{"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/softmax","entry":"softmax","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":240,"n_papers_ran":130,"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":185,"n_samples_ran":96,"n_samples_fingerprinted":89,"n_places":251,"n_places_pointer_only":84,"by_status":{"ran_honours":20,"ran_violates":14,"ran_draft_wrong":18,"ran_fixture":10,"ran":34,"unverified":89},"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":"2608.20400","paper":"/paper/arxiv-2608-20400","title":"When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"smkgenesis/dsgc","path":"src/benchmarking/policy.py","file_url":"https://github.com/smkgenesis/dsgc/blob/HEAD/src/benchmarking/policy.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ca9816c0c550df1a","mcp_get_code":{"code_sha256":"ca9816c0c550df1a"}},{"arxiv_id":"2608.17284","paper":"/paper/arxiv-2608-17284","title":"Rethinking Irregular Time Series Forecasting from the Perspective of Basis Functions","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"hnu-vis/DNBNet","path":"models/Hi_Patch.py","file_url":"https://github.com/hnu-vis/DNBNet/blob/HEAD/models/Hi_Patch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5eafae5f3344851b","mcp_get_code":{"code_sha256":"5eafae5f3344851b"}},{"arxiv_id":"2608.10045","paper":"/paper/arxiv-2608-10045","title":"Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"lucasmaystre/choix","path":"choix/utils.py","file_url":"https://github.com/lucasmaystre/choix/blob/HEAD/choix/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5e48b122b98d031b","mcp_get_code":{"code_sha256":"5e48b122b98d031b"}},{"arxiv_id":"2608.03967","paper":"/paper/arxiv-2608-03967","title":"Information-Geometric Forward Policy Training in GFlowNets","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"rodsveiga/infogeometric_gflows","path":"gflows/utils.py","file_url":"https://github.com/rodsveiga/infogeometric_gflows/blob/HEAD/gflows/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fcf96753d45e5fc7","mcp_get_code":{"code_sha256":"fcf96753d45e5fc7"}},{"arxiv_id":"2607.27987","paper":"/paper/arxiv-2607-27987","title":"It's All Just Vectorization: einx, a Universal Notation for Tensor Operations","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"fferflo/einx","path":"einx/_src/adapter/classical_from_classical.py","file_url":"https://github.com/fferflo/einx/blob/HEAD/einx/_src/adapter/classical_from_classical.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"423d12e4d133d975","mcp_get_code":{"code_sha256":"423d12e4d133d975"}},{"arxiv_id":"2607.10804","paper":"/paper/arxiv-2607-10804","title":"When does distribution shift break graph neural networks calibration?","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"AraoufBh/GNN-Calibration","path":"code/stac.py","file_url":"https://github.com/AraoufBh/GNN-Calibration/blob/HEAD/code/stac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ceb8f93a02b4ee3","mcp_get_code":{"code_sha256":"7ceb8f93a02b4ee3"}},{"arxiv_id":"2606.03048","paper":"/paper/arxiv-2606-03048","title":"The Value Function Semi-Algebraic Set in POMDPs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ryan-a-anderson/pomdp-value-geometry","path":"src/local_optima_experiments.py","file_url":"https://github.com/ryan-a-anderson/pomdp-value-geometry/blob/HEAD/src/local_optima_experiments.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"113a0f2ce97567ba","mcp_get_code":{"code_sha256":"113a0f2ce97567ba"}},{"arxiv_id":"2605.30188","paper":"/paper/arxiv-2605-30188","title":"CalArena: A Large-Scale Post-Hoc Calibration Benchmark","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"probkit/CalArena","path":"calibration_benchmarks/generate_cv_benchmarks.py","file_url":"https://github.com/probkit/CalArena/blob/HEAD/calibration_benchmarks/generate_cv_benchmarks.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":"743ce59ae7c6d8e9","mcp_get_code":{"code_sha256":"743ce59ae7c6d8e9"}},{"arxiv_id":"2605.21240","paper":"/paper/arxiv-2605-21240","title":"APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"liushiliushi/APEX1","path":"src/utils.py","file_url":"https://github.com/liushiliushi/APEX1/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":"a5c45e740fabb819","mcp_get_code":{"code_sha256":"a5c45e740fabb819"}},{"arxiv_id":"2605.07662","paper":"/paper/arxiv-2605-07662","title":"Direction-Preserving Number Representations","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"bardia01/Direction-Preserving-Number-Representations","path":"Experiments/src/directional_coverage_optimizer.py","file_url":"https://github.com/bardia01/Direction-Preserving-Number-Representations/blob/HEAD/Experiments/src/directional_coverage_optimizer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d96b021db8902f1e","mcp_get_code":{"code_sha256":"d96b021db8902f1e"}},{"arxiv_id":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/compute_ground_truth.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/compute_ground_truth.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d3064adf95e8f16e","mcp_get_code":{"code_sha256":"d3064adf95e8f16e"}},{"arxiv_id":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/exp1_coverage.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/exp1_coverage.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b1d8ac976df7a27","mcp_get_code":{"code_sha256":"8b1d8ac976df7a27"}},{"arxiv_id":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/exp2_near_tie.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/exp2_near_tie.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7b74dbfee2cac12","mcp_get_code":{"code_sha256":"f7b74dbfee2cac12"}},{"arxiv_id":"2605.05973","paper":"/paper/arxiv-2605-05973","title":"Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"jznmsl/siren","path":"03_analysis_scripts/exp3_optimism.py","file_url":"https://github.com/jznmsl/siren/blob/HEAD/03_analysis_scripts/exp3_optimism.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"72c3fa12241ebe8f","mcp_get_code":{"code_sha256":"72c3fa12241ebe8f"}},{"arxiv_id":"2604.04230","paper":"/paper/arxiv-2604-04230","title":"Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Cmouzouni/three-phases-moe","path":"moe/costs.py","file_url":"https://github.com/Cmouzouni/three-phases-moe/blob/HEAD/moe/costs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6a18510b8fe51466","mcp_get_code":{"code_sha256":"6a18510b8fe51466"}},{"arxiv_id":"2603.03292","paper":"/paper/arxiv-2603-03292","title":"From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"NJU-RL/MA-RAG","path":"train_bert.py","file_url":"https://github.com/NJU-RL/MA-RAG/blob/HEAD/train_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa2c61ccf3cad586","mcp_get_code":{"code_sha256":"fa2c61ccf3cad586"}},{"arxiv_id":"2602.23876","paper":"/paper/arxiv-2602-23876","title":"RF-Agent: Automated Reward Function Design via Language Agent Tree Search","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"deng-ai-lab/RF-Agent","path":"RF_Agent/rf_agent_algo/rfagent_algo.py","file_url":"https://github.com/deng-ai-lab/RF-Agent/blob/HEAD/RF_Agent/rf_agent_algo/rfagent_algo.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c97e64e59475efc","mcp_get_code":{"code_sha256":"4c97e64e59475efc"}},{"arxiv_id":"2602.19531","paper":"/paper/arxiv-2602-19531","title":"A Statistical Approach for Modeling Irregular Multivariate Time Series with Missing Observations","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"YerevaNN/mimic3-benchmarks","path":"mimic3models/keras_utils.py","file_url":"https://github.com/YerevaNN/mimic3-benchmarks/blob/HEAD/mimic3models/keras_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89812b9ec498264d","mcp_get_code":{"code_sha256":"89812b9ec498264d"}},{"arxiv_id":"2602.12162","paper":"/paper/arxiv-2602-12162","title":"Amortized Molecular Optimization via Group Relative Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Hash-hh/AMORTIX","path":"core/stochastic_beam_search.py","file_url":"https://github.com/Hash-hh/AMORTIX/blob/HEAD/core/stochastic_beam_search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b26c5b115681ee5a","mcp_get_code":{"code_sha256":"b26c5b115681ee5a"}},{"arxiv_id":"2602.09574","paper":"/paper/arxiv-2602-09574","title":"Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Sora-Miyamoto/bg-mcts","path":"treesearch/src/treesearch/algos/bg_mcts.py","file_url":"https://github.com/Sora-Miyamoto/bg-mcts/blob/HEAD/treesearch/src/treesearch/algos/bg_mcts.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b36903455b4e0393","mcp_get_code":{"code_sha256":"b36903455b4e0393"}},{"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/transformer/core.py","file_url":"https://github.com/thepowerfuldeez/sample_efficient_gpt/blob/HEAD/sample_efficient_gpt/transformer/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fb874de8e38ead7a","mcp_get_code":{"code_sha256":"fb874de8e38ead7a"}},{"arxiv_id":"2601.23183","paper":"/paper/arxiv-2601-23183","title":"JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual Résumés and JDs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"confident-ai/deepeval","path":"deepeval/models/answer_relevancy_model.py","file_url":"https://github.com/confident-ai/deepeval/blob/HEAD/deepeval/models/answer_relevancy_model.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":"44f1edd94e78101e","mcp_get_code":{"code_sha256":"44f1edd94e78101e"}},{"arxiv_id":"2601.17103","paper":"/paper/arxiv-2601-17103","title":"Performance uncertainty in medical image analysis: a large-scale investigation of confidence intervals","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"aramis-lab/CIs_Medical_Imaging","path":"src/intervals_and_metrics/pixel_wise_metrics.py","file_url":"https://github.com/aramis-lab/CIs_Medical_Imaging/blob/HEAD/src/intervals_and_metrics/pixel_wise_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8cc426ecde08301f","mcp_get_code":{"code_sha256":"8cc426ecde08301f"}},{"arxiv_id":"2601.16503","paper":"/paper/arxiv-2601-16503","title":"MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"hendrycks/test","path":"evaluate.py","file_url":"https://github.com/hendrycks/test/blob/HEAD/evaluate.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2601.10926","paper":"/paper/arxiv-2601-10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate Preprint XX(X):1-22 ©The Author(s) 2026","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"openai/gpt-2","path":"src/model.py","file_url":"https://github.com/openai/gpt-2/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f42ce3b6444009d9","mcp_get_code":{"code_sha256":"f42ce3b6444009d9"}},{"arxiv_id":"2601.07576","paper":"/paper/arxiv-2601-07576","title":"A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Ascend-Research/HeadPoseEstimation-WHENet","path":"utils.py","file_url":"https://github.com/Ascend-Research/HeadPoseEstimation-WHENet/blob/HEAD/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":"1f4ad91cbcf8ec36","mcp_get_code":{"code_sha256":"1f4ad91cbcf8ec36"}},{"arxiv_id":"2510.10116","paper":"/paper/arxiv-2510-10116","title":"Preference-driven Knowledge Distillation for Few-shot Node Classification","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"GEEX-Weixing/PKD","path":"node_filter.py","file_url":"https://github.com/GEEX-Weixing/PKD/blob/HEAD/node_filter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8bf374c9e1999142","mcp_get_code":{"code_sha256":"8bf374c9e1999142"}},{"arxiv_id":"2510.05566","paper":"/paper/arxiv-2510-05566","title":"Domain-Shift-Aware Conformal Prediction for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"smartyfh/LLM-Uncertainty-Bench","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/LLM-Uncertainty-Bench/blob/HEAD/uncertainty_quantification_via_cp.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"2510.05566","paper":"/paper/arxiv-2510-05566","title":"Domain-Shift-Aware Conformal Prediction for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"zhexiaolin/CP","path":"src/cp_methods.py","file_url":"https://github.com/zhexiaolin/CP/blob/HEAD/src/cp_methods.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"885d6e6994f5e4bd","mcp_get_code":{"code_sha256":"885d6e6994f5e4bd"}},{"arxiv_id":"2506.23502","paper":null,"title":"arXiv:2506.23502","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"Mengxiao-Tian/LAMP","path":"clip/attention.py","file_url":"https://github.com/Mengxiao-Tian/LAMP/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b5d0d43936dc7a5c","mcp_get_code":{"code_sha256":"b5d0d43936dc7a5c"}},{"arxiv_id":"2506.14605","paper":"/paper/unsupervised-imaging-inverse-problems-with","title":"Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"inria-thoth/ddm4ip","path":"ddm4ip/degradations/motion_blur.py","file_url":"https://github.com/inria-thoth/ddm4ip/blob/HEAD/ddm4ip/degradations/motion_blur.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"2505.24449","paper":"/paper/when-large-multimodal-models-confront","title":"When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pjlab-sys4nlp/llama-moe","path":"smoe/entrypoint/eval/eval_mmlu_moe_0.py","file_url":"https://github.com/pjlab-sys4nlp/llama-moe/blob/HEAD/smoe/entrypoint/eval/eval_mmlu_moe_0.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2505.21362","paper":"/paper/evaluating-llm-adaptation-to-sociodemographic","title":"Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FerdinandZhong/model_behavior_adaption","path":"llm_behavior_adaptation/value_measurement/formulas.py","file_url":"https://github.com/FerdinandZhong/model_behavior_adaption/blob/HEAD/llm_behavior_adaptation/value_measurement/formulas.