{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","short_pith_number":"pith:OMTE3XG4","canonical_record":{"source":{"id":"2305.13795","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3","abstract_canon_sha256":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321"},"schema_version":"1.0"},"canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","source":{"kind":"arxiv","id":"2305.13795","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13795v2","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"OMTE3XG4KEAD","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"OMTE3XG4KEADLVHV","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"OMTE3XG4","created_at":"2026-07-05T07:38:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13795","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3","abstract_canon_sha256":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321"},"schema_version":"1.0"},"canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:50.743296Z","signature_b64":"K9YHWE0OorD/Re5UdZH6Mj599P1yKuIlqeg7vlwGhjVrCeMsH0BWcitunJAoDZsJxEZXdjO6LoZvav9T7HFQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","last_reissued_at":"2026-07-05T07:38:50.742743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:50.742743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13795","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWLev43jhJADjJKlN0VnsoaIsP7P9X67GWQUCIrJS1mySGKO5wtBNfU9WQiKwD5w1lMLG09v/uM7DKSibc7PDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:06.868050Z"},"content_sha256":"c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b","schema_version":"1.0","event_id":"sha256:c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksei Petrenko, Bryon Tjanaka, Gaurav Sukhatme, Matthew C. Fontaine, Stefanos Nikolaidis, Sumeet Batra","submitted_at":"2023-05-23T08:05:59Z","abstract_excerpt":"Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields -- Quality Diversity (QD) provides a principled form of exploration and produces collections of behaviorally diverse agents, while Reinforcement Learning (RL) provides a powerful performance improvement operator enabling generalization across tasks and dynamic environments. Existing QD-RL approaches have been constrained to samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13795","kind":"arxiv","version":2},"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/2305.13795/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":"2026-07-05T07:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06u/4gHXrOQVDMEDplkJNjwBRaWx8LYQKf07sMyxpPuNQebdaDpWdaXpaSwTM1ke/WQjGd/TQxWWitnN7mgRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:06.868454Z"},"content_sha256":"3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d","schema_version":"1.0","event_id":"sha256:3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/bundle.json","state_url":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMTE3XG4KEADLVHVJR72VWRMHP/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":"2026-08-03T20:20:06Z","links":{"resolver":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP","bundle":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/bundle.json","state":"https://pith.science/pith/OMTE3XG4KEADLVHVJR72VWRMHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMTE3XG4KEADLVHVJR72VWRMHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OMTE3XG4KEADLVHVJR72VWRMHP","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":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3"},"schema_version":"1.0","source":{"id":"2305.13795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13795v2","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13795","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"OMTE3XG4KEAD","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"OMTE3XG4KEADLVHV","created_at":"2026-07-05T07:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"OMTE3XG4","created_at":"2026-07-05T07:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d","target":"graph","created_at":"2026-07-05T07:38:50Z","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/2305.13795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement Learning (QD-RL) is an emerging research area that blends the best aspects of both fields -- Quality Diversity (QD) provides a principled form of exploration and produces collections of behaviorally diverse agents, while Reinforcement Learning (RL) provides a powerful performance improvement operator enabling generalization across tasks and dynamic environments. Existing QD-RL approaches have been constrained to samp","authors_text":"Aleksei Petrenko, Bryon Tjanaka, Gaurav Sukhatme, Matthew C. Fontaine, Stefanos Nikolaidis, Sumeet Batra","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title":"Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13795","kind":"arxiv","version":2},"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:c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b","target":"record","created_at":"2026-07-05T07:38:50Z","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":"e9c61b98ade0821479cb9bf8169fdefa74eb86624b6e3c8f818d4ce795ab0321","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T08:05:59Z","title_canon_sha256":"04fde76165275f7ee286c481f60be686797b8bbd6e7b2a56f7340430640dc8c3"},"schema_version":"1.0","source":{"id":"2305.13795","kind":"arxiv","version":2}},"canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73264ddcdc510035d4f54c7faada2c3bdefc7d5829e082c7214f702ab6ef9b3b","first_computed_at":"2026-07-05T07:38:50.742743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:50.742743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K9YHWE0OorD/Re5UdZH6Mj599P1yKuIlqeg7vlwGhjVrCeMsH0BWcitunJAoDZsJxEZXdjO6LoZvav9T7HFQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:50.743296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c07abdbdc9d623a13426583fb3ab51fa203b4a7bb63156a7e4bc19881c97d46b","sha256:3548d0ee51e5c5e3e94d83b25e8fe62c51ca899a4cdb6186f2cbb9862c4dfe6d"],"state_sha256":"3c92fc350e572c10791600917b5947020136c22d4abd886b3b4ee0c8d515f31f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+nGmzaH6czeNoDz11LDmyahviqDDpdm9KfGZXn6qcDicKI1pR125JT7HBLSttWCaRYoibwUSjjOfTSyF6W9RAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:20:06.871309Z","bundle_sha256":"948b4c7fe2fb5cc2c5d1212dcd1bdc9a58bd1f523fc86d464c8b0ed31edc620e"}}