com/dhanajitb/petal/blob/HEAD/imagenet/eval_corruptionwise_img3d.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee9939f76f4640cd","mcp_get_code":{"code_sha256":"ee9939f76f4640cd"}},{"arxiv_id":"2212.02437","paper":"/paper/in-context-examples-selection-for-machine","title":"In-context Examples Selection for Machine Translation","date":"2022-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sweta20/incontextmt","path":"run_metrics_eval.py","file_url":"https://github.com/sweta20/incontextmt/blob/HEAD/run_metrics_eval.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":"c211341220630f0a","mcp_get_code":{"code_sha256":"c211341220630f0a"}},{"arxiv_id":"2211.02950","paper":"/paper/the-legal-argument-reasoning-task-in-civil","title":"The Legal Argument Reasoning Task in Civil Procedure","date":"2022-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trusthlt/legal-argument-reasoning-task","path":"src/utils/load_data.py","file_url":"https://github.com/trusthlt/legal-argument-reasoning-task/blob/HEAD/src/utils/load_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":"589bffdd286844da","mcp_get_code":{"code_sha256":"589bffdd286844da"}},{"arxiv_id":"2210.07347","paper":"/paper/disentanglement-of-correlated-factors-via","title":"Disentanglement of Correlated Factors via Hausdorff Factorized Support","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/disentangling-correlated-factors","path":"multischedule.py","file_url":"https://github.com/facebookresearch/disentangling-correlated-factors/blob/HEAD/multischedule.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"daf1330a06c84169","mcp_get_code":{"code_sha256":"daf1330a06c84169"}},{"arxiv_id":"2209.12332","paper":"/paper/on-the-optimal-linear-contraction-order-for","title":"On the Optimal Linear Contraction Order of Tree Tensor Networks, and Beyond","date":null,"month_inferred_from_arxiv_id":"2022-09","title_source":"archive","repo":"stoianmihail/netzwerk","path":"src/netzwerk/spanning_tree.py","file_url":"https://github.com/stoianmihail/netzwerk/blob/HEAD/src/netzwerk/spanning_tree.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e877c22a3d08770","mcp_get_code":{"code_sha256":"0e877c22a3d08770"}},{"arxiv_id":"2207.04672","paper":"/paper/no-language-left-behind-scaling-human-1","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","date":"2022-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ragerri/antidote-projections","path":"cross-lingual-argument-mining/correction/post_processing/projection_corrections.py","file_url":"https://github.com/ragerri/antidote-projections/blob/HEAD/cross-lingual-argument-mining/correction/post_processing/projection_corrections.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":"8f9afa32c236ac4c","mcp_get_code":{"code_sha256":"8f9afa32c236ac4c"}},{"arxiv_id":"2206.09144","paper":"/paper/beyond-real-world-benchmark-datasets-an","title":"Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs","date":"2022-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seijimaekawa/empirical-study-of-gnns","path":"models/dataset_utils.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/dataset_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"623066b29237a22e","mcp_get_code":{"code_sha256":"623066b29237a22e"}},{"arxiv_id":"2204.10532","paper":"/paper/end-to-end-symbolic-regression-with","title":"End-to-end symbolic regression with transformers","date":"2022-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/symbolicregression","path":"evaluate.py","file_url":"https://github.com/facebookresearch/symbolicregression/blob/HEAD/evaluate.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":"40b1a20fe12de364","mcp_get_code":{"code_sha256":"40b1a20fe12de364"}},{"arxiv_id":"2202.01906","paper":"/paper/net-benefit-calibration-threshold-selection","title":"Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcare","date":"2022-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"som-shahlab/net_benefit_ascvd","path":"net_benefit_ascvd/experiments/train_model.py","file_url":"https://github.com/som-shahlab/net_benefit_ascvd/blob/HEAD/net_benefit_ascvd/experiments/train_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"732bae7d31477943","mcp_get_code":{"code_sha256":"732bae7d31477943"}},{"arxiv_id":"2201.12987","paper":"/paper/interpretable-and-generalizable-graph","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","date":"2022-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Graph-COM/GSAT","path":"src/datasets/graph_sst2.py","file_url":"https://github.com/Graph-COM/GSAT/blob/HEAD/src/datasets/graph_sst2.