{"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/create-exp-name","entry":"create_exp_name","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":0,"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":5,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2607.09298","paper":"/paper/arxiv-2607-09298","title":"Risk-Aware General-Utility Markov Decision Processes","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"gh0stwin/risk-aware-gumdp","path":"src/risk_aware_gumdp/simulations/erm_backward_induction.py","file_url":"https://github.com/gh0stwin/risk-aware-gumdp/blob/HEAD/src/risk_aware_gumdp/simulations/erm_backward_induction.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"670512c1b3c28c19","mcp_get_code":{"code_sha256":"670512c1b3c28c19"}},{"arxiv_id":"2607.09298","paper":"/paper/arxiv-2607-09298","title":"Risk-Aware General-Utility Markov Decision Processes","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"gh0stwin/risk-aware-gumdp","path":"src/risk_aware_gumdp/simulations/erm_mcts.py","file_url":"https://github.com/gh0stwin/risk-aware-gumdp/blob/HEAD/src/risk_aware_gumdp/simulations/erm_mcts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c73ec4c89a91bdb9","mcp_get_code":{"code_sha256":"c73ec4c89a91bdb9"}},{"arxiv_id":"2411.11364","paper":"/paper/continual-task-learning-through-adaptive","title":"Continual Task Learning through Adaptive Policy Self-Composition","date":"2024-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charleshsc/CompoFormer","path":"logger.py","file_url":"https://github.com/charleshsc/CompoFormer/blob/HEAD/logger.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":"5e687d63bb9beb4a","mcp_get_code":{"code_sha256":"5e687d63bb9beb4a"}},{"arxiv_id":"2411.01146","paper":"/paper/task-aware-harmony-multi-task-decision","title":"Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","date":"2024-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charleshsc/HarmoDT","path":"logger.py","file_url":"https://github.com/charleshsc/HarmoDT/blob/HEAD/logger.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":"5e687d63bb9beb4a","mcp_get_code":{"code_sha256":"5e687d63bb9beb4a"}},{"arxiv_id":"2405.19690","paper":"/paper/diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TianyuCodings/Diffusion_Trusted_Q_Learning","path":"utils/logger.py","file_url":"https://github.com/TianyuCodings/Diffusion_Trusted_Q_Learning/blob/HEAD/utils/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e687d63bb9beb4a","mcp_get_code":{"code_sha256":"5e687d63bb9beb4a"}},{"arxiv_id":"2405.17098","paper":"/paper/q-value-regularized-transformer-for-offline","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charleshsc/qt","path":"logger.py","file_url":"https://github.com/charleshsc/qt/blob/HEAD/logger.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":"5e687d63bb9beb4a","mcp_get_code":{"code_sha256":"5e687d63bb9beb4a"}},{"arxiv_id":"2210.07484","paper":"/paper/mutual-information-regularized-offline-1","title":"Mutual Information Regularized Offline Reinforcement Learning","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/MISA","path":"viskit/logging.py","file_url":"https://github.com/sail-sg/MISA/blob/HEAD/viskit/logging.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"db7a0efd9adcf84c","mcp_get_code":{"code_sha256":"db7a0efd9adcf84c"}},{"arxiv_id":"2006.04779","paper":"/paper/conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"young-geng/cql","path":"viskit/logging.py","file_url":"https://github.com/young-geng/cql/blob/HEAD/viskit/logging.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3743c5d43e639ab9","mcp_get_code":{"code_sha256":"3743c5d43e639ab9"}}]}