{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QYSKLZTX43ZBBRRR26DFGLFKWG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"31f6d5bdbc216acf9f4c1ab7bdce369476e0f3fbf35079d0bf9aa3eb4a8daf24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-05T17:54:48Z","title_canon_sha256":"56fea31d271806fa816a874361b3e508e0ba23bb9f3f10c323c9ecaa11c9b938"},"schema_version":"1.0","source":{"id":"1606.01540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.01540","created_at":"2026-07-04T21:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"1606.01540v1","created_at":"2026-07-04T21:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01540","created_at":"2026-07-04T21:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"QYSKLZTX43ZB","created_at":"2026-07-04T21:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"QYSKLZTX43ZBBRRR","created_at":"2026-07-04T21:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"QYSKLZTX","created_at":"2026-07-04T21:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:918d7bdd54d65099e54ac30f4e1f09f7aa903f9409620213566a992094fca0f2","target":"graph","created_at":"2026-07-04T21:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a common interface plus public result sharing will be sufficient to drive meaningful progress and fair comparisons, without addressing whether the chosen environments adequately represent real-world complexity or diversity of tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OpenAI Gym introduces a common interface for reinforcement learning environments and a results-sharing website to enable consistent algorithm comparisons."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results."}],"snapshot_sha256":"b4e9a32b03e160a11aca312a59d6b682c72d3c4dbeae247e8c5f59635734a29b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1606.01540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.","authors_text":"Greg Brockman, Jie Tang, John Schulman, Jonas Schneider, Ludwig Pettersson, Vicki Cheung, Wojciech Zaremba","cross_cats":["cs.AI"],"headline":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym"},"references":{"count":15,"internal_anchors":1,"resolved_work":15,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Dynamic programming and optimal control","work_id":"b2ea3f9f-2ebe-41e2-8330-a140e7bf8c6b","year":1995},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"V . Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, S. Petersen, Sadik Beattie, C., Antonoglou A., H. I., King, D. Kum","work_id":"b1509e5c-b3da-4ffa-9f09-45c396463a06","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"J. Schulman, S. Levine, P. Abbeel, M. I. Jordan, and P. Moritz. Trust region policy optimization. In ICML, pages 1889–1897, 2015","work_id":"041d632c-7466-47c8-ad82-9b9a540abe13","year":2015},{"cited_arxiv_id":"1602.01783","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Asynchronous Methods for Deep Reinforcement Learning","work_id":"b54058f9-0b3b-46ae-a9a0-f22748625e2a","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"M. G. Bellemare, Y . Naddaf, J. Veness, and M. Bowling. The Arcade Learning Environment: An evaluation platform for general agents. J. Artif. Intell. Res., 47:253–279, 2013","work_id":"e9360171-a564-4345-b474-6d1665449d8d","year":2013}],"snapshot_sha256":"7cb6aa4d9ea2bb97016e0b2b108bc06c172f7da556469e1c6ace24c4574aa3d2"},"source":{"id":"1606.01540","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-11T19:44:10.330352Z","id":"0d263c97-fdee-4aa7-b588-f82c7144cd12","model_set":{"reader":"grok-4.3"},"one_line_summary":"OpenAI Gym introduces a common interface for reinforcement learning environments and a results-sharing website to enable consistent algorithm comparisons.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A toolkit supplies benchmark problems for reinforcement learning through a shared interface along with a website for comparing algorithm results.","strongest_claim":"OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms.","weakest_assumption":"That a common interface plus public result sharing will be sufficient to drive meaningful progress and fair comparisons, without addressing whether the chosen environments adequately represent real-world complexity or diversity of tasks."}},"verdict_id":"0d263c97-fdee-4aa7-b588-f82c7144cd12"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6707e4cecd3908f0500a06267e16e1c5787f702b2252896168f167da98408920","target":"record","created_at":"2026-07-04T21:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"31f6d5bdbc216acf9f4c1ab7bdce369476e0f3fbf35079d0bf9aa3eb4a8daf24","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-05T17:54:48Z","title_canon_sha256":"56fea31d271806fa816a874361b3e508e0ba23bb9f3f10c323c9ecaa11c9b938"},"schema_version":"1.0","source":{"id":"1606.01540","kind":"arxiv","version":1}},"canonical_sha256":"8624a5e677e6f210c631d786532caab184fd952f3f8ea1deaf845a89d7ed9ff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8624a5e677e6f210c631d786532caab184fd952f3f8ea1deaf845a89d7ed9ff7","first_computed_at":"2026-07-04T21:03:34.073509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T21:03:34.073509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b2sMPH4udiquD6uKXIIV0Oq+ABNXHBcDjt50IJfN7V/wXiofe+OLWBNX9YW2Rgc3BLI4ZxantgYgWbQl60t2CQ==","signature_status":"signed_v1","signed_at":"2026-07-04T21:03:34.074023Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.01540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6707e4cecd3908f0500a06267e16e1c5787f702b2252896168f167da98408920","sha256:918d7bdd54d65099e54ac30f4e1f09f7aa903f9409620213566a992094fca0f2"],"state_sha256":"9ce7f84586c8c304f37ad6a948b122051b6baf38e5713435b09be5444ecf3456"}