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60ccd1c98038811b","mcp_get_code":{"code_sha256":"60ccd1c98038811b"}},{"arxiv_id":"2201.12926","paper":"/paper/compositionality-as-lexical-symmetry","title":"Compositionality as Lexical Symmetry","date":"2022-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ekinakyurek/lexsym","path":"augmenter.py","file_url":"https://github.com/ekinakyurek/lexsym/blob/HEAD/augmenter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bca38980665a4fd","mcp_get_code":{"code_sha256":"0bca38980665a4fd"}},{"arxiv_id":"2201.10936","paper":"/paper/figaro-generating-symbolic-music-with-fine","title":"FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control","date":"2022-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvruette/figaro","path":"src/evaluate.py","file_url":"https://github.com/dvruette/figaro/blob/HEAD/src/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00ffe13005e97804","mcp_get_code":{"code_sha256":"00ffe13005e97804"}},{"arxiv_id":"2111.14820","paper":"/paper/towards-robust-and-adaptive-motion","title":"Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective","date":"2021-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vita-epfl/causalmotion","path":"spurious/trajectories.py","file_url":"https://github.com/vita-epfl/causalmotion/blob/HEAD/spurious/trajectories.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"123c2031d3127cc9","mcp_get_code":{"code_sha256":"123c2031d3127cc9"}},{"arxiv_id":"2110.03370","paper":"/paper/wenetspeech-a-10000-hours-multi-domain","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","date":"2021-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenet-e2e/wenetspeech","path":"toolkits/wenet/local/process_opus.py","file_url":"https://github.com/wenet-e2e/wenetspeech/blob/HEAD/toolkits/wenet/local/process_opus.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":"b7cc041a8cc401d7","mcp_get_code":{"code_sha256":"b7cc041a8cc401d7"}},{"arxiv_id":"2109.08535","paper":"/paper/simple-entity-centric-questions-challenge","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","date":"2021-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/EntityQuestions","path":"utils/ion.py","file_url":"https://github.com/princeton-nlp/EntityQuestions/blob/HEAD/utils/ion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7b94494907985b3","mcp_get_code":{"code_sha256":"e7b94494907985b3"}},{"arxiv_id":"2109.07095","paper":"/paper/towards-document-level-paraphrase-generation","title":"Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering","date":"2021-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"l-zhe/corpg","path":"eval/bleu.py","file_url":"https://github.com/l-zhe/corpg/blob/HEAD/eval/bleu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"40eb3071da4a388b","mcp_get_code":{"code_sha256":"40eb3071da4a388b"}},{"arxiv_id":"2109.04513","paper":"/paper/filling-the-gaps-in-ancient-akkadian-texts-a","title":"Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SLAB-NLP/Akk","path":"RAW/work_on_files.py","file_url":"https://github.com/SLAB-NLP/Akk/blob/HEAD/RAW/work_on_files.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6b76badec7a176c5","mcp_get_code":{"code_sha256":"6b76badec7a176c5"}},{"arxiv_id":"2108.12250","paper":"/paper/a-comparison-of-approaches-to-improve-worst","title":"A comparison of approaches to improve worst-case predictive model performance over patient subpopulations","date":"2021-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"som-shahlab/subpopulation_robustness","path":"group_robustness_fairness/omop/train_model.py","file_url":"https://github.com/som-shahlab/subpopulation_robustness/blob/HEAD/group_robustness_fairness/omop/train_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"732bae7d31477943","mcp_get_code":{"code_sha256":"732bae7d31477943"}},{"arxiv_id":"2108.12250","paper":"/paper/a-comparison-of-approaches-to-improve-worst","title":"A