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"411fac55497025e8","mcp_get_code":{"code_sha256":"411fac55497025e8"}},{"arxiv_id":"2505.18917","paper":"/paper/behavior-injection-preparing-language-models","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czp16/bridge-llm-reasoning","path":"iGSM-reasoning/igsm_reasoning/utils/misc.py","file_url":"https://github.com/czp16/bridge-llm-reasoning/blob/HEAD/iGSM-reasoning/igsm_reasoning/utils/misc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a0b94e702fcbb1c4","mcp_get_code":{"code_sha256":"a0b94e702fcbb1c4"}},{"arxiv_id":"2505.18513","paper":"/paper/enhancing-training-data-attribution-with","title":"Enhancing Training Data Attribution with Representational Optimization","date":"2025-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunnweiwei/airrep","path":"scripts/04_evaluate.py","file_url":"https://github.com/sunnweiwei/airrep/blob/HEAD/scripts/04_evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a445568164614eb","mcp_get_code":{"code_sha256":"6a445568164614eb"}},{"arxiv_id":"2505.15437","paper":"/paper/adaptive-temperature-scaling-with-conformal","title":"Adaptive Temperature Scaling with Conformal Prediction","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stat-ml/conformal_probability_calibration","path":"caliblab/calibrators/conformal_mass_threshold_calibrator.py","file_url":"https://github.com/stat-ml/conformal_probability_calibration/blob/HEAD/caliblab/calibrators/conformal_mass_threshold_calibrator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08bc835660d4723f","mcp_get_code":{"code_sha256":"08bc835660d4723f"}},{"arxiv_id":"2505.11737","paper":"/paper/token-level-uncertainty-estimation-for-large","title":"Token-Level Uncertainty Estimation for Large Language Model Reasoning","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wang-ML-Lab/TokUR","path":"eval/eval_scaling_test_multi_gpu.py","file_url":"https://github.com/Wang-ML-Lab/TokUR/blob/HEAD/eval/eval_scaling_test_multi_gpu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1124b1f7a07898d8","mcp_get_code":{"code_sha256":"1124b1f7a07898d8"}},{"arxiv_id":"2504.05457","paper":null,"title":"arXiv:2504.05457","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"vesteinn/vlm-eval","path":"src/vlmeval/calculate_scores/map_predictions.py","file_url":"https://github.com/vesteinn/vlm-eval/blob/HEAD/src/vlmeval/calculate_scores/map_predictions.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08883768489fd226","mcp_get_code":{"code_sha256":"08883768489fd226"}},{"arxiv_id":"2503.14493","paper":"/paper/state-space-model-meets-transformer-a-new-1","title":"State Space Model Meets Transformer: A New Paradigm for 3D Object Detection","date":"2025-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenSpaceAI/DEST3D","path":"models/ap_helper.py","file_url":"https://github.com/OpenSpaceAI/DEST3D/blob/HEAD/models/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2503.08537","paper":"/paper/chemical-reasoning-in-llms-unlocks-steerable","title":"Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation","date":"2025-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schwallergroup/steer","path":"src/steer/mechanism/search.py","file_url":"https://github.com/schwallergroup/steer/blob/HEAD/src/steer/mechanism/search.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"2503.04412","paper":"/paper/wider-or-deeper-scaling-llm-inference-time","title":"Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search","date":"2025-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SakanaAI/treequest","path":"src/treequest/algos/standard_mcts.py","file_url":"https://github.com/SakanaAI/treequest/blob/HEAD/src/treequest/algos/standard_mcts.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":"ad49db271d83dd77","mcp_get_code":{"code_sha256":"ad49db271d83dd77"}},{"arxiv_id":"2502.04510","paper":"/paper/heterogeneous-swarms-jointly-optimizing-model","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BunsenFeng/heterogeneous_swarm","path":"search.py","file_url":"https://github.com/BunsenFeng/heterogeneous_swarm/blob/HEAD/search.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"380f691b7059126a","mcp_get_code":{"code_sha256":"380f691b7059126a"}},{"arxiv_id":"2412.09492","paper":"/paper/video-seal-open-and-efficient-video","title":"Video Seal: Open and Efficient Video Watermarking","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/videoseal","path":"videoseal/losses/watson_fft.py","file_url":"https://github.com/facebookresearch/videoseal/blob/HEAD/videoseal/losses/watson_fft.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc287dc402b9202b","mcp_get_code":{"code_sha256":"cc287dc402b9202b"}},{"arxiv_id":"2412.07618","paper":"/paper/adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"futureeeeee/dynamic-rag","path":"utils.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"69e582d84850bb60","mcp_get_code":{"code_sha256":"69e582d84850bb60"}},{"arxiv_id":"2412.06474","paper":"/paper/from-uncertainty-to-trust-enhancing","title":"From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kigb/DropoutDecoding","path":"chair_test/chair_metrics/lm_consistency.py","file_url":"https://github.com/kigb/DropoutDecoding/blob/HEAD/chair_test/chair_metrics/lm_consistency.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bfe1425c081169ef","mcp_get_code":{"code_sha256":"bfe1425c081169ef"}},{"arxiv_id":"2412.01572","paper":"/paper/mba-rag-a-bandit-approach-for-adaptive","title":"MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"futureeeeee/mba","path":"MAB/train_mab_mo_multiple.py","file_url":"https://github.com/futureeeeee/mba/blob/HEAD/MAB/train_mab_mo_multiple.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"69e582d84850bb60","mcp_get_code":{"code_sha256":"69e582d84850bb60"}},{"arxiv_id":"2411.02446","paper":"/paper/learning-world-models-for-unconstrained-goal","title":"Learning World Models for Unconstrained Goal Navigation","date":"2024-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RU-Automated-Reasoning-Group/MUN","path":"dreamerv2_APS/gc_goal_picker.py","file_url":"https://github.com/RU-Automated-Reasoning-Group/MUN/blob/HEAD/dreamerv2_APS/gc_goal_picker.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29f0fc44eda255b5","mcp_get_code":{"code_sha256":"29f0fc44eda255b5"}},{"arxiv_id":"2411.00823","paper":"/paper/mobility-llm-learning-visiting-intentions-and","title":"Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LetianGong/Mobility-LLM","path":"utils.py","file_url":"https://github.com/LetianGong/Mobility-LLM/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c3743723a7ad6877","mcp_get_code":{"code_sha256":"c3743723a7ad6877"}},{"arxiv_id":"2410.24001","paper":"/paper/imov3d-learning-open-vocabulary-point-clouds","title":"ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangtiming/ImOV3D","path":"models/ap_helper.py","file_url":"https://github.com/yangtiming/ImOV3D/blob/HEAD/models/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2410.10450","paper":"/paper/kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/KBLaM","path":"src/kblam/utils/eval_utils.py","file_url":"https://github.com/microsoft/KBLaM/blob/HEAD/src/kblam/utils/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":"aa519f4c344d1787","mcp_get_code":{"code_sha256":"aa519f4c344d1787"}},{"arxiv_id":"2410.02604","paper":"/paper/long-sequence-recommendation-models-need","title":"Long-Sequence Recommendation Models Need Decoupled Embeddings","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/DARE","path":"analysis/attention_accuracy_analysis/calc_learned.py","file_url":"https://github.com/thuml/DARE/blob/HEAD/analysis/attention_accuracy_analysis/calc_learned.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a585b44308980803","mcp_get_code":{"code_sha256":"a585b44308980803"}},{"arxiv_id":"2409.07556","paper":"/paper/ssr-speech-towards-stable-safe-and-robust","title":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WangHelin1997/SSR-Speech","path":"models/modules/scaling.py","file_url":"https://github.com/WangHelin1997/SSR-Speech/blob/HEAD/models/modules/scaling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c124aa8bd6b9ebe9","mcp_get_code":{"code_sha256":"c124aa8bd6b9ebe9"}},{"arxiv_id":"2407.03575","paper":"/paper/dgr-mil-exploring-diverse-global","title":"DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ChongQingNoSubway/DGR-MIL","path":"models/dgrmil.py","file_url":"https://github.com/ChongQingNoSubway/DGR-MIL/blob/HEAD/models/dgrmil.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c42e5fa46bf385ab","mcp_get_code":{"code_sha256":"c42e5fa46bf385ab"}},{"arxiv_id":"2406.16535","paper":"/paper/token-based-decision-criteria-are-suboptimal","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hc495/Hidden_Calibration","path":"util/calibrations.py","file_url":"https://github.com/hc495/Hidden_Calibration/blob/HEAD/util/calibrations.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63593798e1f9db95","mcp_get_code":{"code_sha256":"63593798e1f9db95"}},{"arxiv_id":"2406.13909","paper":"/paper/beyond-optimism-exploration-with-partially","title":"Beyond Optimism: Exploration With Partially Observable Rewards","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amiithinks/mon_mdp_neurips24","path":"src/actor.py","file_url":"https://github.com/amiithinks/mon_mdp_neurips24/blob/HEAD/src/actor.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"78dec1bfaaffb901","mcp_get_code":{"code_sha256":"78dec1bfaaffb901"}},{"arxiv_id":"2406.13123","paper":"/paper/vilco-bench-video-language-continual-learning","title":"ViLCo-Bench: VIdeo Language COntinual learning Benchmark","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cruiseresearchgroup/ViLCo","path":"MQ/utils.py","file_url":"https://github.com/cruiseresearchgroup/ViLCo/blob/HEAD/MQ/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a5b4d48b717da75","mcp_get_code":{"code_sha256":"3a5b4d48b717da75"}},{"arxiv_id":"2406.12649","paper":"/paper/probabilistic-conceptual-explainers","title":"Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wang-ML-Lab/interpretable-foundation-models","path":"PACE/src/model.py","file_url":"https://github.com/Wang-ML-Lab/interpretable-foundation-models/blob/HEAD/PACE/src/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d6c2bedc92a8075","mcp_get_code":{"code_sha256":"8d6c2bedc92a8075"}},{"arxiv_id":"2406.04606","paper":"/paper/helpful-or-harmful-data-fine-tuning-free","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JTWang2000/FreeShap","path":"vinfo/dvutils/utils.py","file_url":"https://github.com/JTWang2000/FreeShap/blob/HEAD/vinfo/dvutils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f45ae25efe8c0fa","mcp_get_code":{"code_sha256":"7f45ae25efe8c0fa"}},{"arxiv_id":"2405.19298","paper":"/paper/adaptive-image-quality-assessment-via","title":"Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Compare2Score","path":"q_align/evaluate/scorer.py","file_url":"https://github.com/Q-Future/Compare2Score/blob/HEAD/q_align/evaluate/scorer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50d788b8ddf322fa","mcp_get_code":{"code_sha256":"50d788b8ddf322fa"}},{"arxiv_id":"2405.14039","paper":"/paper/trajectory-volatility-for-out-of-distribution","title":"Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alsace08/OOD-Math-Reasoning","path":"Computation/score_utils.py","file_url":"https://github.com/Alsace08/OOD-Math-Reasoning/blob/HEAD/Computation/score_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b79dff7fdb873c4","mcp_get_code":{"code_sha256":"2b79dff7fdb873c4"}},{"arxiv_id":"2405.10974","paper":"/paper/bottleneck-minimal-indexing-for-generative","title":"Bottleneck-Minimal Indexing for Generative Document Retrieval","date":"2024-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kduxin/Bottleneck-Minimal-Indexing","path":"NCIRetriever/model.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"2405.07883","paper":"/paper/zero-shot-tokenizer-transfer","title":"Zero-Shot Tokenizer Transfer","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bminixhofer/zett","path":"zett/utils.py","file_url":"https://github.com/bminixhofer/zett/blob/HEAD/zett/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"adb54f0d1ae9c13b","mcp_get_code":{"code_sha256":"adb54f0d1ae9c13b"}},{"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_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"2404.19509","paper":"/paper/do-large-language-models-understand","title":"Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sjtu-compling/llm-pragmatics","path":"eval_logit/query.py","file_url":"https://github.com/sjtu-compling/llm-pragmatics/blob/HEAD/eval_logit/query.