{"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/observationmodel","entry":"ObservationModel","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":3,"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":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":3},"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":"2505.16732","paper":"/paper/sequential-monte-carlo-for-policy","title":"Sequential Monte Carlo for Policy Optimization in Continuous POMDPs","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sahel13/particle-pomdp","path":"ppomdp/smc/_smc.py","file_url":"https://github.com/Sahel13/particle-pomdp/blob/HEAD/ppomdp/smc/_smc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3c32c6451adb09a","mcp_get_code":{"code_sha256":"c3c32c6451adb09a"}},{"arxiv_id":"2411.00465","paper":"/paper/uncertainty-based-offline-variational","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MIRALab-USTC/RL-TRACER","path":"algo/model_free/tracer.py","file_url":"https://github.com/MIRALab-USTC/RL-TRACER/blob/HEAD/algo/model_free/tracer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"57ef107ba6ccf74c","mcp_get_code":{"code_sha256":"57ef107ba6ccf74c"}},{"arxiv_id":"2311.02227","paper":"/paper/state-wise-safe-reinforcement-learning-with","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","date":"2023-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simonzhan-code/step-wise_saferl_pixel","path":"modules/models.py","file_url":"https://github.com/simonzhan-code/step-wise_saferl_pixel/blob/HEAD/modules/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd4df7e37f410cf0","mcp_get_code":{"code_sha256":"cd4df7e37f410cf0"}},{"arxiv_id":"2303.07109","paper":"/paper/transformer-based-world-models-are-happy-with","title":"Transformer-based World Models Are Happy With 100k Interactions","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jrobine/twm","path":"twm/world_model.py","file_url":"https://github.com/jrobine/twm/blob/HEAD/twm/world_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"430454696696dc84","mcp_get_code":{"code_sha256":"430454696696dc84"}},{"arxiv_id":"2005.05960","paper":"/paper/planning-to-explore-via-self-supervised-world","title":"Planning to Explore via Self-Supervised World Models","date":"2020-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yusukeurakami/plan2explore-pytorch","path":"models.py","file_url":"https://github.com/yusukeurakami/plan2explore-pytorch/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"32fa4df355b9a218","mcp_get_code":{"code_sha256":"32fa4df355b9a218"}},{"arxiv_id":"1912.01603","paper":"/paper/dream-to-control-learning-behaviors-by-latent","title":"Dream to Control: Learning Behaviors by Latent Imagination","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yizhao111/dreamer-pytorch","path":"agent.py","file_url":"https://github.com/Yizhao111/dreamer-pytorch/blob/HEAD/agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"be5a219bf8efda66","mcp_get_code":{"code_sha256":"be5a219bf8efda66"}}]}