{"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-monitor-files","entry":"get_monitor_files","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":7,"n_papers_ran":1,"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":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":5},"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":"2605.18591","paper":"/paper/arxiv-2605-18591","title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"agent-lab/ICML2026-RAT","path":"utils/monitor.py","file_url":"https://github.com/agent-lab/ICML2026-RAT/blob/HEAD/utils/monitor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6dabfbf42f09101c","mcp_get_code":{"code_sha256":"6dabfbf42f09101c"}},{"arxiv_id":"2111.03941","paper":"/paper/time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"artberryx/SAR","path":"sb/stable_baselines/bench/monitor.py","file_url":"https://github.com/artberryx/SAR/blob/HEAD/sb/stable_baselines/bench/monitor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d0ddaf36545261e","mcp_get_code":{"code_sha256":"0d0ddaf36545261e"}},{"arxiv_id":"2010.09170","paper":"/paper/belief-grounded-networks-for-acceleratedrobot","title":"Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability","date":"2020-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hai-h-nguyen/belief-grounded-network","path":"modifications/monitor.py","file_url":"https://github.com/hai-h-nguyen/belief-grounded-network/blob/HEAD/modifications/monitor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc7cbce302df4a1e","mcp_get_code":{"code_sha256":"dc7cbce302df4a1e"}},{"arxiv_id":"2006.04061","paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/bench/monitor.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/bench/monitor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"c6cb2f61f176b29b","mcp_get_code":{"code_sha256":"c6cb2f61f176b29b"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/bench/monitor.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/bench/monitor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"fa39f243af244088","mcp_get_code":{"code_sha256":"fa39f243af244088"}},{"arxiv_id":"1811.02073","paper":"/paper/quota-the-quantile-option-architecture-for","title":"QUOTA: The Quantile Option Architecture for Reinforcement Learning","date":"2018-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kchu/DeepRL_CK","path":"Distributional_RL/monitor.py","file_url":"https://github.com/Kchu/DeepRL_CK/blob/HEAD/Distributional_RL/monitor.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":"fa39f243af244088","mcp_get_code":{"code_sha256":"fa39f243af244088"}},{"arxiv_id":"1606.03476","paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Techget/gail-tf-sc2","path":"gailtf/baselines/bench/monitor.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/monitor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"af3d493bdc17ad51","mcp_get_code":{"code_sha256":"af3d493bdc17ad51"}}]}