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c4be464cbe63fba","mcp_get_code":{"code_sha256":"9c4be464cbe63fba"}},{"arxiv_id":"2404.18185","paper":"/paper/ranked-list-truncation-for-large-language","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chuanmeng/rlt4reranking","path":"rlt/embedding.py","file_url":"https://github.com/chuanmeng/rlt4reranking/blob/HEAD/rlt/embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3135afc4e722e27d","mcp_get_code":{"code_sha256":"3135afc4e722e27d"}},{"arxiv_id":"2404.16493","paper":"/paper/commonsense-prototype-for-outdoor","title":"Commonsense Prototype for Outdoor Unsupervised 3D Object Detection","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hailanyi/CPD","path":"cpd/unsupervised_core/outline_utils.py","file_url":"https://github.com/hailanyi/CPD/blob/HEAD/cpd/unsupervised_core/outline_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"777a44a7613e767e","mcp_get_code":{"code_sha256":"777a44a7613e767e"}},{"arxiv_id":"2404.12362","paper":"/paper/transformer-tricks-removing-weights-for","title":"Transformer tricks: Removing weights for skipless transformers","date":"2024-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmachine-ai/transformer-tricks","path":"slimAttn_paper.py","file_url":"https://github.com/openmachine-ai/transformer-tricks/blob/HEAD/slimAttn_paper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f99579ed1c453457","mcp_get_code":{"code_sha256":"f99579ed1c453457"}},{"arxiv_id":"2404.02078","paper":"/paper/advancing-llm-reasoning-generalists-with","title":"Advancing LLM Reasoning Generalists with Preference Trees","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbmb/eurus","path":"eval/mmlu/evaluate_mmlu.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/mmlu/evaluate_mmlu.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2403.15180","paper":"/paper/self-improvement-for-neural-combinatorial","title":"Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"grimmlab/gumbeldore","path":"core/stochastic_beam_search.py","file_url":"https://github.com/grimmlab/gumbeldore/blob/HEAD/core/stochastic_beam_search.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b26c5b115681ee5a","mcp_get_code":{"code_sha256":"b26c5b115681ee5a"}},{"arxiv_id":"2403.14111","paper":"/paper/hetal-efficient-privacy-preserving-transfer","title":"HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CryptoLabInc/HETAL","path":"src/benchmark/softmax.py","file_url":"https://github.com/CryptoLabInc/HETAL/blob/HEAD/src/benchmark/softmax.py","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7c0d7e9e7a7f89cc","mcp_get_code":{"code_sha256":"7c0d7e9e7a7f89cc"}},{"arxiv_id":"2403.14111","paper":"/paper/hetal-efficient-privacy-preserving-transfer","title":"HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cryptolabinc/hetal","path":"src/benchmark/softmax.py","file_url":"https://github.com/cryptolabinc/hetal/blob/HEAD/src/benchmark/softmax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0bb0e5c7816d7fc0","mcp_get_code":{"code_sha256":"0bb0e5c7816d7fc0"}},{"arxiv_id":"2403.12809","paper":"/paper/comparing-explanation-faithfulness-between","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CPJKU/wechsel","path":"legacy/prepare.py","file_url":"https://github.com/CPJKU/wechsel/blob/HEAD/legacy/prepare.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d304abe064b5615","mcp_get_code":{"code_sha256":"4d304abe064b5615"}},{"arxiv_id":"2403.12729","paper":"/paper/posterior-uncertainty-quantification-in","title":"Posterior Uncertainty Quantification in Neural Networks using Data Augmentation","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-mixupmp","path":"utils.py","file_url":"https://github.com/apple/ml-mixupmp/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a16c332f67a73877","mcp_get_code":{"code_sha256":"a16c332f67a73877"}},{"arxiv_id":"2403.09346","paper":"/paper/avibench-towards-evaluating-the-robustness-of","title":"B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhanghao5201/b-avibench","path":"image_attack_tool/models/patch_attack.py","file_url":"https://github.com/zhanghao5201/b-avibench/blob/HEAD/image_attack_tool/models/patch_attack.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"36fe3fda88777bd1","mcp_get_code":{"code_sha256":"36fe3fda88777bd1"}},{"arxiv_id":"2403.03823","paper":"/paper/a-modular-approach-for-multimodal","title":"A Modular Approach for Multimodal Summarization of TV Shows","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/FActScore","path":"factscore/npm.py","file_url":"https://github.com/shmsw25/FActScore/blob/HEAD/factscore/npm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"925c59b7e44138ab","mcp_get_code":{"code_sha256":"925c59b7e44138ab"}},{"arxiv_id":"2403.01244","paper":"/paper/mitigating-catastrophic-forgetting-in-large","title":"Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepLearnXMU/SSR","path":"mmlu_test/evaluate.py","file_url":"https://github.com/DeepLearnXMU/SSR/blob/HEAD/mmlu_test/evaluate.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2402.18045","paper":"/paper/multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sheikhshafayat/multi-fact","path":"factscore/npm.py","file_url":"https://github.com/sheikhshafayat/multi-fact/blob/HEAD/factscore/npm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"925c59b7e44138ab","mcp_get_code":{"code_sha256":"925c59b7e44138ab"}},{"arxiv_id":"2402.17229","paper":"/paper/preserving-fairness-generalization-in","title":"Preserving Fairness Generalization in Deepfake Detection","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"purdue-m2/fairness-generalization","path":"training/fairness_metrics.py","file_url":"https://github.com/purdue-m2/fairness-generalization/blob/HEAD/training/fairness_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7937fb59ef6dda7d","mcp_get_code":{"code_sha256":"7937fb59ef6dda7d"}},{"arxiv_id":"2402.15933","paper":"/paper/bridging-the-gap-between-2d-and-3d-visual","title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthewdm0816/bridgeqa","path":"lib/ap_helper.py","file_url":"https://github.com/matthewdm0816/bridgeqa/blob/HEAD/lib/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2402.15708","paper":"/paper/query-augmentation-by-decoding-semantics-from","title":"Query Augmentation by Decoding Semantics from Brain Signals","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeziyi1998/brain-query-augmentation","path":"ict/bm25.py","file_url":"https://github.com/yeziyi1998/brain-query-augmentation/blob/HEAD/ict/bm25.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d79002277745e36d","mcp_get_code":{"code_sha256":"d79002277745e36d"}},{"arxiv_id":"2402.15309","paper":"/paper/counterfactual-generation-with-1","title":"Counterfactual Generation with Identifiability Guarantees","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanqi-qi/matte","path":"models/flow_network.py","file_url":"https://github.com/hanqi-qi/matte/blob/HEAD/models/flow_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"96ef68ae66a3280f","mcp_get_code":{"code_sha256":"96ef68ae66a3280f"}},{"arxiv_id":"2402.14418","paper":"/paper/uncertainty-aware-evaluation-for-vision","title":"Uncertainty-Aware Evaluation for Vision-Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ensec-ai/vlm-uncertainty-bench","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/ensec-ai/vlm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"2402.12840","paper":"/paper/arabicmmlu-assessing-massive-multitask","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mbzuai-nlp/arabicmmlu","path":"util_compute.py","file_url":"https://github.com/mbzuai-nlp/arabicmmlu/blob/HEAD/util_compute.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2402.12659","paper":"/paper/the-finben-an-holistic-financial-benchmark","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chancefocus/pixiu","path":"src/factscore_package/npm.py","file_url":"https://github.com/chancefocus/pixiu/blob/HEAD/src/factscore_package/npm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"925c59b7e44138ab","mcp_get_code":{"code_sha256":"925c59b7e44138ab"}},{"arxiv_id":"2402.10811","paper":"/paper/quantifying-the-persona-effect-in-llm","title":"Quantifying the Persona Effect in LLM Simulations","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/persona_effect","path":"run_ANES_RQ4.py","file_url":"https://github.com/cambridgeltl/persona_effect/blob/HEAD/run_ANES_RQ4.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"2402.07116","paper":"/paper/a-benchmark-for-multi-modal-foundation-models","title":"Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs","date":"2024-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Q-Future/Q-Bench","path":"example_code_for_idefics/a3_assessment_all.py","file_url":"https://github.com/Q-Future/Q-Bench/blob/HEAD/example_code_for_idefics/a3_assessment_all.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1927793129d4508f","mcp_get_code":{"code_sha256":"1927793129d4508f"}},{"arxiv_id":"2401.12794","paper":"/paper/benchmarking-llms-via-uncertainty","title":"Benchmarking LLMs via Uncertainty Quantification","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"2401.12794","paper":"/paper/benchmarking-llms-via-uncertainty","title":"Benchmarking LLMs via Uncertainty Quantification","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"smartyfh/llm-uncertainty-bench","path":"uncertainty_quantification_via_cp.py","file_url":"https://github.com/smartyfh/llm-uncertainty-bench/blob/HEAD/uncertainty_quantification_via_cp.py","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae9771b6b08aedbd","mcp_get_code":{"code_sha256":"ae9771b6b08aedbd"}},{"arxiv_id":"2401.09750","paper":"/paper/exploration-and-anti-exploration-with","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","date":"2024-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yk7333/DRND","path":"online/utils.py","file_url":"https://github.com/yk7333/DRND/blob/HEAD/online/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"011537d0bea7fe09","mcp_get_code":{"code_sha256":"011537d0bea7fe09"}},{"arxiv_id":"2401.04247","paper":"/paper/robust-image-watermarking-using-stable","title":"Attack-Resilient Image Watermarking Using Stable Diffusion","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhanglijun95/ZoDiac","path":"loss/watson_vgg.py","file_url":"https://github.com/zhanglijun95/ZoDiac/blob/HEAD/loss/watson_vgg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc287dc402b9202b","mcp_get_code":{"code_sha256":"cc287dc402b9202b"}},{"arxiv_id":"2312.12736","paper":"/paper/learning-and-forgetting-unsafe-examples-in","title":"Learning and Forgetting Unsafe Examples in Large Language Models","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andotalao24/learn-forget-unsafe-llm","path":"src/train_eval.py","file_url":"https://github.com/andotalao24/learn-forget-unsafe-llm/blob/HEAD/src/train_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"62d3b888dc672b51","mcp_get_code":{"code_sha256":"62d3b888dc672b51"}},{"arxiv_id":"2312.09059","paper":"/paper/auto-prox-training-free-vision-transformer","title":"Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery","date":"2023-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lilujunai/auto-prox-aaai24","path":"pycls/models/auto/module/multihead_super.py","file_url":"https://github.com/lilujunai/auto-prox-aaai24/blob/HEAD/pycls/models/auto/module/multihead_super.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":"fb5908c47c2af90c","mcp_get_code":{"code_sha256":"fb5908c47c2af90c"}},{"arxiv_id":"2312.06323","paper":"/paper/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vill-lab/2024-aaai-hpt","path":"clip/attention.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5d0d43936dc7a5c","mcp_get_code":{"code_sha256":"b5d0d43936dc7a5c"}},{"arxiv_id":"2312.02849","paper":"/paper/algorithms-for-mean-field-variational","title":"Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apooladian/mfvi","path":"BayesianUtils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/BayesianUtils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5ac707ebfd83b4ce","mcp_get_code":{"code_sha256":"5ac707ebfd83b4ce"}},{"arxiv_id":"2312.02224","paper":"/paper/tracing-hyperparameter-dependencies-for-model","title":"Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network","date":"2023-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"98bba89c2a19a3bb","mcp_get_code":{"code_sha256":"98bba89c2a19a3bb"}},{"arxiv_id":"2311.04071","paper":"/paper/energy-based-calibrated-vae-with-test-time","title":"Energy-Calibrated VAE with Test Time Free Lunch","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DJ-LYH/EC-VAE","path":"loss/watson.py","file_url":"https://github.com/DJ-LYH/EC-VAE/blob/HEAD/loss/watson.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc287dc402b9202b","mcp_get_code":{"code_sha256":"cc287dc402b9202b"}},{"arxiv_id":"2310.10378","paper":"/paper/cross-lingual-consistency-of-factual","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Betswish/Cross-Lingual-Consistency","path":"1_easyrun/RankC.py","file_url":"https://github.com/Betswish/Cross-Lingual-Consistency/blob/HEAD/1_easyrun/RankC.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a49ec0b422e77ed3","mcp_get_code":{"code_sha256":"a49ec0b422e77ed3"}},{"arxiv_id":"2310.09550","paper":"/paper/can-large-language-model-comprehend-ancient","title":"Can Large Language Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE","date":"2023-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isen-zhang/aclue","path":"src/utils.py","file_url":"https://github.com/isen-zhang/aclue/blob/HEAD/src/utils.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2310.07229","paper":"/paper/self-supervised-pocket-pretraining-via","title":"ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bowen-gao/ProFSA","path":"src/dataset/profsa2.py","file_url":"https://github.com/bowen-gao/ProFSA/blob/HEAD/src/dataset/profsa2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c28c7c5c968e7205","mcp_get_code":{"code_sha256":"c28c7c5c968e7205"}},{"arxiv_id":"2310.04928","paper":"/paper/large-language-models-only-pass-primary","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fajri91/indommlu","path":"utils.py","file_url":"https://github.com/fajri91/indommlu/blob/HEAD/utils.