{"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/rng","entry":"rng","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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"2403.12309","paper":"/paper/reinforcement-learning-from-delayed","title":"Reinforcement Learning from Delayed Observations via World Models","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"indylab/delayeddreamer","path":"dreamerv3/ninjax.py","file_url":"https://github.com/indylab/delayeddreamer/blob/HEAD/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}},{"arxiv_id":"2403.04253","paper":"/paper/mastering-memory-tasks-with-world-models","title":"Mastering Memory Tasks with World Models","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chandar-lab/Recall2Imagine","path":"recall2imagine/ninjax.py","file_url":"https://github.com/chandar-lab/Recall2Imagine/blob/HEAD/recall2imagine/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}},{"arxiv_id":"2310.00344","paper":"/paper/harmony-world-models-boosting-sample","title":"HarmonyDream: Task Harmonization Inside World Models","date":"2023-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thuml/HarmonyDream","path":"dreamerv3-jax/dreamerv3/ninjax.py","file_url":"https://github.com/thuml/HarmonyDream/blob/HEAD/dreamerv3-jax/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}},{"arxiv_id":"2307.07176","paper":"/paper/safe-dreamerv3-safe-reinforcement-learning","title":"SafeDreamer: Safe Reinforcement Learning with World Models","date":"2023-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-Alignment/SafeDreamer","path":"SafeDreamer/ninjax.py","file_url":"https://github.com/PKU-Alignment/SafeDreamer/blob/HEAD/SafeDreamer/ninjax.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":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}},{"arxiv_id":"2306.11488","paper":"/paper/informed-pomdp-leveraging-additional","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","date":"2023-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glambrechts/informed-dreamer","path":"dreamerv3/ninjax.py","file_url":"https://github.com/glambrechts/informed-dreamer/blob/HEAD/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}},{"arxiv_id":"2305.14343","paper":"/paper/video-prediction-models-as-rewards-for","title":"Video Prediction Models as Rewards for Reinforcement Learning","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alescontrela/viper_rl","path":"viper_rl/dreamerv3/ninjax.py","file_url":"https://github.com/Alescontrela/viper_rl/blob/HEAD/viper_rl/dreamerv3/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a03f3f2133e3fcee","mcp_get_code":{"code_sha256":"a03f3f2133e3fcee"}},{"arxiv_id":"2303.03226","paper":"/paper/safe-reinforcement-learning-via-probabilistic","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","date":"2023-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacktock/ambs","path":"dreamerV3-base/ninjax.py","file_url":"https://github.com/sacktock/ambs/blob/HEAD/dreamerV3-base/ninjax.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45b97b51433849a7","mcp_get_code":{"code_sha256":"45b97b51433849a7"}}]}