{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BKBTX3GWJZRILLGHRHLFODW2MM","short_pith_number":"pith:BKBTX3GW","canonical_record":{"source":{"id":"2312.16189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"224e80979d2091fde40dfb8cfc2fe59c0af75cfcf532b9825843882edd535c98","abstract_canon_sha256":"9c1d8e8515218ad479b8862ba184c7234658e660499476fba371e0bb16d10a3a"},"schema_version":"1.0"},"canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","source":{"kind":"arxiv","id":"2312.16189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16189","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16189v1","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16189","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"BKBTX3GWJZRI","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"BKBTX3GWJZRILLGH","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"BKBTX3GW","created_at":"2026-07-05T07:28:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BKBTX3GWJZRILLGHRHLFODW2MM","target":"record","payload":{"canonical_record":{"source":{"id":"2312.16189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"224e80979d2091fde40dfb8cfc2fe59c0af75cfcf532b9825843882edd535c98","abstract_canon_sha256":"9c1d8e8515218ad479b8862ba184c7234658e660499476fba371e0bb16d10a3a"},"schema_version":"1.0"},"canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:13.960620Z","signature_b64":"SPl5FoihYFEx1xXCDGYNzKEeJjw5schUdAYGlXse1gOjJkBmX5YPnhK84ORUUqfFOVjVe35G/L8e9mtVvKT2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","last_reissued_at":"2026-07-05T07:28:13.960218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:13.960218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.16189","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCCYzty3qRexdkHBOzSxn4NV05oSvOSgb+67oAdgJcXem0eNLkcQgZ4enptqZrpLCIw6xpQi4JCp9GGpNSHVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:59:07.639112Z"},"content_sha256":"ac12fd25329497dc3a4c22162455f5d1a32c94fe21e7c88f4363e608998786b0","schema_version":"1.0","event_id":"sha256:ac12fd25329497dc3a4c22162455f5d1a32c94fe21e7c88f4363e608998786b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BKBTX3GWJZRILLGHRHLFODW2MM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenRL: A Unified Reinforcement Learning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuqing Bie, Shiyu Huang, Wei-Wei Tu, Wentse Chen, Yiwen Sun","submitted_at":"2023-12-20T12:04:06Z","abstract_excerpt":"We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers agents to develop advanced strategies in competitive settings. Notably, OpenRL integrates Natural Language Processing (NLP) with RL, enabling researchers to address a combination of RL training and language-centric tasks effectively. Leveraging PyTorch's robust capabilities, OpenRL exemplifies modularity and a user-centric approach. It offers a universal interfa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16189","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/2312.16189/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Et5e7t4kfh29c8pGtFQVjALRBpKytcMqIzV2zucJczlsa38jZj/9RJmbwl/q9Aa69z3AbsTYOl0QgxKzKlI6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:59:07.639490Z"},"content_sha256":"bf8847320be4ae1c589bd93cb55c71f05556f98a085b88101539c7f7c491efb9","schema_version":"1.0","event_id":"sha256:bf8847320be4ae1c589bd93cb55c71f05556f98a085b88101539c7f7c491efb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/bundle.json","state_url":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKBTX3GWJZRILLGHRHLFODW2MM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T02:59:07Z","links":{"resolver":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM","bundle":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/bundle.json","state":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKBTX3GWJZRILLGHRHLFODW2MM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BKBTX3GWJZRILLGHRHLFODW2MM","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":"9c1d8e8515218ad479b8862ba184c7234658e660499476fba371e0bb16d10a3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","title_canon_sha256":"224e80979d2091fde40dfb8cfc2fe59c0af75cfcf532b9825843882edd535c98"},"schema_version":"1.0","source":{"id":"2312.16189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16189","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16189v1","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16189","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"BKBTX3GWJZRI","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"BKBTX3GWJZRILLGH","created_at":"2026-07-05T07:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"BKBTX3GW","created_at":"2026-07-05T07:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:bf8847320be4ae1c589bd93cb55c71f05556f98a085b88101539c7f7c491efb9","target":"graph","created_at":"2026-07-05T07:28:13Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.16189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers agents to develop advanced strategies in competitive settings. Notably, OpenRL integrates Natural Language Processing (NLP) with RL, enabling researchers to address a combination of RL training and language-centric tasks effectively. Leveraging PyTorch's robust capabilities, OpenRL exemplifies modularity and a user-centric approach. It offers a universal interfa","authors_text":"Fuqing Bie, Shiyu Huang, Wei-Wei Tu, Wentse Chen, Yiwen Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","title":"OpenRL: A Unified Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16189","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac12fd25329497dc3a4c22162455f5d1a32c94fe21e7c88f4363e608998786b0","target":"record","created_at":"2026-07-05T07:28:13Z","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":"9c1d8e8515218ad479b8862ba184c7234658e660499476fba371e0bb16d10a3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","title_canon_sha256":"224e80979d2091fde40dfb8cfc2fe59c0af75cfcf532b9825843882edd535c98"},"schema_version":"1.0","source":{"id":"2312.16189","kind":"arxiv","version":1}},"canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","first_computed_at":"2026-07-05T07:28:13.960218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:13.960218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SPl5FoihYFEx1xXCDGYNzKEeJjw5schUdAYGlXse1gOjJkBmX5YPnhK84ORUUqfFOVjVe35G/L8e9mtVvKT2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:13.960620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac12fd25329497dc3a4c22162455f5d1a32c94fe21e7c88f4363e608998786b0","sha256:bf8847320be4ae1c589bd93cb55c71f05556f98a085b88101539c7f7c491efb9"],"state_sha256":"088178003c4878aed4aa01bec75e6c7c0d68c2bdc3b3aa4f587f001c7028717c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1keReP4Ju9SLJZKdIeiBDLT7GLf3ZE5dfiyDeoZQVuAfQWPvUf2+L9EA8/y78bKRyZpih37YpzQeTDGhN7aTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:59:07.641984Z","bundle_sha256":"55dfe49ad9139240ba05d835e63944aab79ea5c1b71df136d752df6c7628ff0d"}}