{"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/run-experiment","entry":"run_experiment","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":8,"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":22,"n_samples_ran":8,"n_samples_fingerprinted":1,"n_places":22,"n_places_pointer_only":7,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":3,"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":"2606.31082","paper":"/paper/arxiv-2606-31082","title":"Fleet: Few Shots Lead Effective AI-generated Image Detection","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ICTMCG/Fleet","path":"src/fleet/train/fewshot_experiment.py","file_url":"https://github.com/ICTMCG/Fleet/blob/HEAD/src/fleet/train/fewshot_experiment.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":"5afbfae2678a5e07","mcp_get_code":{"code_sha256":"5afbfae2678a5e07"}},{"arxiv_id":"2605.06615","paper":"/paper/arxiv-2605-06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on ℓ 1 -norm Lower Bounds","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Dingzhen230/SignSGD_Outperforms_SGD","path":"toy_models/sto.py","file_url":"https://github.com/Dingzhen230/SignSGD_Outperforms_SGD/blob/HEAD/toy_models/sto.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d83a5bca8e23539e","mcp_get_code":{"code_sha256":"d83a5bca8e23539e"}},{"arxiv_id":"2603.08286","paper":"/paper/arxiv-2603-08286","title":"LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"LavanyaPobbathi/LAMUS","path":"code/experiment/A_run_4_models_1st.py","file_url":"https://github.com/LavanyaPobbathi/LAMUS/blob/HEAD/code/experiment/A_run_4_models_1st.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f66e2e1e82555cf","mcp_get_code":{"code_sha256":"6f66e2e1e82555cf"}},{"arxiv_id":"2506.06985","paper":"/paper/certified-unlearning-for-neural-networks","title":"Certified Unlearning for Neural Networks","date":"2025-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stair-lab/certified-unlearning-neural-networks-icml-2025","path":"run_exp.py","file_url":"https://github.com/stair-lab/certified-unlearning-neural-networks-icml-2025/blob/HEAD/run_exp.py","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cba600c66766b28","mcp_get_code":{"code_sha256":"0cba600c66766b28"}},{"arxiv_id":"2501.06911","paper":"/paper/risk-averse-finetuning-of-large-language","title":"Risk-Averse Finetuning of Large Language Models","date":"2025-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sapanachaudhary/ra-rlhf","path":"benchmark/benchmark.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/benchmark/benchmark.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":"d6e962139d6c0dec","mcp_get_code":{"code_sha256":"d6e962139d6c0dec"}},{"arxiv_id":"2411.12068","paper":"/paper/the-statistical-accuracy-of-neural-posterior","title":"The Statistical Accuracy of Neural Posterior and Likelihood Estimation","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RyanJafefKelly/npe_convergence","path":"npe_convergence/scripts/run_experiment.py","file_url":"https://github.com/RyanJafefKelly/npe_convergence/blob/HEAD/npe_convergence/scripts/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28e1589ab34256f6","mcp_get_code":{"code_sha256":"28e1589ab34256f6"}},{"arxiv_id":"2408.06292","paper":"/paper/the-ai-scientist-towards-fully-automated-open","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","date":"2024-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sakanaai/ai-scientist","path":"ai_scientist/perform_experiments.py","file_url":"https://github.com/sakanaai/ai-scientist/blob/HEAD/ai_scientist/perform_experiments.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8d71b435fe16e51f","mcp_get_code":{"code_sha256":"8d71b435fe16e51f"}},{"arxiv_id":"2408.04154","paper":"/paper/the-data-addition-dilemma","title":"The Data Addition Dilemma","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"the-chen-lab/data-addition-dilemma","path":"Yelp-MIMIC/run_mixture.py","file_url":"https://github.com/the-chen-lab/data-addition-dilemma/blob/HEAD/Yelp-MIMIC/run_mixture.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb6dd2f3e62967b9","mcp_get_code":{"code_sha256":"bb6dd2f3e62967b9"}},{"arxiv_id":"2407.19938","paper":"/paper/robust-conformal-volume-estimation-in-3d","title":"Robust Conformal Volume Estimation in 3D Medical Images","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"benolmbrt/wcp_miccai","path":"weighted_cp.py","file_url":"https://github.com/benolmbrt/wcp_miccai/blob/HEAD/weighted_cp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7ebd500b8420939","mcp_get_code":{"code_sha256":"a7ebd500b8420939"}},{"arxiv_id":"2406.05405","paper":"/paper/robust-conformal-prediction-using-privileged","title":"Robust Conformal Prediction Using Privileged Information","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Shai128/pcp","path":"src/run_experiment.py","file_url":"https://github.com/Shai128/pcp/blob/HEAD/src/run_experiment.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":"f7cbc2cf0fc5f7da","mcp_get_code":{"code_sha256":"f7cbc2cf0fc5f7da"}},{"arxiv_id":"2406.02464","paper":"/paper/meta-learners-for-partially-identified","title":"Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlaaLab/conformal-metalearners","path":"run_conformal_metalearners.py","file_url":"https://github.com/AlaaLab/conformal-metalearners/blob/HEAD/run_conformal_metalearners.