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2310.03342","paper":"/paper/lesson-learning-to-integrate-exploration","title":"LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beanie00/lesson","path":"rl_algorithm/common/option_model.py","file_url":"https://github.com/beanie00/lesson/blob/HEAD/rl_algorithm/common/option_model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3be33e47b8058815","mcp_get_code":{"code_sha256":"3be33e47b8058815"}},{"arxiv_id":"2310.01224","paper":"/paper/revisiting-mobility-modeling-with-graph-a","title":"Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yukayo/mobgt","path":"baseline_models/DeepMove/train_foursquare.py","file_url":"https://github.com/yukayo/mobgt/blob/HEAD/baseline_models/DeepMove/train_foursquare.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11e6984e1e22b85a","mcp_get_code":{"code_sha256":"11e6984e1e22b85a"}},{"arxiv_id":"2310.00567","paper":"/paper/understanding-the-robustness-of-randomized","title":"Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mail-research/randomized_defenses","path":"utils.py","file_url":"https://github.com/mail-research/randomized_defenses/blob/HEAD/utils.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":"8bf374c9e1999142","mcp_get_code":{"code_sha256":"8bf374c9e1999142"}},{"arxiv_id":"2309.12645","paper":"/paper/kuaisim-a-comprehensive-simulator-for","title":"KuaiSim: A Comprehensive Simulator for Recommender Systems","date":"2023-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"applied-machine-learning-lab/kuaisim","path":"code/recsim/choice_model.py","file_url":"https://github.com/applied-machine-learning-lab/kuaisim/blob/HEAD/code/recsim/choice_model.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":"a238753019219ccc","mcp_get_code":{"code_sha256":"a238753019219ccc"}},{"arxiv_id":"2309.09702","paper":"/paper/information-based-explanation-methods-for","title":"Information based explanation methods for deep learning agents -- with applications on large open-source chess models","date":"2023-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"patrik-ha/ii-map","path":"processing/ii_map.py","file_url":"https://github.com/patrik-ha/ii-map/blob/HEAD/processing/ii_map.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f022cdba5374f4d","mcp_get_code":{"code_sha256":"7f022cdba5374f4d"}},{"arxiv_id":"2309.03882","paper":"/paper/on-large-language-models-selection-bias-in","title":"Large Language Models Are Not Robust Multiple Choice Selectors","date":"2023-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chujiezheng/llm-mcq-bias","path":"code/debias_utils.py","file_url":"https://github.com/chujiezheng/llm-mcq-bias/blob/HEAD/code/debias_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"64e12b411d5ec4ca","mcp_get_code":{"code_sha256":"64e12b411d5ec4ca"}},{"arxiv_id":"2308.16692","paper":"/paper/speechtokenizer-unified-speech-tokenizer-for","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"0nutation/uslm","path":"modules/scaling.py","file_url":"https://github.com/0nutation/uslm/blob/HEAD/modules/scaling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c124aa8bd6b9ebe9","mcp_get_code":{"code_sha256":"c124aa8bd6b9ebe9"}},{"arxiv_id":"2308.15074","paper":"/paper/exploring-model-transferability-through-the","title":"Exploring Model Transferability through the Lens of Potential Energy","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lixiaotong97/ped","path":"metrics.py","file_url":"https://github.com/lixiaotong97/ped/blob/HEAD/metrics.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8ae5c6e4eb58226","mcp_get_code":{"code_sha256":"a8ae5c6e4eb58226"}},{"arxiv_id":"2308.11804","paper":"/paper/ceci-n-est-pas-une-pomme-adversarial","title":"Adversarial Illusions in Multi-Modal Embeddings","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ebagdasa/adversarial_illusions","path":"query_attack.py","file_url":"https://github.com/ebagdasa/adversarial_illusions/blob/HEAD/query_attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8bf374c9e1999142","mcp_get_code":{"code_sha256":"8bf374c9e1999142"}},{"arxiv_id":"2308.04836","paper":"/paper/intrinsic-motivation-via-surprise-memory","title":"Beyond Surprise: Improving Exploration Through Surprise Novelty","date":"2023-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thaihungle/sm","path":"utils.py","file_url":"https://github.com/thaihungle/sm/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"011537d0bea7fe09","mcp_get_code":{"code_sha256":"011537d0bea7fe09"}},{"arxiv_id":"2308.02097","paper":"/paper/multi-interactive-feature-learning-and-a-full","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runjia0124/coconet","path":"models/train_tasks.py","file_url":"https://github.com/runjia0124/coconet/blob/HEAD/models/train_tasks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7fbf8b3d61a9af4b","mcp_get_code":{"code_sha256":"7fbf8b3d61a9af4b"}},{"arxiv_id":"2308.00951","paper":"/paper/from-sparse-to-soft-mixtures-of-experts","title":"From Sparse to Soft Mixtures of Experts","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bwconrad/soft-moe","path":"soft_moe/soft_moe.py","file_url":"https://github.com/bwconrad/soft-moe/blob/HEAD/soft_moe/soft_moe.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"348d3e3d68c0c2dc","mcp_get_code":{"code_sha256":"348d3e3d68c0c2dc"}},{"arxiv_id":"2308.00951","paper":"/paper/from-sparse-to-soft-mixtures-of-experts","title":"From Sparse to Soft Mixtures of Experts","date":"2023-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bwconrad/soft-moe","path":"soft_moe/soft_moe.py","file_url":"https://github.com/bwconrad/soft-moe/blob/HEAD/soft_moe/soft_moe.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"84195cc106a2908b","mcp_get_code":{"code_sha256":"84195cc106a2908b"}},{"arxiv_id":"2306.03081","paper":"/paper/sequential-monte-carlo-steering-of-large","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","date":"2023-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"probcomp/hfppl","path":"llamppl/util.py","file_url":"https://github.com/probcomp/hfppl/blob/HEAD/llamppl/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":"20d709d931c06147","mcp_get_code":{"code_sha256":"20d709d931c06147"}},{"arxiv_id":"2306.01128","paper":"/paper/learning-transformer-programs-1","title":"Learning Transformer Programs","date":"2023-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/transformerprograms","path":"src/models/programs.py","file_url":"https://github.com/princeton-nlp/transformerprograms/blob/HEAD/src/models/programs.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3599c195e20c0fc","mcp_get_code":{"code_sha256":"e3599c195e20c0fc"}},{"arxiv_id":"2305.14251","paper":"/paper/factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/factscore","path":"factscore/npm.py","file_url":"https://github.com/shmsw25/factscore/blob/HEAD/factscore/npm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"925c59b7e44138ab","mcp_get_code":{"code_sha256":"925c59b7e44138ab"}},{"arxiv_id":"2303.14420","paper":"/paper/better-aligning-text-to-image-models-with","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","date":"2023-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tgxs002/align_sd","path":"select_training_images.py","file_url":"https://github.com/tgxs002/align_sd/blob/HEAD/select_training_images.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":"4cb345d10a4a752b","mcp_get_code":{"code_sha256":"4cb345d10a4a752b"}},{"arxiv_id":"2303.08658","paper":"/paper/skinned-motion-retargeting-with-residual","title":"Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry","date":"2023-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kebii/R2ET","path":"inference_bvh.py","file_url":"https://github.com/Kebii/R2ET/blob/HEAD/inference_bvh.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"645e56f7684d87a0","mcp_get_code":{"code_sha256":"645e56f7684d87a0"}},{"arxiv_id":"2303.03926","paper":"/paper/speak-foreign-languages-with-your-own-voice","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","date":"2023-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"plachtaa/vall-e-x","path":"modules/scaling.py","file_url":"https://github.com/plachtaa/vall-e-x/blob/HEAD/modules/scaling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c124aa8bd6b9ebe9","mcp_get_code":{"code_sha256":"c124aa8bd6b9ebe9"}},{"arxiv_id":"2302.12200","paper":"/paper/a-neural-span-based-continual-named-entity","title":"A Neural Span-Based Continual Named Entity Recognition Model","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qznan/SpanKL","path":"train_clner.py","file_url":"https://github.com/Qznan/SpanKL/blob/HEAD/train_clner.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":"8be5cd65e55e3370","mcp_get_code":{"code_sha256":"8be5cd65e55e3370"}},{"arxiv_id":"2302.01860","paper":"/paper/gladis-a-general-and-large-acronym","title":"GLADIS: A General and Large Acronym Disambiguation Benchmark","date":"2023-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tigerchen52/gladis","path":"inference/acrobert.py","file_url":"https://github.com/tigerchen52/gladis/blob/HEAD/inference/acrobert.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"e2d7e8e52b358025","mcp_get_code":{"code_sha256":"e2d7e8e52b358025"}},{"arxiv_id":"2301.02111","paper":"/paper/neural-codec-language-models-are-zero-shot","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","date":"2023-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lifeiteng/vall-e","path":"valle/modules/scaling.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/modules/scaling.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":"c124aa8bd6b9ebe9","mcp_get_code":{"code_sha256":"c124aa8bd6b9ebe9"}},{"arxiv_id":"2212.06801","paper":"/paper/a-fine-grained-comparison-of-pragmatic","title":"A fine-grained comparison of pragmatic language understanding in humans and language models","date":"2022-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jennhu/lm-pragmatics","path":"query_openai.py","file_url":"https://github.com/jennhu/lm-pragmatics/blob/HEAD/query_openai.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c4be464cbe63fba","mcp_get_code":{"code_sha256":"9c4be464cbe63fba"}},{"arxiv_id":"2212.04085","paper":"/paper/graph-matching-with-bi-level-noisy","title":"Graph Matching with Bi-level Noisy Correspondence","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lin-Yijie/Graph-Matching-Networks","path":"COMMON/src/lap_solvers/ILP.py","file_url":"https://github.com/Lin-Yijie/Graph-Matching-Networks/blob/HEAD/COMMON/src/lap_solvers/ILP.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"98bba89c2a19a3bb","mcp_get_code":{"code_sha256":"98bba89c2a19a3bb"}},{"arxiv_id":"2211.04079","paper":"/paper/copen-probing-conceptual-knowledge-in-pre","title":"COPEN: Probing Conceptual Knowledge in Pre-trained Language Models","date":"2022-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-KEG/COPEN","path":"code/finetuning/metrics.py","file_url":"https://github.com/THU-KEG/COPEN/blob/HEAD/code/finetuning/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa0f399def18c806","mcp_get_code":{"code_sha256":"aa0f399def18c806"}},{"arxiv_id":"2209.14941","paper":"/paper/eda-explicit-text-decoupling-and-dense","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","date":"2022-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yanmin-wu/eda","path":"src/grounding_evaluator.py","file_url":"https://github.com/yanmin-wu/eda/blob/HEAD/src/grounding_evaluator.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f89fc809b3a7824a","mcp_get_code":{"code_sha256":"f89fc809b3a7824a"}},{"arxiv_id":"2207.03036","paper":"/paper/not-all-models-are-equal-predicting-model","title":"Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space","date":"2022-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TencentARC/SFDA","path":"metrics.py","file_url":"https://github.com/TencentARC/SFDA/blob/HEAD/metrics.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a8ae5c6e4eb58226","mcp_get_code":{"code_sha256":"a8ae5c6e4eb58226"}},{"arxiv_id":"2207.01115","paper":"/paper/usher-unbiased-sampling-for-hindsight","title":"USHER: Unbiased Sampling for Hindsight Experience Replay","date":"2022-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schrammlb2/USHER_Implementation","path":"discrete_usher/clean_q_implementation.py","file_url":"https://github.com/schrammlb2/USHER_Implementation/blob/HEAD/discrete_usher/clean_q_implementation.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a6f0cbbf7e6a8d9","mcp_get_code":{"code_sha256":"4a6f0cbbf7e6a8d9"}},{"arxiv_id":"2206.05825","paper":"/paper/a-unified-approach-to-reinforcement-learning","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","date":"2022-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ryan-dorazio/mmd-dilated","path":"mmd_dilated/mmd_dilated.py","file_url":"https://github.com/ryan-dorazio/mmd-dilated/blob/HEAD/mmd_dilated/mmd_dilated.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50d5258bd0761c1b","mcp_get_code":{"code_sha256":"50d5258bd0761c1b"}},{"arxiv_id":"2206.05712","paper":"/paper/graph-based-spatial-transformer-with-memory-1","title":"Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction","date":"2022-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jacobieee/ST-MR","path":"code/pred_models.py","file_url":"https://github.com/Jacobieee/ST-MR/blob/HEAD/code/pred_models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c6972c9a6a8d0ea2","mcp_get_code":{"code_sha256":"c6972c9a6a8d0ea2"}},{"arxiv_id":"2206.01451","paper":"/paper/learning-distributed-and-fair-policies-for","title":"Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game","date":"2022-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyuanyaoj/marllb","path":"src/lb/baseline.py","file_url":"https://github.com/zhiyuanyaoj/marllb/blob/HEAD/src/lb/baseline.