{"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/get-scores","entry":"get_scores","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":22,"n_papers_ran":9,"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":23,"n_samples_ran":9,"n_samples_fingerprinted":2,"n_places":23,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":4,"ran":4,"unverified":14},"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":"2604.26673","paper":"/paper/arxiv-2604-26673","title":"Laplace Approximation for Bayesian Tensor Network Kernel Machines","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"AlbMLpy/laplace-tnkm","path":"source/models/LaplaceCPR.py","file_url":"https://github.com/AlbMLpy/laplace-tnkm/blob/HEAD/source/models/LaplaceCPR.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbbbd8c608bbaa0e","mcp_get_code":{"code_sha256":"bbbbd8c608bbaa0e"}},{"arxiv_id":"2603.15892","paper":"/paper/arxiv-2603-15892","title":"Temporal Conflicts in LLMs: Reproducibility Insights from Unifying DYNAMICQA and MULAN","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"terrierteam/temporal_conflicts","path":"fact_mutability/bkp_inference.py","file_url":"https://github.com/terrierteam/temporal_conflicts/blob/HEAD/fact_mutability/bkp_inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a6131b16a998443","mcp_get_code":{"code_sha256":"2a6131b16a998443"}},{"arxiv_id":"2512.11391","paper":"/paper/arxiv-2512-11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"ivanniu/NSPO","path":"script/safe_reward.py","file_url":"https://github.com/ivanniu/NSPO/blob/HEAD/script/safe_reward.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d129731f3e8f3a7","mcp_get_code":{"code_sha256":"6d129731f3e8f3a7"}},{"arxiv_id":"2501.17144","paper":"/paper/factcg-enhancing-fact-checkers-with-graph","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","date":"2025-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derenlei/FactCG","path":"benchmark.py","file_url":"https://github.com/derenlei/FactCG/blob/HEAD/benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1798c50ae7165bb","mcp_get_code":{"code_sha256":"c1798c50ae7165bb"}},{"arxiv_id":"2501.17144","paper":"/paper/factcg-enhancing-fact-checkers-with-graph","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","date":"2025-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derenlei/FactCG","path":"wice_connected_reasoning.py","file_url":"https://github.com/derenlei/FactCG/blob/HEAD/wice_connected_reasoning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bec4d78405f6ec00","mcp_get_code":{"code_sha256":"bec4d78405f6ec00"}},{"arxiv_id":"2412.01023","paper":"/paper/learning-structured-representations-with","title":"Learning Structured Representations with Hyperbolic Embeddings","date":"2024-12-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuctml/HypStructure","path":"utils.py","file_url":"https://github.com/uiuctml/HypStructure/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":"cf06b847b490e55a","mcp_get_code":{"code_sha256":"cf06b847b490e55a"}},{"arxiv_id":"2410.15522","paper":"/paper/m-rewardbench-evaluating-reward-models-in","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","date":"2024-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"for-ai/m-rewardbench","path":"analysis/plot_utils.py","file_url":"https://github.com/for-ai/m-rewardbench/blob/HEAD/analysis/plot_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91d627e4e585fc2c","mcp_get_code":{"code_sha256":"91d627e4e585fc2c"}},{"arxiv_id":"2408.10798","paper":"/paper/universal-novelty-detection-through-adaptive-1","title":"Universal Novelty Detection Through Adaptive Contrastive Learning","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mojtaba-nafez/unode","path":"evals/evaluation.py","file_url":"https://github.com/mojtaba-nafez/unode/blob/HEAD/evals/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03e22dcc6d7e01c6","mcp_get_code":{"code_sha256":"03e22dcc6d7e01c6"}},{"arxiv_id":"2405.18942","paper":"/paper/verifiably-robust-conformal-prediction","title":"Verifiably Robust Conformal Prediction","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ddv-lab/Verifiably_Robust_CP","path":"VRCP_Classification/VRCP/experiment.py","file_url":"https://github.com/ddv-lab/Verifiably_Robust_CP/blob/HEAD/VRCP_Classification/VRCP/experiment.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f780342ea9e8fa2e","mcp_get_code":{"code_sha256":"f780342ea9e8fa2e"}},{"arxiv_id":"2403.13031","paper":"/paper/rigorllm-resilient-guardrails-for-large","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eurekayuan/rigorllm","path":"moderation.py","file_url":"https://github.com/eurekayuan/rigorllm/blob/HEAD/moderation.