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"225998302c2fd076","mcp_get_code":{"code_sha256":"225998302c2fd076"}},{"arxiv_id":"2310.02207","paper":"/paper/language-models-represent-space-and-time","title":"Language Models Represent Space and Time","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wesg52/world-models","path":"generalization_experiment.py","file_url":"https://github.com/wesg52/world-models/blob/HEAD/generalization_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eeab6f68b890a0fb","mcp_get_code":{"code_sha256":"eeab6f68b890a0fb"}},{"arxiv_id":"2308.15478","paper":"/paper/an-adaptive-tangent-feature-perspective-of","title":"An Adaptive Tangent Feature Perspective of Neural Networks","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dlej/adaptive-feature-perspective","path":"batch_gpu.py","file_url":"https://github.com/dlej/adaptive-feature-perspective/blob/HEAD/batch_gpu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"48e54303d2ca26ec","mcp_get_code":{"code_sha256":"48e54303d2ca26ec"}},{"arxiv_id":"2302.10160","paper":"/paper/pseudo-labeling-for-kernel-ridge-regression","title":"Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift","date":"2023-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kw2934/krr","path":"KRR.py","file_url":"https://github.com/kw2934/krr/blob/HEAD/KRR.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e560621f86aa8a37","mcp_get_code":{"code_sha256":"e560621f86aa8a37"}},{"arxiv_id":"2207.04771","paper":"/paper/functional-generalized-empirical-likelihood","title":"Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions","date":"2022-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heinerkremer/functional-gel","path":"run_experiment.py","file_url":"https://github.com/heinerkremer/functional-gel/blob/HEAD/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8dfc976d4c69f79b","mcp_get_code":{"code_sha256":"8dfc976d4c69f79b"}},{"arxiv_id":"2112.11622","paper":"/paper/an-alternate-policy-gradient-estimator-for","title":"An Alternate Policy Gradient Estimator for Softmax Policies","date":"2021-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"svmgrg/alternate_pg","path":"neural/nn_experiment.py","file_url":"https://github.com/svmgrg/alternate_pg/blob/HEAD/neural/nn_experiment.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"430d245b6b2253f7","mcp_get_code":{"code_sha256":"430d245b6b2253f7"}},{"arxiv_id":"2112.10599","paper":"/paper/differentially-private-regret-minimization-in","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","date":"2021-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingyuzhou989/privatetabularrl","path":"src/experiment.py","file_url":"https://github.com/xingyuzhou989/privatetabularrl/blob/HEAD/src/experiment.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b869db27b44dccef","mcp_get_code":{"code_sha256":"b869db27b44dccef"}},{"arxiv_id":"2106.02029","paper":"/paper/off-policy-evaluation-via-adaptive-weighting","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gsbDBI/contextual_bandits_evaluation","path":"adaptive/experiment.py","file_url":"https://github.com/gsbDBI/contextual_bandits_evaluation/blob/HEAD/adaptive/experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ecb20e1fe43bf2b","mcp_get_code":{"code_sha256":"9ecb20e1fe43bf2b"}},{"arxiv_id":"2101.08367","paper":"/paper/influence-estimation-for-generative-1","title":"Influence Estimation for Generative Adversarial Networks","date":"2021-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hitachi-rd-cv/influence-estimation-for-gans","path":"experiments/lininfl.py","file_url":"https://github.com/hitachi-rd-cv/influence-estimation-for-gans/blob/HEAD/experiments/lininfl.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15d25954ccb3bef3","mcp_get_code":{"code_sha256":"15d25954ccb3bef3"}},{"arxiv_id":"1909.00505","paper":"/paper/commonsense-knowledge-mining-from-pretrained","title":"Commonsense Knowledge Mining from Pretrained Models","date":"2019-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gychant/CSKMTermDefn","path":"Extracting-CK-from-Large-LM/wiktionary_experiment.py","file_url":"https://github.com/gychant/CSKMTermDefn/blob/HEAD/Extracting-CK-from-Large-LM/wiktionary_experiment.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":"156dd2cf88dd53dd","mcp_get_code":{"code_sha256":"156dd2cf88dd53dd"}},{"arxiv_id":"1804.09170","paper":"/paper/realistic-evaluation-of-deep-semi-supervised","title":"Realistic Evaluation of Deep Semi-Supervised Learning Algorithms","date":"2018-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"melkherj/puddle","path":"puddle/active_evaluate.py","file_url":"https://github.com/melkherj/puddle/blob/HEAD/puddle/active_evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f47977b925bb5e5","mcp_get_code":{"code_sha256":"4f47977b925bb5e5"}},{"arxiv_id":"1409.0575","paper":"/paper/imagenet-large-scale-visual-recognition","title":"ImageNet Large Scale Visual Recognition Challenge","date":"2014-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"y2l/meta-transfer-learning-tensorflow","path":"tensorflow/run_experiment.py","file_url":"https://github.com/y2l/meta-transfer-learning-tensorflow/blob/HEAD/tensorflow/run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbc206e8ce0aee30","mcp_get_code":{"code_sha256":"cbc206e8ce0aee30"}}]}