comparison of approaches to improve worst-case predictive model performance over patient subpopulations","date":"2021-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"som-shahlab/subpopulation_robustness","path":"group_robustness_fairness/mimic_eicu/train_model.py","file_url":"https://github.com/som-shahlab/subpopulation_robustness/blob/HEAD/group_robustness_fairness/mimic_eicu/train_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48c2fca73de3d05e","mcp_get_code":{"code_sha256":"48c2fca73de3d05e"}},{"arxiv_id":"2105.00303","paper":"/paper/ratt-leveraging-unlabeled-data-to-guarantee","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","date":"2021-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"acmi-lab/ratt_generalization_bound","path":"plots_helper/plot_acc.py","file_url":"https://github.com/acmi-lab/ratt_generalization_bound/blob/HEAD/plots_helper/plot_acc.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":"eeb3d9b0ff6d3654","mcp_get_code":{"code_sha256":"eeb3d9b0ff6d3654"}},{"arxiv_id":"2104.01320","paper":"/paper/an-empirical-study-on-channel-effects-for","title":"An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems","date":"2021-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yzyouzhang/asvspoof2021_air","path":"score_fusion.py","file_url":"https://github.com/yzyouzhang/asvspoof2021_air/blob/HEAD/score_fusion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c331f51bee478856","mcp_get_code":{"code_sha256":"c331f51bee478856"}},{"arxiv_id":"2010.11326","paper":"/paper/fast-and-robust-bio-inspired-teach-and-repeat","title":"Fast and Robust Bio-inspired Teach and Repeat Navigation","date":null,"month_inferred_from_arxiv_id":"2020-10","title_source":"archive","repo":"QVPR/teach-repeat","path":"nodes/localiser.py","file_url":"https://github.com/QVPR/teach-repeat/blob/HEAD/nodes/localiser.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"a5475924efbab98a","mcp_get_code":{"code_sha256":"a5475924efbab98a"}},{"arxiv_id":"2010.05432","paper":"/paper/it-s-not-a-non-issue-negation-as-a-source-of","title":"It's not a Non-Issue: Negation as a Source of Error in Machine Translation","date":"2020-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mosharafhossain/negation-mt","path":"extract_negation.py","file_url":"https://github.com/mosharafhossain/negation-mt/blob/HEAD/extract_negation.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":"e48b72f6fb921c89","mcp_get_code":{"code_sha256":"e48b72f6fb921c89"}},{"arxiv_id":"2009.14654","paper":"/paper/owl2vec-embedding-of-owl-ontologies","title":"OWL2Vec*: Embedding of OWL Ontologies","date":"2020-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sevinjt/owl2vec4oa","path":"LogmapIntersectionAml.py","file_url":"https://github.com/sevinjt/owl2vec4oa/blob/HEAD/LogmapIntersectionAml.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":"7c9db6909a5a3be9","mcp_get_code":{"code_sha256":"7c9db6909a5a3be9"}},{"arxiv_id":"2009.14654","paper":"/paper/owl2vec-embedding-of-owl-ontologies","title":"OWL2Vec*: Embedding of OWL Ontologies","date":"2020-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sevinjt/owl2vec4oa","path":"LogmapUnionAml.py","file_url":"https://github.com/sevinjt/owl2vec4oa/blob/HEAD/LogmapUnionAml.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":"4534693785a12b2a","mcp_get_code":{"code_sha256":"4534693785a12b2a"}},{"arxiv_id":"2008.01065","paper":"/paper/memory-augmented-dense-predictive-coding-for","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","date":"2020-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TengdaHan/MemDPC","path":"memdpc/dataset.py","file_url":"https://github.com/TengdaHan/MemDPC/blob/HEAD/memdpc/dataset.