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":"27a7b444209f077d","mcp_get_code":{"code_sha256":"27a7b444209f077d"}},{"arxiv_id":"2205.12134","paper":"/paper/adversarial-attack-on-attackers-post-process","title":"Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks","date":"2022-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sizhe-chen/aaa","path":"utils.py","file_url":"https://github.com/sizhe-chen/aaa/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"785d346b27b67e09","mcp_get_code":{"code_sha256":"785d346b27b67e09"}},{"arxiv_id":"2204.08958","paper":"/paper/maniqa-multi-dimension-attention-network-for","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","date":"2022-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhewu/assessor360","path":"inference_one_image.py","file_url":"https://github.com/tianhewu/assessor360/blob/HEAD/inference_one_image.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82a1d89eac8a63ca","mcp_get_code":{"code_sha256":"82a1d89eac8a63ca"}},{"arxiv_id":"2204.06272","paper":"/paper/3d-sps-single-stage-3d-visual-grounding-via","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","date":"2022-04-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fjhzhixi/3D-SPS","path":"lib/ap_helper.py","file_url":"https://github.com/fjhzhixi/3D-SPS/blob/HEAD/lib/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2203.15565","paper":"/paper/killing-two-birds-with-one-stone-efficient","title":"Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC","date":"2022-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangyucheng000/-insightface","path":"python-package/insightface/model_zoo/retinaface.py","file_url":"https://github.com/yangyucheng000/-insightface/blob/HEAD/python-package/insightface/model_zoo/retinaface.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"011537d0bea7fe09","mcp_get_code":{"code_sha256":"011537d0bea7fe09"}},{"arxiv_id":"2203.09440","paper":"/paper/to-scene-a-large-scale-dataset-for","title":"TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GAP-LAB-CUHK-SZ/TO-Scene","path":"obj_det/models/ap_helper.py","file_url":"https://github.com/GAP-LAB-CUHK-SZ/TO-Scene/blob/HEAD/obj_det/models/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2203.08958","paper":"/paper/on-the-usefulness-of-the-fit-on-the-test-view","title":"On the Usefulness of the Fit-on-the-Test View on Evaluating Calibration of Classifiers","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"markus93/fit-on-the-test","path":"Experiments_Pseudo/cal_methods.py","file_url":"https://github.com/markus93/fit-on-the-test/blob/HEAD/Experiments_Pseudo/cal_methods.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"80483261c3f6087d","mcp_get_code":{"code_sha256":"80483261c3f6087d"}},{"arxiv_id":"2203.06462","paper":"/paper/low-rank-softmax-can-have-unargmaxable-1","title":"Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice","date":"2022-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andreasgrv/unargmaxable","path":"paper/plots/stolen_probability.py","file_url":"https://github.com/andreasgrv/unargmaxable/blob/HEAD/paper/plots/stolen_probability.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a612b0389a399641","mcp_get_code":{"code_sha256":"a612b0389a399641"}},{"arxiv_id":"2203.05203","paper":"/paper/more-multi-order-relation-mining-for-dense","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","date":"2022-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SxJyJay/MORE","path":"lib/ap_helper.py","file_url":"https://github.com/SxJyJay/MORE/blob/HEAD/lib/ap_helper.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":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2202.12295","paper":"/paper/factorizer-a-scalable-interpretable-approach","title":"Factorizer: A Scalable Interpretable Approach to Context Modeling for Medical Image Segmentation","date":"2022-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pashtari/factorizer","path":"factorizer/factorization/operations.py","file_url":"https://github.com/pashtari/factorizer/blob/HEAD/factorizer/factorization/operations.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":"c2b903446314fbd0","mcp_get_code":{"code_sha256":"c2b903446314fbd0"}},{"arxiv_id":"2202.11356","paper":"/paper/preformer-predictive-transformer-with-multi","title":"Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting","date":"2022-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ddz16/Preformer","path":"layers/SelfAttention_Family.py","file_url":"https://github.com/ddz16/Preformer/blob/HEAD/layers/SelfAttention_Family.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c80a100f32887d8","mcp_get_code":{"code_sha256":"3c80a100f32887d8"}},{"arxiv_id":"2202.07304","paper":"/paper/xai-for-transformers-better-explanations","title":"XAI for Transformers: Better Explanations through Conservative Propagation","date":"2022-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ameenali/xai_transformers","path":"attribution.py","file_url":"https://github.com/ameenali/xai_transformers/blob/HEAD/attribution.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91fe7a23c1c052b7","mcp_get_code":{"code_sha256":"91fe7a23c1c052b7"}},{"arxiv_id":"2202.06602","paper":"/paper/neural-re-ranking-in-multi-stage-recommender","title":"Neural Re-ranking in Multi-stage Recommender Systems: A Review","date":"2022-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"librerank-community/librerank","path":"librerank/utils.py","file_url":"https://github.com/librerank-community/librerank/blob/HEAD/librerank/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6122f021db6d387","mcp_get_code":{"code_sha256":"b6122f021db6d387"}},{"arxiv_id":"2201.08044","paper":"/paper/metropolis-augmented-hamiltonian-monte-carlo","title":"Metropolis Augmented Hamiltonian Monte Carlo","date":null,"month_inferred_from_arxiv_id":"2022-01","title_source":"archive","repo":"StannisZhou/mixed_hmc","path":"momentum/hmc/mixed_hmc_jax.py","file_url":"https://github.com/StannisZhou/mixed_hmc/blob/HEAD/momentum/hmc/mixed_hmc_jax.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfa2b9d7cdc8e473","mcp_get_code":{"code_sha256":"dfa2b9d7cdc8e473"}},{"arxiv_id":"2111.07970","paper":"/paper/triggerless-backdoor-attack-for-nlp-tasks","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","date":"2021-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leileigan/clean_label_textual_backdoor_attack","path":"OpenAttack/attackers/genetic.py","file_url":"https://github.com/leileigan/clean_label_textual_backdoor_attack/blob/HEAD/OpenAttack/attackers/genetic.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"54948e052031386e","mcp_get_code":{"code_sha256":"54948e052031386e"}},{"arxiv_id":"2111.05498","paper":"/paper/attention-approximates-sparse-distributed","title":"Attention Approximates Sparse Distributed Memory","date":"2021-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trentbrick/attention-approximates-sdm","path":"SDM_Circ_Inter_Funcs.py","file_url":"https://github.com/trentbrick/attention-approximates-sdm/blob/HEAD/SDM_Circ_Inter_Funcs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df0360e77dc451b9","mcp_get_code":{"code_sha256":"df0360e77dc451b9"}},{"arxiv_id":"2111.02080","paper":"/paper/an-explanation-of-in-context-learning-as-1","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","date":"2021-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"p-lambda/incontext-learning","path":"generate_data.py","file_url":"https://github.com/p-lambda/incontext-learning/blob/HEAD/generate_data.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d8e37876ec1be74c","mcp_get_code":{"code_sha256":"d8e37876ec1be74c"}},{"arxiv_id":"2111.00941","paper":"/paper/turning-traffic-monitoring-cameras-into","title":"Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation","date":"2021-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zijianhu/traffic_density_estimation","path":"camera_calibration/util_files/process.py","file_url":"https://github.com/zijianhu/traffic_density_estimation/blob/HEAD/camera_calibration/util_files/process.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":"c2354886a9598fe0","mcp_get_code":{"code_sha256":"c2354886a9598fe0"}},{"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":"evaluate.py","file_url":"https://github.com/blacknoodle/tucore-gcn/blob/HEAD/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb5cbea0e8219ff5","mcp_get_code":{"code_sha256":"cb5cbea0e8219ff5"}},{"arxiv_id":"2108.11577","paper":"/paper/machine-unlearning-of-features-and-labels","title":"Machine Unlearning of Features and Labels","date":"2021-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alewarne/machineunlearning","path":"Unlearner/ensemble.py","file_url":"https://github.com/alewarne/machineunlearning/blob/HEAD/Unlearner/ensemble.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0d8549e3db234f8","mcp_get_code":{"code_sha256":"d0d8549e3db234f8"}},{"arxiv_id":"2107.08861","paper":"/paper/volcanoml-speeding-up-end-to-end-automl-via","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","date":"2021-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thomas-young-2013/mindware","path":"mindware/components/utils/model_util.py","file_url":"https://github.com/thomas-young-2013/mindware/blob/HEAD/mindware/components/utils/model_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8bfe49aa3252c0d8","mcp_get_code":{"code_sha256":"8bfe49aa3252c0d8"}},{"arxiv_id":"2106.14574","paper":"/paper/quantifying-social-biases-in-nlp-a","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","date":"2021-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/generalized-fairness-metrics","path":"src/models/process_predictions.py","file_url":"https://github.com/amazon-science/generalized-fairness-metrics/blob/HEAD/src/models/process_predictions.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":"e1a1ac537cadf5d0","mcp_get_code":{"code_sha256":"e1a1ac537cadf5d0"}},{"arxiv_id":"2106.08408","paper":"/paper/seeing-through-clouds-in-satellite-images","title":"Seeing Through Clouds in Satellite Images","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/farmvibes-ai","path":"ops/compute_cloud_prob/compute_cloud_prob.py","file_url":"https://github.com/microsoft/farmvibes-ai/blob/HEAD/ops/compute_cloud_prob/compute_cloud_prob.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b111adfaff1bbd9","mcp_get_code":{"code_sha256":"1b111adfaff1bbd9"}},{"arxiv_id":"2106.04696","paper":"/paper/curriculum-design-for-teaching-via","title":"Curriculum Design for Teaching via Demonstrations: Theory and Applications","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adishs/neurips2021_curriculum-teaching-demonstrations_code","path":"code_cardriving/IRL/teacher.py","file_url":"https://github.com/adishs/neurips2021_curriculum-teaching-demonstrations_code/blob/HEAD/code_cardriving/IRL/teacher.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"113ce2c0734fb450","mcp_get_code":{"code_sha256":"113ce2c0734fb450"}},{"arxiv_id":"2105.15010","paper":"/paper/querynet-an-efficient-attack-framework-with","title":"Query Attack by Multi-Identity Surrogates","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenchen1998/querynet","path":"utils.py","file_url":"https://github.com/allenchen1998/querynet/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":"8bf374c9e1999142","mcp_get_code":{"code_sha256":"8bf374c9e1999142"}},{"arxiv_id":"2105.12085","paper":"/paper/dsanet-dynamic-segment-aggregation-network","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","date":"2021-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whwu95/DSANet","path":"codes/core/evaluation/accuracy.py","file_url":"https://github.com/whwu95/DSANet/blob/HEAD/codes/core/evaluation/accuracy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"622de14b270a7195","mcp_get_code":{"code_sha256":"622de14b270a7195"}},{"arxiv_id":"2105.06506","paper":"/paper/sanity-simulations-for-saliency-methods","title":"Sanity Simulations for Saliency Methods","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wnstlr/SMERF","path":"smerf/explanations.py","file_url":"https://github.com/wnstlr/SMERF/blob/HEAD/smerf/explanations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1d161285c1b841e","mcp_get_code":{"code_sha256":"c1d161285c1b841e"}},{"arxiv_id":"2104.09791","paper":"/paper/b-prop-bootstrapped-pre-training-with","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","date":"2021-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Albert-Ma/PROP","path":"prop/multiprocessing_generate_word_sets.py","file_url":"https://github.com/Albert-Ma/PROP/blob/HEAD/prop/multiprocessing_generate_word_sets.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":"2871908e26a30647","mcp_get_code":{"code_sha256":"2871908e26a30647"}},{"arxiv_id":"2104.01528","paper":"/paper/sgcn-sparse-graph-convolution-network-for","title":"SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction","date":"2021-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyqcom/sgcn","path":"postprocess.py","file_url":"https://github.com/lyqcom/sgcn/blob/HEAD/postprocess.