{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A6CH3SNKIW566YYRFOQYGAP44F","short_pith_number":"pith:A6CH3SNK","schema_version":"1.0","canonical_sha256":"07847dc9aa45bbef63112ba18301fce150f64d1b810d6c347680115b11730319","source":{"kind":"arxiv","id":"2111.08819","version":1},"attestation_state":"computed","paper":{"title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Ye, Jeff Braga, Rousslan Fernand Julien Dossa, Shengyi Huang","submitted_at":"2021-11-16T22:44:56Z","abstract_excerpt":"CleanRL is an open-source library that provides high-quality single-file implementations of Deep Reinforcement Learning algorithms. It provides a simpler yet scalable developing experience by having a straightforward codebase and integrating production tools to help interact and scale experiments. In CleanRL, we put all details of an algorithm into a single file, making these performance-relevant details easier to recognize. Additionally, an experiment tracking feature is available to help log metrics, hyperparameters, videos of an agent's gameplay, dependencies, and more to the cloud. Despite"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.08819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-16T22:44:56Z","cross_cats_sorted":[],"title_canon_sha256":"c20c90edf43dfc81cbc0447ed29a5ab59c04badf941b66e04db267f56b96b538","abstract_canon_sha256":"06728a2b0532bcaf8f908a610bc00dc89e0f9bdaaa975a9c39fcf16908824f87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:41.257459Z","signature_b64":"hjgB7w7EW6Y/eiOAaDYR1vOgqPJ1o3qdX+JHZb8wyvdNU6+Obm0hQPHXcVXiItv41pkbsKpyvvFL5cZfF3bhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07847dc9aa45bbef63112ba18301fce150f64d1b810d6c347680115b11730319","last_reissued_at":"2026-07-05T03:32:41.256941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:41.256941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Ye, Jeff Braga, Rousslan Fernand Julien Dossa, Shengyi Huang","submitted_at":"2021-11-16T22:44:56Z","abstract_excerpt":"CleanRL is an open-source library that provides high-quality single-file implementations of Deep Reinforcement Learning algorithms. It provides a simpler yet scalable developing experience by having a straightforward codebase and integrating production tools to help interact and scale experiments. In CleanRL, we put all details of an algorithm into a single file, making these performance-relevant details easier to recognize. Additionally, an experiment tracking feature is available to help log metrics, hyperparameters, videos of an agent's gameplay, dependencies, and more to the cloud. Despite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08819","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.08819/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.08819","created_at":"2026-07-05T03:32:41.257021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08819v1","created_at":"2026-07-05T03:32:41.257021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08819","created_at":"2026-07-05T03:32:41.257021+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6CH3SNKIW56","created_at":"2026-07-05T03:32:41.257021+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6CH3SNKIW566YYR","created_at":"2026-07-05T03:32:41.257021+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6CH3SNK","created_at":"2026-07-05T03:32:41.257021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F","json":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F.json","graph_json":"https://pith.science/api/pith-number/A6CH3SNKIW566YYRFOQYGAP44F/graph.json","events_json":"https://pith.science/api/pith-number/A6CH3SNKIW566YYRFOQYGAP44F/events.json","paper":"https://pith.science/paper/A6CH3SNK"},"agent_actions":{"view_html":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F","download_json":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F.json","view_paper":"https://pith.science/paper/A6CH3SNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08819&json=true","fetch_graph":"https://pith.science/api/pith-number/A6CH3SNKIW566YYRFOQYGAP44F/graph.json","fetch_events":"https://pith.science/api/pith-number/A6CH3SNKIW566YYRFOQYGAP44F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F/action/storage_attestation","attest_author":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F/action/author_attestation","sign_citation":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F/action/citation_signature","submit_replication":"https://pith.science/pith/A6CH3SNKIW566YYRFOQYGAP44F/action/replication_record"}},"created_at":"2026-07-05T03:32:41.257021+00:00","updated_at":"2026-07-05T03:32:41.257021+00:00"}