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":"38ccb62cde04dd54","mcp_get_code":{"code_sha256":"38ccb62cde04dd54"}},{"arxiv_id":"2007.10306","paper":"/paper/an-empirical-characterization-of-fair-machine","title":"An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction","date":"2020-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"som-shahlab/fairness_benchmark","path":"fairness_benchmark/train_model.py","file_url":"https://github.com/som-shahlab/fairness_benchmark/blob/HEAD/fairness_benchmark/train_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f3965f978a31b1a","mcp_get_code":{"code_sha256":"1f3965f978a31b1a"}},{"arxiv_id":"2006.00751","paper":"/paper/evaluation-of-cnn-based-automatic-music","title":"Evaluation of CNN-based Automatic Music Tagging Models","date":null,"month_inferred_from_arxiv_id":"2020-06","title_source":"archive","repo":"minzwon/sota-music-tagging-models","path":"training/robustness.py","file_url":"https://github.com/minzwon/sota-music-tagging-models/blob/HEAD/training/robustness.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8aa1dec7ce5bdeda","mcp_get_code":{"code_sha256":"8aa1dec7ce5bdeda"}},{"arxiv_id":"2004.08532","paper":"/paper/dgl-ke-training-knowledge-graph-embeddings-at","title":"DGL-KE: Training Knowledge Graph Embeddings at Scale","date":null,"month_inferred_from_arxiv_id":"2020-04","title_source":"archive","repo":"idirlab/freebases","path":"ExperimentsScripts/FB1_statistics_domain_triples_relations.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/FB1_statistics_domain_triples_relations.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":"da36ef8474d88ac2","mcp_get_code":{"code_sha256":"da36ef8474d88ac2"}},{"arxiv_id":"2004.08013","paper":"/paper/how-recurrent-networks-implement-contextual","title":"How recurrent networks implement contextual processing in sentiment analysis","date":"2020-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/computation-thru-dynamics","path":"fixed_point_finder/utils.py","file_url":"https://github.com/google-research/computation-thru-dynamics/blob/HEAD/fixed_point_finder/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":"670f241a0a278e35","mcp_get_code":{"code_sha256":"670f241a0a278e35"}},{"arxiv_id":"2002.12418","paper":"/paper/mnn-a-universal-and-efficient-inference","title":"MNN: A Universal and Efficient Inference Engine","date":"2020-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/MNN","path":"apps/frameworks/sherpa-mnn/python-api-examples/http_server.py","file_url":"https://github.com/alibaba/MNN/blob/HEAD/apps/frameworks/sherpa-mnn/python-api-examples/http_server.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":"b6c521a26530e9d3","mcp_get_code":{"code_sha256":"b6c521a26530e9d3"}},{"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":"eval/auto_eval.py","file_url":"https://github.com/ivabojic/sleepqa/blob/HEAD/eval/auto_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b127fbfb02fb0632","mcp_get_code":{"code_sha256":"b127fbfb02fb0632"}},{"arxiv_id":"1907.07897","paper":"/paper/neural-shuffle-exchange-networks-sequence","title":"Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time","date":"2019-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LUMII-Syslab/shuffle-exchange","path":"language/lambada.py","file_url":"https://github.com/LUMII-Syslab/shuffle-exchange/blob/HEAD/language/lambada.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"201029f100790c9c","mcp_get_code":{"code_sha256":"201029f100790c9c"}},{"arxiv_id":"1904.07418","paper":"/paper/positional-encoding-to-control-output","title":"Positional Encoding to Control Output Sequence Length","date":"2019-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"takase/control-length","path":"eval/calculate_variance_from_fixlength.py","file_url":"https://github.com/takase/control-length/blob/HEAD/eval/calculate_variance_from_fixlength.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":"46c303dd0a228f2e","mcp_get_code":{"code_sha256":"46c303dd0a228f2e"}},{"arxiv_id":"1903.02428","paper":"/paper/fast-graph-representation-learning-with","title":"Fast Graph Representation Learning with PyTorch Geometric","date":"2019-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"long-9621/splinecnn","path":"torch_geometric/io/planetoid.py","file_url":"https://github.com/long-9621/splinecnn/blob/HEAD/torch_geometric/io/planetoid.