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":"a37b39bfcca0d059","mcp_get_code":{"code_sha256":"a37b39bfcca0d059"}},{"arxiv_id":"2104.00795","paper":"/paper/no-cost-likelihood-manipulation-at-test-time","title":"No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sgk98/CRM-Better-Mistakes","path":"src/compute_results.py","file_url":"https://github.com/sgk98/CRM-Better-Mistakes/blob/HEAD/src/compute_results.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4471357a1f78d539","mcp_get_code":{"code_sha256":"4471357a1f78d539"}},{"arxiv_id":"2103.15692","paper":"/paper/self-constructing-neural-networks-through","title":"Self-Constructing Neural Networks Through Random Mutation","date":"2021-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samuelschmidgall/randommutationsearch","path":"random_mutation_search.py","file_url":"https://github.com/samuelschmidgall/randommutationsearch/blob/HEAD/random_mutation_search.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"2010.12777","paper":"/paper/improving-multilingual-models-with-language","title":"Improving Multilingual Models with Language-Clustered Vocabularies","date":"2020-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"afshinrahimi/mmner","path":"models.py","file_url":"https://github.com/afshinrahimi/mmner/blob/HEAD/models.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":"a585b44308980803","mcp_get_code":{"code_sha256":"a585b44308980803"}},{"arxiv_id":"2010.04159","paper":"/paper/deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyqcom/detr","path":"src/DETR/matcher_np.py","file_url":"https://github.com/lyqcom/detr/blob/HEAD/src/DETR/matcher_np.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":"4c36dfd151b487bb","mcp_get_code":{"code_sha256":"4c36dfd151b487bb"}},{"arxiv_id":"2010.03403","paper":"/paper/universal-weighting-metric-learning-for-cross-1","title":"Universal Weighting Metric Learning for Cross-Modal Matching","date":"2020-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wayne980/PolyLoss","path":"evaluation.py","file_url":"https://github.com/wayne980/PolyLoss/blob/HEAD/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"652f07c5ff410713","mcp_get_code":{"code_sha256":"652f07c5ff410713"}},{"arxiv_id":"2009.03509","paper":"/paper/masked-label-prediction-unified-massage","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","date":"2020-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"willyfh/graph-transformer","path":"graph_transformer/graph_transformer_model.py","file_url":"https://github.com/willyfh/graph-transformer/blob/HEAD/graph_transformer/graph_transformer_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f6500993366c0f7","mcp_get_code":{"code_sha256":"2f6500993366c0f7"}},{"arxiv_id":"2009.03300","paper":"/paper/measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","date":"2020-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ollmer/mmlu","path":"evaluate.py","file_url":"https://github.com/ollmer/mmlu/blob/HEAD/evaluate.py","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19f01570b0a18e2b","mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"arxiv_id":"2008.08476","paper":"/paper/nascaps-a-framework-for-neural-architecture","title":"NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks","date":"2020-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ehw-fit/nascaps","path":"layers/CapsuleLayers.py","file_url":"https://github.com/ehw-fit/nascaps/blob/HEAD/layers/CapsuleLayers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64fc32d35c3074b1","mcp_get_code":{"code_sha256":"64fc32d35c3074b1"}},{"arxiv_id":"2007.09933","paper":"/paper/motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arunos728/MotionSqueeze","path":"ops/utils.py","file_url":"https://github.com/arunos728/MotionSqueeze/blob/HEAD/ops/utils.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":"2fc0c71db48a9af8","mcp_get_code":{"code_sha256":"2fc0c71db48a9af8"}},{"arxiv_id":"2007.05233","paper":"/paper/continual-adaptation-for-deep-stereo","title":"Continual Adaptation for Deep Stereo","date":"2020-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CVLAB-Unibo/Real-time-self-adaptive-deep-stereo","path":"Stereo_Continual_Adaptation.py","file_url":"https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo/blob/HEAD/Stereo_Continual_Adaptation.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a49ec0b422e77ed3","mcp_get_code":{"code_sha256":"a49ec0b422e77ed3"}},{"arxiv_id":"2007.02832","paper":"/paper/maximum-entropy-gain-exploration-for-long","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","date":"2020-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"penn-pal-lab/peg","path":"dreamerv2/goal_picker.py","file_url":"https://github.com/penn-pal-lab/peg/blob/HEAD/dreamerv2/goal_picker.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"083546dc5ac62494","mcp_get_code":{"code_sha256":"083546dc5ac62494"}},{"arxiv_id":"2007.00808","paper":"/paper/approximate-nearest-neighbor-negative","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","date":"2020-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/ANCE","path":"model/SEED_Encoder/modules.py","file_url":"https://github.com/microsoft/ANCE/blob/HEAD/model/SEED_Encoder/modules.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4d9cafead3a750e","mcp_get_code":{"code_sha256":"f4d9cafead3a750e"}},{"arxiv_id":"2006.15426","paper":"/paper/molecule-edit-graph-attention-network","title":"Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits","date":"2020-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"molecule-one/megan","path":"src/model/megan_modules/decoder.py","file_url":"https://github.com/molecule-one/megan/blob/HEAD/src/model/megan_modules/decoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ecfb638373066abe","mcp_get_code":{"code_sha256":"ecfb638373066abe"}},{"arxiv_id":"2006.15057","paper":"/paper/a-loss-function-for-generative-neural","title":"A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model","date":"2020-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"steffenczolbe/perceptualsimilarity","path":"src/loss/watson.py","file_url":"https://github.com/steffenczolbe/perceptualsimilarity/blob/HEAD/src/loss/watson.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cc287dc402b9202b","mcp_get_code":{"code_sha256":"cc287dc402b9202b"}},{"arxiv_id":"2006.04647","paper":"/paper/neural-architecture-search-without-training","title":"Neural Architecture Search without Training","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlinc1905/evolutionary-reinforcement-learner","path":"models/mlp.py","file_url":"https://github.com/nlinc1905/evolutionary-reinforcement-learner/blob/HEAD/models/mlp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2374481500fc132c","mcp_get_code":{"code_sha256":"2374481500fc132c"}},{"arxiv_id":"2006.04176","paper":"/paper/deep-active-inference-agents-using-monte","title":"Deep active inference agents using Monte-Carlo methods","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zfountas/deep-active-inference-mc","path":"test_demo.py","file_url":"https://github.com/zfountas/deep-active-inference-mc/blob/HEAD/test_demo.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"cd98260d20abd01f","mcp_get_code":{"code_sha256":"cd98260d20abd01f"}},{"arxiv_id":"2005.12872","paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LKLQQ/detr","path":"src/matcher.py","file_url":"https://github.com/LKLQQ/detr/blob/HEAD/src/matcher.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":"4c36dfd151b487bb","mcp_get_code":{"code_sha256":"4c36dfd151b487bb"}},{"arxiv_id":"2005.06803","paper":"/paper/tam-temporal-adaptive-module-for-video","title":"TAM: Temporal Adaptive Module for Video Recognition","date":"2020-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liu-zhy/TANet","path":"ops/utils.py","file_url":"https://github.com/liu-zhy/TANet/blob/HEAD/ops/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":"2fc0c71db48a9af8","mcp_get_code":{"code_sha256":"2fc0c71db48a9af8"}},{"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/evaluate.py","file_url":"https://github.com/nlpdata/dialogre/blob/HEAD/bert/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"cb5cbea0e8219ff5","mcp_get_code":{"code_sha256":"cb5cbea0e8219ff5"}},{"arxiv_id":"2004.05679","paper":"/paper/mlcvnet-multi-level-context-votenet-for-3d","title":"MLCVNet: Multi-Level Context VoteNet for 3D Object Detection","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NUAAXQ/MLCVNet","path":"models/dump_helper.py","file_url":"https://github.com/NUAAXQ/MLCVNet/blob/HEAD/models/dump_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"2004.01888","paper":"/paper/a-simple-baseline-for-multi-object-tracking","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","date":"2020-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nolanzzz/MTMCT","path":"util.py","file_url":"https://github.com/nolanzzz/MTMCT/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66744e8b3c8d06d3","mcp_get_code":{"code_sha256":"66744e8b3c8d06d3"}},{"arxiv_id":"2002.12326","paper":"/paper/estimating-the-effects-of-continuous-valued","title":"Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks","date":"2020-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ioanabica/SCIGAN","path":"data_simulation.py","file_url":"https://github.com/ioanabica/SCIGAN/blob/HEAD/data_simulation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8da1f8c64d19ad65","mcp_get_code":{"code_sha256":"8da1f8c64d19ad65"}},{"arxiv_id":"2001.06499","paper":"/paper/temporal-interlacing-network","title":"Temporal Interlacing Network","date":"2020-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eynaij/X-Temporal_catdim","path":"x_temporal/core/utils.py","file_url":"https://github.com/eynaij/X-Temporal_catdim/blob/HEAD/x_temporal/core/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fc0c71db48a9af8","mcp_get_code":{"code_sha256":"2fc0c71db48a9af8"}},{"arxiv_id":"1912.11803","paper":"/paper/sess-self-ensembling-semi-supervised-3d","title":"SESS: Self-Ensembling Semi-Supervised 3D Object Detection","date":"2019-12-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Na-Z/sess","path":"models/ap_helper.py","file_url":"https://github.com/Na-Z/sess/blob/HEAD/models/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"1912.10917","paper":"/paper/fasterseg-searching-for-faster-real-time-1","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","date":"2019-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TAMU-VITA/FasterSeg","path":"latency/model_seg.py","file_url":"https://github.com/TAMU-VITA/FasterSeg/blob/HEAD/latency/model_seg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"961eced33874cb53","mcp_get_code":{"code_sha256":"961eced33874cb53"}},{"arxiv_id":"1909.04852","paper":"/paper/mixed-hamiltonian-monte-carlo-for-mixed","title":"Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables","date":null,"month_inferred_from_arxiv_id":"2019-09","title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"dfa2b9d7cdc8e473","mcp_get_code":{"code_sha256":"dfa2b9d7cdc8e473"}},{"arxiv_id":"1909.04847","paper":"/paper/recsim-a-configurable-simulation-platform-for","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/recsim","path":"recsim/choice_model.py","file_url":"https://github.com/google-research/recsim/blob/HEAD/recsim/choice_model.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":"a238753019219ccc","mcp_get_code":{"code_sha256":"a238753019219ccc"}},{"arxiv_id":"1908.10063","paper":"/paper/finbert-financial-sentiment-analysis-with-pre","title":"FinBERT: Financial Sentiment Analysis with Pre-trained Language Models","date":"2019-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ProsusAI/finBERT","path":"finbert/utils.py","file_url":"https://github.com/ProsusAI/finBERT/blob/HEAD/finbert/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":"a88ac8d98297ec6c","mcp_get_code":{"code_sha256":"a88ac8d98297ec6c"}},{"arxiv_id":"1908.09453","paper":"/paper/openspiel-a-framework-for-reinforcement","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","date":"2019-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qmaai/open_spiel","path":"open_spiel/python/algorithms/ars.py","file_url":"https://github.com/qmaai/open_spiel/blob/HEAD/open_spiel/python/algorithms/ars.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":"a585b44308980803","mcp_get_code":{"code_sha256":"a585b44308980803"}},{"arxiv_id":"1907.06679","paper":"/paper/towards-near-imperceptible-steganographic","title":"Towards Near-imperceptible Steganographic Text","date":"2019-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"falcondai/lm-steganography","path":"bucket.py","file_url":"https://github.com/falcondai/lm-steganography/blob/HEAD/bucket.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5bed7d25d3a24a2f","mcp_get_code":{"code_sha256":"5bed7d25d3a24a2f"}},{"arxiv_id":"1907.04502","paper":"/paper/deepxde-a-deep-learning-library-for-solving","title":"DeepXDE: A deep learning library for solving differential equations","date":"2019-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PhysicsTeacher13/Deepxde","path":"deepxde/math_ops.py","file_url":"https://github.com/PhysicsTeacher13/Deepxde/blob/HEAD/deepxde/math_ops.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":"6f58b8df8556a3aa","mcp_get_code":{"code_sha256":"6f58b8df8556a3aa"}},{"arxiv_id":"1906.05394","paper":"/paper/neural-arabic-question-answering","title":"Neural Arabic Question Answering","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"husseinmozannar/SOQAL","path":"soqal.py","file_url":"https://github.com/husseinmozannar/SOQAL/blob/HEAD/soqal.