{"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/avgl1norm","entry":"AvgL1Norm","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":6,"n_papers_ran":5,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":1},"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":"2603.12087","paper":"/paper/arxiv-2603-12087","title":"Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"dmksjfl/PAR","path":"algo/PAR.py","file_url":"https://github.com/dmksjfl/PAR/blob/HEAD/algo/PAR.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":"1e71094b23b75fbe","mcp_get_code":{"code_sha256":"1e71094b23b75fbe"}},{"arxiv_id":"2411.07007","paper":"/paper/non-adversarial-inverse-reinforcement","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arnavkj1995/sfm","path":"agents/sfm_sac.py","file_url":"https://github.com/arnavkj1995/sfm/blob/HEAD/agents/sfm_sac.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b821d8f39dbe176b","mcp_get_code":{"code_sha256":"b821d8f39dbe176b"}},{"arxiv_id":"2410.20750","paper":"/paper/odrl-a-benchmark-for-off-dynamics","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"offdynamicsrl/off-dynamics-rl","path":"algo/offline_online/bc_par.py","file_url":"https://github.com/offdynamicsrl/off-dynamics-rl/blob/HEAD/algo/offline_online/bc_par.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":"1e71094b23b75fbe","mcp_get_code":{"code_sha256":"1e71094b23b75fbe"}},{"arxiv_id":"2405.15369","paper":"/paper/cross-domain-policy-adaptation-by-capturing","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","date":"2024-05-24","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":"1e71094b23b75fbe","mcp_get_code":{"code_sha256":"1e71094b23b75fbe"}},{"arxiv_id":"2405.11718","paper":"/paper/feasibility-consistent-representation","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czp16/fcsrl","path":"fcsrl/network/representation.py","file_url":"https://github.com/czp16/fcsrl/blob/HEAD/fcsrl/network/representation.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":"1e71094b23b75fbe","mcp_get_code":{"code_sha256":"1e71094b23b75fbe"}},{"arxiv_id":"2306.02451","paper":"/paper/for-sale-state-action-representation-learning-1","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","date":"2023-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sfujim/TD7","path":"TD7.py","file_url":"https://github.com/sfujim/TD7/blob/HEAD/TD7.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":"1e71094b23b75fbe","mcp_get_code":{"code_sha256":"1e71094b23b75fbe"}}]}