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35ef2289cbdcde86","mcp_get_code":{"code_sha256":"35ef2289cbdcde86"}},{"arxiv_id":"1902.10909","paper":"/paper/bert-for-joint-intent-classification-and-slot","title":"BERT for Joint Intent Classification and Slot Filling","date":"2019-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinghao1019/Joint_learn","path":"predict.py","file_url":"https://github.com/yinghao1019/Joint_learn/blob/HEAD/predict.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":"7b9905a68c0add30","mcp_get_code":{"code_sha256":"7b9905a68c0add30"}},{"arxiv_id":"1812.09755","paper":"/paper/learning-when-to-communicate-at-scale-in","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","date":"2018-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IC3Net/IC3Net","path":"plot_script.py","file_url":"https://github.com/IC3Net/IC3Net/blob/HEAD/plot_script.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9fef680e2912a66","mcp_get_code":{"code_sha256":"a9fef680e2912a66"}},{"arxiv_id":"1810.03993","paper":"/paper/model-cards-for-model-reporting","title":"Model Cards for Model Reporting","date":"2018-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tensorflow/model-card-toolkit","path":"model_card_toolkit/utils/io_utils.py","file_url":"https://github.com/tensorflow/model-card-toolkit/blob/HEAD/model_card_toolkit/utils/io_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":"71f79125049402a3","mcp_get_code":{"code_sha256":"71f79125049402a3"}},{"arxiv_id":"1806.05476","paper":"/paper/copycat-cnn-stealing-knowledge-by-persuading","title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","date":"2018-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeiks/Stealing_DL_Models","path":"Copycat_CNN-Expansion/01-classification_space-TSNE/experiment-01-DIG10/tsne.py","file_url":"https://github.com/jeiks/Stealing_DL_Models/blob/HEAD/Copycat_CNN-Expansion/01-classification_space-TSNE/experiment-01-DIG10/tsne.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2cd7184053135d4d","mcp_get_code":{"code_sha256":"2cd7184053135d4d"}},{"arxiv_id":"1805.08241","paper":"/paper/sparse-and-constrained-attention-for-neural","title":"Sparse and Constrained Attention for Neural Machine Translation","date":"2018-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Unbabel/sparse_constrained_attention","path":"fertility/utils.py","file_url":"https://github.com/Unbabel/sparse_constrained_attention/blob/HEAD/fertility/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":"dcf92267cfb613e2","mcp_get_code":{"code_sha256":"dcf92267cfb613e2"}},{"arxiv_id":"1804.07573","paper":"/paper/mobilefacenets-efficient-cnns-for-accurate","title":"MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices","date":"2018-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foamliu/MobileFaceNet","path":"create_lfw_test_pair.py","file_url":"https://github.com/foamliu/MobileFaceNet/blob/HEAD/create_lfw_test_pair.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":"7e9755b0b787bdf3","mcp_get_code":{"code_sha256":"7e9755b0b787bdf3"}},{"arxiv_id":"1803.11175","paper":"/paper/universal-sentence-encoder","title":"Universal Sentence Encoder","date":"2018-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TAUSBV/sentence-level-domain-classification","path":"src/utils.py","file_url":"https://github.com/TAUSBV/sentence-level-domain-classification/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46df1f9c4f68b7a2","mcp_get_code":{"code_sha256":"46df1f9c4f68b7a2"}},{"arxiv_id":"1710.02224","paper":"/paper/dilated-recurrent-neural-networks","title":"Dilated Recurrent Neural Networks","date":"2017-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zalandoresearch/pytorch-dilated-rnn","path":"char_rnn/utils.py","file_url":"https://github.com/zalandoresearch/pytorch-dilated-rnn/blob/HEAD/char_rnn/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0edd931ca8776ea","mcp_get_code":{"code_sha256":"b0edd931ca8776ea"}},{"arxiv_id":"1612.01840","paper":"/paper/fma-a-dataset-for-music-analysis","title":"FMA: A Dataset For Music