{"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/maskedcausalattention","entry":"MaskedCausalAttention","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":5,"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":6,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":0},"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":"2509.25727","paper":"/paper/arxiv-2509-25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"HuikangSu/B2R","path":"model/B2R.py","file_url":"https://github.com/HuikangSu/B2R/blob/HEAD/model/B2R.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"67e44afff973c336","mcp_get_code":{"code_sha256":"67e44afff973c336"}},{"arxiv_id":"2502.02834","paper":"/paper/task-aware-virtual-training-enhancing","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunwoolee0504/wall","path":"src/modules/step/models.py","file_url":"https://github.com/sunwoolee0504/wall/blob/HEAD/src/modules/step/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7a7dab71d814fea4","mcp_get_code":{"code_sha256":"7a7dab71d814fea4"}},{"arxiv_id":"2405.08740","paper":"/paper/reinformer-max-return-sequence-modeling-for","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","date":"2024-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dragon-zhuang/reinformer","path":"model/reinformer.py","file_url":"https://github.com/dragon-zhuang/reinformer/blob/HEAD/model/reinformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4387bc25a5116e60","mcp_get_code":{"code_sha256":"4387bc25a5116e60"}},{"arxiv_id":"2303.03391","paper":"/paper/decision-transformer-under-random-frame","title":"Decision Transformer under Random Frame Dropping","date":"2023-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hukz18/defog","path":"atari/model.py","file_url":"https://github.com/hukz18/defog/blob/HEAD/atari/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a702a180fca3dbc4","mcp_get_code":{"code_sha256":"a702a180fca3dbc4"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LAS1520/Gato-A-Generalist-Agent","path":"Gato_models/model.py","file_url":"https://github.com/LAS1520/Gato-A-Generalist-Agent/blob/HEAD/Gato_models/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"621a87d0ebc957c4","mcp_get_code":{"code_sha256":"621a87d0ebc957c4"}},{"arxiv_id":"2106.01345","paper":"/paper/decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendilab/DI-engine","path":"ding/model/template/decision_transformer.py","file_url":"https://github.com/opendilab/DI-engine/blob/HEAD/ding/model/template/decision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"23842a66d5113ef0","mcp_get_code":{"code_sha256":"23842a66d5113ef0"}}]}