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"1906.04045","paper":"/paper/phiseg-capturing-uncertainty-in-medical-image","title":"PHiSeg: Capturing Uncertainty in Medical Image Segmentation","date":"2019-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"winstonhutiger/phiseg-code","path":"phiseg_makegif_samples.py","file_url":"https://github.com/winstonhutiger/phiseg-code/blob/HEAD/phiseg_makegif_samples.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":"c8ac39e53aaa7830","mcp_get_code":{"code_sha256":"c8ac39e53aaa7830"}},{"arxiv_id":"1906.01827","paper":"/paper/data-sketching-for-faster-training-of-machine","title":"Coresets for Data-efficient Training of Machine Learning Models","date":"2019-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baharanm/craig","path":"logistic.py","file_url":"https://github.com/baharanm/craig/blob/HEAD/logistic.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa0acf499f826391","mcp_get_code":{"code_sha256":"aa0acf499f826391"}},{"arxiv_id":"1905.11286","paper":"/paper/stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/OpenSeq2Seq","path":"frame_asr.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/frame_asr.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":"758f37e8c4f07d0f","mcp_get_code":{"code_sha256":"758f37e8c4f07d0f"}},{"arxiv_id":"1905.03381","paper":"/paper/190503381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","date":"2019-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangjiong724/autoassist-exp","path":"image_classification/assistant.py","file_url":"https://github.com/zhangjiong724/autoassist-exp/blob/HEAD/image_classification/assistant.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"91fe7a23c1c052b7","mcp_get_code":{"code_sha256":"91fe7a23c1c052b7"}},{"arxiv_id":"1905.01413","paper":"/paper/arsm-augment-reinforce-swap-merge-estimator","title":"ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables","date":"2019-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ARM-gradient/ARSM","path":"toy/ARSM_Univariate.py","file_url":"https://github.com/ARM-gradient/ARSM/blob/HEAD/toy/ARSM_Univariate.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad039f77ef1e89fc","mcp_get_code":{"code_sha256":"ad039f77ef1e89fc"}},{"arxiv_id":"1905.00641","paper":"/paper/190500641","title":"RetinaFace: Single-stage Dense Face Localisation in the Wild","date":"2019-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nhatduy19599/insightface-master","path":"python-package/insightface/model_zoo/scrfd.py","file_url":"https://github.com/nhatduy19599/insightface-master/blob/HEAD/python-package/insightface/model_zoo/scrfd.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"011537d0bea7fe09","mcp_get_code":{"code_sha256":"011537d0bea7fe09"}},{"arxiv_id":"1904.10729","paper":"/paper/neural-logic-reinforcement-learning","title":"Neural Logic Reinforcement Learning","date":"2019-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengyaoJiang/NLRL","path":"core/induction.py","file_url":"https://github.com/ZhengyaoJiang/NLRL/blob/HEAD/core/induction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fa20456ba9a25be","mcp_get_code":{"code_sha256":"2fa20456ba9a25be"}},{"arxiv_id":"1904.09664","paper":"/paper/deep-hough-voting-for-3d-object-detection-in","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","date":"2019-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LONG-9621/VoteNet","path":"models/ap_helper.py","file_url":"https://github.com/LONG-9621/VoteNet/blob/HEAD/models/ap_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"1a034a72c15f9903","mcp_get_code":{"code_sha256":"1a034a72c15f9903"}},{"arxiv_id":"1904.07850","paper":"/paper/objects-as-points","title":"Objects as Points","date":"2019-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlongRide/CenterNet_anchor_free","path":"1_util.py","file_url":"https://github.com/AlongRide/CenterNet_anchor_free/blob/HEAD/1_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66744e8b3c8d06d3","mcp_get_code":{"code_sha256":"66744e8b3c8d06d3"}},{"arxiv_id":"1903.03503","paper":"/paper/unsupervised-data-imputation-via-variational","title":"Unsupervised Data Imputation via Variational Inference of Deep Subspaces","date":"2019-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adalca/neuron","path":"neurite/py/utils.py","file_url":"https://github.com/adalca/neuron/blob/HEAD/neurite/py/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":"b578a1d36f2dab7a","mcp_get_code":{"code_sha256":"b578a1d36f2dab7a"}},{"arxiv_id":"1902.06022","paper":"/paper/a-fully-differentiable-beam-search-decoder","title":"A Fully Differentiable Beam Search Decoder","date":"2019-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johnhw/differentiable_sorting","path":"differentiable_sorting/differentiable_sorting.py","file_url":"https://github.com/johnhw/differentiable_sorting/blob/HEAD/differentiable_sorting/differentiable_sorting.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"66850af2b5403afd","mcp_get_code":{"code_sha256":"66850af2b5403afd"}},{"arxiv_id":"1901.10912","paper":"/paper/a-meta-transfer-objective-for-learning-to","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","date":"2019-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ec6dde01667145e58de60f864e05a4/CausalOptimizationAnon","path":"causal_meta/utils/numpy_utils.py","file_url":"https://github.com/ec6dde01667145e58de60f864e05a4/CausalOptimizationAnon/blob/HEAD/causal_meta/utils/numpy_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00e92b434199185e","mcp_get_code":{"code_sha256":"00e92b434199185e"}},{"arxiv_id":"1901.09216","paper":"/paper/multi-agent-generalized-recursive-reasoning","title":"Modelling Bounded Rationality in Multi-Agent Interactions by Generalized Recursive Reasoning","date":"2019-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ying-wen/gr2","path":"code/maci/utils.py","file_url":"https://github.com/ying-wen/gr2/blob/HEAD/code/maci/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91fe7a23c1c052b7","mcp_get_code":{"code_sha256":"91fe7a23c1c052b7"}},{"arxiv_id":"1901.08394","paper":"/paper/application-of-decision-rules-for-handling","title":"Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation","date":"2019-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"robin-chan/decision-rules","path":"scripts-predict/predict.py","file_url":"https://github.com/robin-chan/decision-rules/blob/HEAD/scripts-predict/predict.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"442a2012d75c4821","mcp_get_code":{"code_sha256":"442a2012d75c4821"}},{"arxiv_id":"1901.06852","paper":"/paper/calibration-with-bias-corrected-temperature","title":"Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation","date":"2019-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kundajelab/abstention","path":"abstention/calibration.py","file_url":"https://github.com/kundajelab/abstention/blob/HEAD/abstention/calibration.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a0b58e25479df38","mcp_get_code":{"code_sha256":"1a0b58e25479df38"}},{"arxiv_id":"1901.02477","paper":"/paper/differentially-private-generative-adversarial","title":"Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data","date":null,"month_inferred_from_arxiv_id":"2019-01","title_source":"archive","repo":"SAP-samples/security-research-differentially-private-generative-models","path":"models.py","file_url":"https://github.com/SAP-samples/security-research-differentially-private-generative-models/blob/HEAD/models.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":"f7b3855bbe962c24","mcp_get_code":{"code_sha256":"f7b3855bbe962c24"}},{"arxiv_id":"1811.04187","paper":"/paper/the-global-convergence-of-the-alternating","title":"Accelerated Gradient-free Neural Network Training by Multi-convex Alternating Optimization","date":null,"month_inferred_from_arxiv_id":"2018-11","title_source":"archive","repo":"xianggebenben/mdlam","path":"mDLAM.py","file_url":"https://github.com/xianggebenben/mdlam/blob/HEAD/mDLAM.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81767458c6ff4e4d","mcp_get_code":{"code_sha256":"81767458c6ff4e4d"}},{"arxiv_id":"1810.03947","paper":"/paper/texttovec-deep-contextualized-neural","title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","date":"2018-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pgcool/textTOvec","path":"train_model.py","file_url":"https://github.com/pgcool/textTOvec/blob/HEAD/train_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"51f9969762b91ea3","mcp_get_code":{"code_sha256":"51f9969762b91ea3"}},{"arxiv_id":"1810.03728","paper":"/paper/probabilistic-semantic-inpainting-with-pixel","title":"Probabilistic Semantic Inpainting with Pixel Constrained CNNs","date":"2018-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Schlumberger/pixel-constrained-cnn-tf","path":"utils.py","file_url":"https://github.com/Schlumberger/pixel-constrained-cnn-tf/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":"450372368e548e3b","mcp_get_code":{"code_sha256":"450372368e548e3b"}},{"arxiv_id":"1809.03627","paper":"/paper/clustergan-latent-space-clustering-in","title":"ClusterGAN : Latent Space Clustering in Generative Adversarial Networks","date":"2018-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eriklindernoren/PyTorch-GAN","path":"implementations/cluster_gan/clustergan.py","file_url":"https://github.com/eriklindernoren/PyTorch-GAN/blob/HEAD/implementations/cluster_gan/clustergan.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dd816971308e752","mcp_get_code":{"code_sha256":"8dd816971308e752"}},{"arxiv_id":"1809.00388","paper":"/paper/mtnt-a-testbed-for-machine-translation-of","title":"MTNT: A Testbed for Machine Translation of Noisy Text","date":"2018-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pmichel31415/mtnt","path":"src/util.py","file_url":"https://github.com/pmichel31415/mtnt/blob/HEAD/src/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4499c317153eeb2d","mcp_get_code":{"code_sha256":"4499c317153eeb2d"}},{"arxiv_id":"1806.07470","paper":"/paper/contrastive-explanations-with-local-foil","title":"Contrastive Explanations with Local Foil Trees","date":"2018-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MarcelRobeer/ContrastiveExplanation","path":"contrastive_explanation/utils.py","file_url":"https://github.com/MarcelRobeer/ContrastiveExplanation/blob/HEAD/contrastive_explanation/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":"5a872a566dbb586d","mcp_get_code":{"code_sha256":"5a872a566dbb586d"}},{"arxiv_id":"1806.06498","paper":"/paper/conditional-affordance-learning-for-driving","title":"Conditional Affordance Learning for Driving in Urban Environments","date":"2018-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xl-sr/CAL","path":"python_client/agents/CAL_agent/perception/cal_network.py","file_url":"https://github.com/xl-sr/CAL/blob/HEAD/python_client/agents/CAL_agent/perception/cal_network.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c4be464cbe63fba","mcp_get_code":{"code_sha256":"9c4be464cbe63fba"}},{"arxiv_id":"1806.04743","paper":"/paper/inferno-inference-aware-neural-optimisation","title":"INFERNO: Inference-Aware Neural Optimisation","date":"2018-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pablodecm/paper-inferno","path":"code/train_helpers.py","file_url":"https://github.com/pablodecm/paper-inferno/blob/HEAD/code/train_helpers.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":"b408147a7d567f0d","mcp_get_code":{"code_sha256":"b408147a7d567f0d"}},{"arxiv_id":"1805.04096","paper":"/paper/fighting-fake-news-image-splice-detection-via","title":"Fighting Fake News: Image Splice Detection via Learned Self-Consistency","date":"2018-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minyoungg/selfconsistency","path":"lib/utils/util.py","file_url":"https://github.com/minyoungg/selfconsistency/blob/HEAD/lib/utils/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":"19daaab909243516","mcp_get_code":{"code_sha256":"19daaab909243516"}},{"arxiv_id":"1805.02628","paper":"/paper/prada-protecting-against-dnn-model-stealing","title":"PRADA: Protecting against DNN Model Stealing Attacks","date":null,"month_inferred_from_arxiv_id":"2018-05","title_source":"archive","repo":"SSGAalto/prada-protecting-against-dnn-model-stealing-attacks","path":"src/growing_set_ops.py","file_url":"https://github.com/SSGAalto/prada-protecting-against-dnn-model-stealing-attacks/blob/HEAD/src/growing_set_ops.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":"b5f6b17164e5a0c1","mcp_get_code":{"code_sha256":"b5f6b17164e5a0c1"}},{"arxiv_id":"1804.08049","paper":"/paper/semi-supervised-user-geolocation-via-graph","title":"Semi-supervised User Geolocation via Graph Convolutional Networks","date":"2018-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"91fe7a23c1c052b7","mcp_get_code":{"code_sha256":"91fe7a23c1c052b7"}},{"arxiv_id":"1804.00090","paper":"/paper/floornet-a-unified-framework-for-floorplan","title":"FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans","date":"2018-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"art-programmer/FloorNet","path":"utils.py","file_url":"https://github.com/art-programmer/FloorNet/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":"70ee1b0d14e84ac1","mcp_get_code":{"code_sha256":"70ee1b0d14e84ac1"}},{"arxiv_id":"1803.08024","paper":"/paper/stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abhidipbhattacharyya/srl_aware_ret","path":"evaluation.py","file_url":"https://github.com/abhidipbhattacharyya/srl_aware_ret/blob/HEAD/evaluation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"652f07c5ff410713","mcp_get_code":{"code_sha256":"652f07c5ff410713"}},{"arxiv_id":"1803.05337","paper":"/paper/learning-to-recognize-musical-genre-from","title":"Learning to Recognize Musical Genre from Audio","date":"2018-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crowdAI/crowdai-musical-genre-recognition-starter-kit","path":"random_submission.py","file_url":"https://github.com/crowdAI/crowdai-musical-genre-recognition-starter-kit/blob/HEAD/random_submission.