{"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/flat-concat","entry":"flat_concat","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":7,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2605.11975","paper":"/paper/arxiv-2605-11975","title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"milanganai/milanganai.github.io","path":"NeurIPS2023/code/utils/mpi_tf.py","file_url":"https://github.com/milanganai/milanganai.github.io/blob/HEAD/NeurIPS2023/code/utils/mpi_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"2401.14758","paper":"/paper/off-policy-primal-dual-safe-reinforcement","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","date":"2024-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlgTUDelft/WCSAC","path":"wc_sac/utils/mpi_tf.py","file_url":"https://github.com/AlgTUDelft/WCSAC/blob/HEAD/wc_sac/utils/mpi_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"2302.02299","paper":"/paper/sample-dropout-a-simple-yet-effective","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","date":"2023-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzichuan/sdpo","path":"baselines/ppo2/model.py","file_url":"https://github.com/linzichuan/sdpo/blob/HEAD/baselines/ppo2/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"2302.00808","paper":"/paper/average-constrained-policy-optimization","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/safety-starter-agents","path":"safe_rl/pg/trust_region.py","file_url":"https://github.com/openai/safety-starter-agents/blob/HEAD/safe_rl/pg/trust_region.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"2210.07573","paper":"/paper/model-based-safe-deep-reinforcement-learning","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akjayant/mbppol","path":"src/utils/mpi_tf.py","file_url":"https://github.com/akjayant/mbppol/blob/HEAD/src/utils/mpi_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"2006.07442","paper":"/paper/self-imitation-learning-via-generalized-lower","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","date":"2020-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/spinningup","path":"spinup/utils/mpi_tf.py","file_url":"https://github.com/openai/spinningup/blob/HEAD/spinup/utils/mpi_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}},{"arxiv_id":"aaai_35251","paper":null,"title":"arXiv:aaai_35251","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Teddy298/continualworld-ppo","path":"continualworld/utils_ppo/mpi_tf.py","file_url":"https://github.com/Teddy298/continualworld-ppo/blob/HEAD/continualworld/utils_ppo/mpi_tf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f29202d8108bccd3","mcp_get_code":{"code_sha256":"f29202d8108bccd3"}}]}