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a42c00a4f305dd22","mcp_get_code":{"code_sha256":"a42c00a4f305dd22"}},{"arxiv_id":"2402.17497","paper":"/paper/rear-a-relevance-aware-retrieval-augmented","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUCAIBox/REAR","path":"rear/src/inf.py","file_url":"https://github.com/RUCAIBox/REAR/blob/HEAD/rear/src/inf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73a6d0a707d6cc37","mcp_get_code":{"code_sha256":"73a6d0a707d6cc37"}},{"arxiv_id":"2402.01404","paper":"/paper/on-measuring-context-utilization-in-document","title":"On Measuring Context Utilization in Document-Level MT Systems","date":"2024-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZurichNLP/ContraPro","path":"evaluate.py","file_url":"https://github.com/ZurichNLP/ContraPro/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b884fdc3e1f18c8","mcp_get_code":{"code_sha256":"8b884fdc3e1f18c8"}},{"arxiv_id":"2310.13682","paper":"/paper/optimizing-retrieval-augmented-reader-models","title":"Optimizing Retrieval-augmented Reader Models via Token Elimination","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mosheber/token_elimination","path":"src/model.py","file_url":"https://github.com/mosheber/token_elimination/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"f350bef02278b760","mcp_get_code":{"code_sha256":"f350bef02278b760"}},{"arxiv_id":"2310.10237","paper":"/paper/sgood-substructure-enhanced-graph-level-out","title":"SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tommydzh/sgood","path":"utils.py","file_url":"https://github.com/tommydzh/sgood/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"34664e472317e283","mcp_get_code":{"code_sha256":"34664e472317e283"}},{"arxiv_id":"2307.07534","paper":"/paper/masked-autoencoders-for-unsupervised-anomaly","title":"Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images","date":"2023-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lilygeorgescu/mae-medical-anomaly-detection","path":"evaluate_sup.py","file_url":"https://github.com/lilygeorgescu/mae-medical-anomaly-detection/blob/HEAD/evaluate_sup.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"139e763b4bd191ec","mcp_get_code":{"code_sha256":"139e763b4bd191ec"}},{"arxiv_id":"2302.03357","paper":"/paper/towards-better-time-series-contrastive","title":"Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach","date":"2023-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lanxiang1017/dynamicbadpairmining_iclr24","path":"models/dbpm_model.py","file_url":"https://github.com/lanxiang1017/dynamicbadpairmining_iclr24/blob/HEAD/models/dbpm_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c18b03944ec98848","mcp_get_code":{"code_sha256":"c18b03944ec98848"}},{"arxiv_id":"2209.09513","paper":"/paper/learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lupantech/ScienceQA","path":"tools/evaluate_acc.py","file_url":"https://github.com/lupantech/ScienceQA/blob/HEAD/tools/evaluate_acc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab3717114ec507c3","mcp_get_code":{"code_sha256":"ab3717114ec507c3"}},{"arxiv_id":"2207.12576","paper":"/paper/winogavil-gamified-association-benchmark-to","title":"WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models","date":"2022-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WinoGAViL/WinoGAViL-experiments","path":"run_zero_shot.py","file_url":"https://github.com/WinoGAViL/WinoGAViL-experiments/blob/HEAD/run_zero_shot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fb34eee819c2938e","mcp_get_code":{"code_sha256":"fb34eee819c2938e"}},{"arxiv_id":"2205.01066","paper":"/paper/quantifying-health-inequalities-induced-by","title":"Quantifying Health Inequalities Induced by Data and AI Models","date":"2022-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"knowlab/DAindex-Framework","path":"daindex/ml.py","file_url":"https://github.com/knowlab/DAindex-Framework/blob/HEAD/daindex/ml.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1fd27fd4b01f06c1","mcp_get_code":{"code_sha256":"1fd27fd4b01f06c1"}},{"arxiv_id":"2107.06917","paper":"/paper/a-field-guide-to-federated-optimization","title":"A Field Guide to Federated Optimization","date":"2021-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AParayil/AParayil-Distribued-Learning-via-Bayesian-Inferencing","path":"mnist_dist_sgld_svhn_plot_pred_scores.py","file_url":"https://github.com/AParayil/AParayil-Distribued-Learning-via-Bayesian-Inferencing/blob/HEAD/mnist_dist_sgld_svhn_plot_pred_scores.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a5fafd0528bc7da8","mcp_get_code":{"code_sha256":"a5fafd0528bc7da8"}},{"arxiv_id":"2009.13902","paper":"/paper/utterance-level-dialogue-understanding-an","title":"Utterance-level Dialogue Understanding: An Empirical Study","date":"2020-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/dialogue-understanding","path":"glove-end-to-end/train_shuffled_context.py","file_url":"https://github.com/declare-lab/dialogue-understanding/blob/HEAD/glove-end-to-end/train_shuffled_context.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53d8a07aaa1a0e6b","mcp_get_code":{"code_sha256":"53d8a07aaa1a0e6b"}},{"arxiv_id":"1811.10978","paper":"/paper/neural-non-stationary-spectral-kernel","title":"Neural Non-Stationary Spectral Kernel","date":"2018-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sremes/nssm-gp","path":"experiments/get_best_results.py","file_url":"https://github.com/sremes/nssm-gp/blob/HEAD/experiments/get_best_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b9c51089aa7b439","mcp_get_code":{"code_sha256":"9b9c51089aa7b439"}},{"arxiv_id":"2023.findings-acl.765","paper":null,"title":"arXiv:2023.findings-acl.765","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qtli/EIB","path":"code/Prompting-Filter/csqa_demo.py","file_url":"https://github.com/qtli/EIB/blob/HEAD/code/Prompting-Filter/csqa_demo.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":"335d193e8f3c624e","mcp_get_code":{"code_sha256":"335d193e8f3c624e"}}]}