Analysis","date":"2016-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weepingwillowben/sound-eval","path":"gather_computed.py","file_url":"https://github.com/weepingwillowben/sound-eval/blob/HEAD/gather_computed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c708ef13e6436433","mcp_get_code":{"code_sha256":"c708ef13e6436433"}},{"arxiv_id":"1609.01454","paper":"/paper/attention-based-recurrent-neural-network","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","date":"2016-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7b9905a68c0add30","mcp_get_code":{"code_sha256":"7b9905a68c0add30"}},{"arxiv_id":"1511.06811","paper":"/paper/learning-visual-groups-from-co-occurrences-in","title":"Learning visual groups from co-occurrences in space and time","date":"2015-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benblack769/sound-eval","path":"gather_computed.py","file_url":"https://github.com/benblack769/sound-eval/blob/HEAD/gather_computed.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c708ef13e6436433","mcp_get_code":{"code_sha256":"c708ef13e6436433"}},{"arxiv_id":"1503.00075","paper":"/paper/improved-semantic-representations-from-tree","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","date":"2015-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EmilReinert/DeepLearningPipelines","path":"workspace/pipelines/defect_prediction.py","file_url":"https://github.com/EmilReinert/DeepLearningPipelines/blob/HEAD/workspace/pipelines/defect_prediction.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":"33e96662baea2bc4","mcp_get_code":{"code_sha256":"33e96662baea2bc4"}},{"arxiv_id":"aaai_29103","paper":null,"title":"arXiv:aaai_29103","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yaoyao-yaoyao-cell/CRCG","path":"datasets/graphsst2_dataset.py","file_url":"https://github.com/yaoyao-yaoyao-cell/CRCG/blob/HEAD/datasets/graphsst2_dataset.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60ccd1c98038811b","mcp_get_code":{"code_sha256":"60ccd1c98038811b"}},{"arxiv_id":"aaai_20873","paper":null,"title":"arXiv:aaai_20873","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RICE-EIC/Early-Bird-GCN","path":"NELL_utils.py","file_url":"https://github.com/RICE-EIC/Early-Bird-GCN/blob/HEAD/NELL_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":"35ef2289cbdcde86","mcp_get_code":{"code_sha256":"35ef2289cbdcde86"}},{"arxiv_id":"Ahn_Refining_Action_Segmentation_With_Hierarchical_Video_Representations_ICCV_2021_paper","paper":null,"title":"arXiv:Ahn_Refining_Action_Segmentation_With_Hierarchical_Video_Representations_ICCV_2021_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cotton-ahn/HASR_iccv2021","path":"src/utils.py","file_url":"https://github.com/cotton-ahn/HASR_iccv2021/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2188327bf35280a1","mcp_get_code":{"code_sha256":"2188327bf35280a1"}},{"arxiv_id":"2025.emnlp-main.1702","paper":null,"title":"arXiv:2025.emnlp-main.1702","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IBM/NESTFUL","path":"src/utils.py","file_url":"https://github.com/IBM/NESTFUL/blob/HEAD/src/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":"ba6cfefa8094dcb6","mcp_get_code":{"code_sha256":"ba6cfefa8094dcb6"}},{"arxiv_id":"2025.acl-long.562","paper":null,"title":"arXiv:2025.acl-long.562","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"aeg-hit/PwnGPT","path":"preprocessing/analysis.py","file_url":"https://github.com/aeg-hit/PwnGPT/blob/HEAD/preprocessing/analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"990ff33e4c206334","mcp_get_code":{"code_sha256":"990ff33e4c206334"}},{"arxiv_id":"2023.findings-emnlp.978","paper":null,"title":"arXiv:2023.findings-emnlp.978","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"libeineu/MMT-VQA","path":"meteor.py","file_url":"https://github.com/libeineu/MMT-VQA/blob/HEAD/meteor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bc73c3b9bba36ec","mcp_get_code":{"code_sha256":"1bc73c3b9bba36ec"}},{"arxiv_id":"2023.findings-eacl.134","paper":null,"title":"arXiv:2023.findings-eacl.134","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"UniversalPropositions/PriMeSRL-Eval","path":"src/conll/conllu_conversion.py","file_url":"https://github.com/UniversalPropositions/PriMeSRL-Eval/blob/HEAD/src/conll/conllu_conversion.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":"1f1fb8453ae47648","mcp_get_code":{"code_sha256":"1f1fb8453ae47648"}}]}