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f9b15275ca5759c","mcp_get_code":{"code_sha256":"7f9b15275ca5759c"}},{"arxiv_id":"1711.02013","paper":"/paper/neural-language-modeling-by-jointly-learning","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","date":"2017-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nyu-mll/PRPN-Analysis","path":"blocks.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/blocks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd0b027b739c21bd","mcp_get_code":{"code_sha256":"fd0b027b739c21bd"}},{"arxiv_id":"1710.09829","paper":"/paper/dynamic-routing-between-capsules","title":"Dynamic Routing Between Capsules","date":"2017-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gram-ai/capsule-networks","path":"capsule_network.py","file_url":"https://github.com/gram-ai/capsule-networks/blob/HEAD/capsule_network.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d55eaf6b69be6376","mcp_get_code":{"code_sha256":"d55eaf6b69be6376"}},{"arxiv_id":"1710.09829","paper":"/paper/dynamic-routing-between-capsules","title":"Dynamic Routing Between Capsules","date":"2017-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Utkarsh87/Capsule-Networks","path":"src/digitcaps.py","file_url":"https://github.com/Utkarsh87/Capsule-Networks/blob/HEAD/src/digitcaps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2719723f2846d85e","mcp_get_code":{"code_sha256":"2719723f2846d85e"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"krocki/np-transformer","path":"transformer.py","file_url":"https://github.com/krocki/np-transformer/blob/HEAD/transformer.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"54fe686797cba4a9","mcp_get_code":{"code_sha256":"54fe686797cba4a9"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baoqianwang/iros22_darl1n","path":"maddpg_o/maddpg_local/trainer/maddpg.py","file_url":"https://github.com/baoqianwang/iros22_darl1n/blob/HEAD/maddpg_o/maddpg_local/trainer/maddpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"61d3f2ae09e0df23","mcp_get_code":{"code_sha256":"61d3f2ae09e0df23"}},{"arxiv_id":"1705.08492","paper":"/paper/uplift-modeling-with-multiple-treatments-and","title":"Uplift Modeling with Multiple Treatments and General Response Types","date":"2017-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ibotta/mr_uplift","path":"mr_uplift/erupt.py","file_url":"https://github.com/Ibotta/mr_uplift/blob/HEAD/mr_uplift/erupt.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"74138c11e6beb035","mcp_get_code":{"code_sha256":"74138c11e6beb035"}},{"arxiv_id":"1703.07771","paper":"/paper/multitask-learning-and-benchmarking-with","title":"Multitask learning and benchmarking with clinical time series data","date":"2017-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Dongximing/Mimic3","path":"mimic3models/keras_utils.py","file_url":"https://github.com/Dongximing/Mimic3/blob/HEAD/mimic3models/keras_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"89812b9ec498264d","mcp_get_code":{"code_sha256":"89812b9ec498264d"}},{"arxiv_id":"1701.07204","paper":"/paper/fast-exact-k-means-k-medians-and-bregman","title":"Fast Exact k-Means, k-Medians and Bregman Divergence Clustering in 1D","date":"2017-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-stable-diffusion","path":"python_coreml_stable_diffusion/attention.py","file_url":"https://github.com/apple/ml-stable-diffusion/blob/HEAD/python_coreml_stable_diffusion/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e47c68e7594be7c2","mcp_get_code":{"code_sha256":"e47c68e7594be7c2"}},{"arxiv_id":"1701.06547","paper":"/paper/adversarial-learning-for-neural-dialogue","title":"Adversarial Learning for Neural Dialogue Generation","date":"2017-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow","path":"al_neural_dialogue_train.py","file_url":"https://github.com/liuyuemaicha/Adversarial-Learning-for-Neural-Dialogue-Generation-in-Tensorflow/blob/HEAD/al_neural_dialogue_train.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2d8244fa9563626","mcp_get_code":{"code_sha256":"b2d8244fa9563626"}},{"arxiv_id":"1611.03852","paper":"/paper/a-connection-between-generative-adversarial","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","date":"2016-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Haichao-Zhang/IRL","path":"tabular_maxent_irl/q_iteration.py","file_url":"https://github.com/Haichao-Zhang/IRL/blob/HEAD/tabular_maxent_irl/q_iteration.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d46376eaa3b436fa","mcp_get_code":{"code_sha256":"d46376eaa3b436fa"}},{"arxiv_id":"1610.02136","paper":"/paper/a-baseline-for-detecting-misclassified-and","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","date":"2016-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kobybibas/pnml_ood_detection","path":"src/score_utils.py","file_url":"https://github.com/kobybibas/pnml_ood_detection/blob/HEAD/src/score_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ddc824e88e78020","mcp_get_code":{"code_sha256":"7ddc824e88e78020"}},{"arxiv_id":"1610.02136","paper":"/paper/a-baseline-for-detecting-misclassified-and","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","date":"2016-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/error-detection","path":"ASR/CTC/CTC_eval.py","file_url":"https://github.com/hendrycks/error-detection/blob/HEAD/ASR/CTC/CTC_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3dea44d35e56a40","mcp_get_code":{"code_sha256":"f3dea44d35e56a40"}},{"arxiv_id":"1609.05140","paper":"/paper/the-option-critic-architecture","title":"The Option-Critic Architecture","date":"2016-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"elitalobo/Hierarchical-RL-Algorithms","path":"option-critic/hierarchical_dqn.py","file_url":"https://github.com/elitalobo/Hierarchical-RL-Algorithms/blob/HEAD/option-critic/hierarchical_dqn.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":"e4490f9789c3a31e","mcp_get_code":{"code_sha256":"e4490f9789c3a31e"}},{"arxiv_id":"1608.00859","paper":"/paper/temporal-segment-networks-towards-good","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","date":"2016-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrazySherman/goodlife","path":"pyActionRecog/utils/metrics.py","file_url":"https://github.com/CrazySherman/goodlife/blob/HEAD/pyActionRecog/utils/metrics.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":"a59fc47a6706506b","mcp_get_code":{"code_sha256":"a59fc47a6706506b"}},{"arxiv_id":"1605.02019","paper":"/paper/mixing-dirichlet-topic-models-and-word","title":"Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec","date":"2016-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cemoody/lda2vec","path":"lda2vec/fake_data.py","file_url":"https://github.com/cemoody/lda2vec/blob/HEAD/lda2vec/fake_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"858518cc85c49662","mcp_get_code":{"code_sha256":"858518cc85c49662"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qihongl/demo-advantage-actor-critic","path":"src/models/_A2C_discrete.py","file_url":"https://github.com/qihongl/demo-advantage-actor-critic/blob/HEAD/src/models/_A2C_discrete.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9559ea8ea49d3010","mcp_get_code":{"code_sha256":"9559ea8ea49d3010"}},{"arxiv_id":"1511.02222","paper":"/paper/deep-kernel-learning","title":"Deep Kernel Learning","date":"2015-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziatdinovmax/gpax","path":"gpax/hypo.py","file_url":"https://github.com/ziatdinovmax/gpax/blob/HEAD/gpax/hypo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bd006eaea192a794","mcp_get_code":{"code_sha256":"bd006eaea192a794"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wassname/rl-portfolio-management","path":"rl_portfolio_management/util.py","file_url":"https://github.com/wassname/rl-portfolio-management/blob/HEAD/rl_portfolio_management/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84d603f2102cf1ed","mcp_get_code":{"code_sha256":"84d603f2102cf1ed"}},{"arxiv_id":"1506.02640","paper":"/paper/you-only-look-once-unified-real-time-object","title":"You Only Look Once: Unified, Real-Time Object Detection","date":"2015-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Banus/caffe-demo","path":"yolo_detection.py","file_url":"https://github.com/Banus/caffe-demo/blob/HEAD/yolo_detection.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"475ce08eea0c1d56","mcp_get_code":{"code_sha256":"475ce08eea0c1d56"}},{"arxiv_id":"1506.02640","paper":"/paper/you-only-look-once-unified-real-time-object","title":"You Only Look Once: Unified, Real-Time Object Detection","date":"2015-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leon-liangwu/MaskYolo_Caffe","path":"lib/utils.py","file_url":"https://github.com/leon-liangwu/MaskYolo_Caffe/blob/HEAD/lib/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8825c7c596e27b6f","mcp_get_code":{"code_sha256":"8825c7c596e27b6f"}},{"arxiv_id":"1503.02531","paper":"/paper/distilling-the-knowledge-in-a-neural-network","title":"Distilling the Knowledge in a Neural Network","date":"2015-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knotgrass/Knowledge-Distillation","path":"distiller/loss.py","file_url":"https://github.com/knotgrass/Knowledge-Distillation/blob/HEAD/distiller/loss.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb5cbea0e8219ff5","mcp_get_code":{"code_sha256":"cb5cbea0e8219ff5"}},{"arxiv_id":"1503.00269","paper":"/paper/contrastive-pessimistic-likelihood-estimation","title":"Contrastive Pessimistic Likelihood Estimation for Semi-Supervised Classification","date":"2015-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BorisovDm/CPLE_SSL","path":"utils.py","file_url":"https://github.com/BorisovDm/CPLE_SSL/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"db83f3a3d4f7c604","mcp_get_code":{"code_sha256":"db83f3a3d4f7c604"}},{"arxiv_id":"1411.2738","paper":"/paper/word2vec-parameter-learning-explained","title":"word2vec Parameter Learning Explained","date":"2014-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayank2498/Skip-Gram-model-using-numpy","path":"word2vec.py","file_url":"https://github.com/mayank2498/Skip-Gram-model-using-numpy/blob/HEAD/word2vec.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c0cf1196424d4f71","mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"arxiv_id":"1301.3781","paper":"/paper/efficient-estimation-of-word-representations","title":"Efficient Estimation of Word Representations in Vector Space","date":"2013-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"cb5cbea0e8219ff5","mcp_get_code":{"code_sha256":"cb5cbea0e8219ff5"}},{"arxiv_id":"1301.3781","paper":"/paper/efficient-estimation-of-word-representations","title":"Efficient Estimation of Word Representations in Vector Space","date":"2013-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeremycz/word-vectors","path":"a2/word2vec.py","file_url":"https://github.com/jeremycz/word-vectors/blob/HEAD/a2/word2vec.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9374cbb282b14e3e","mcp_get_code":{"code_sha256":"9374cbb282b14e3e"}},{"arxiv_id":"aaai_29511","paper":null,"title":"arXiv:aaai_29511","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lilujunai/Auto-Prox-AAAI24","path":"pycls/models/auto/module/multihead_super.py","file_url":"https://github.com/lilujunai/Auto-Prox-AAAI24/blob/HEAD/pycls/models/auto/module/multihead_super.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":"fb5908c47c2af90c","mcp_get_code":{"code_sha256":"fb5908c47c2af90c"}},{"arxiv_id":"aaai_28387","paper":null,"title":"arXiv:aaai_28387","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Vill-Lab/2024-AAAI-HPT","path":"clip/attention.py","file_url":"https://github.com/Vill-Lab/2024-AAAI-HPT/blob/HEAD/clip/attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5d0d43936dc7a5c","mcp_get_code":{"code_sha256":"b5d0d43936dc7a5c"}},{"arxiv_id":"2023.findings-acl.76","paper":null,"title":"arXiv:2023.findings-acl.76","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HKUST-KnowComp/FolkScope","path":"src/classifier/run_classification.py","file_url":"https://github.com/HKUST-KnowComp/FolkScope/blob/HEAD/src/classifier/run_classification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a0dec5c00f5c42d0","mcp_get_code":{"code_sha256":"a0dec5c00f5c42d0"}},{"arxiv_id":"2023.emnlp-main.534","paper":null,"title":"arXiv:2023.emnlp-main.534","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PreferredAI/superposed-topics","path":"gpt2/model.py","file_url":"https://github.com/PreferredAI/superposed-topics/blob/HEAD/gpt2/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"43894c3f1d3469e3","mcp_get_code":{"code_sha256":"43894c3f1d3469e3"}},{"arxiv_id":"136730727","paper":null,"title":"arXiv:136730727","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"louisYen/S3R","path":"anomaly/datasets/video_dataset.py","file_url":"https://github.com/louisYen/S3R/blob/HEAD/anomaly/datasets/video_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f745b756264a9ef","mcp_get_code":{"code_sha256":"1f745b756264a9ef"}}]}