{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UXKUUPFBZXRL2MRUH4Q4RBC4M2","short_pith_number":"pith:UXKUUPFB","canonical_record":{"source":{"id":"2011.10024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T18:47:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"50db4341f2cbf546a94c823e5127a98eee4ea24f5c24ca47ad6cd40cec8fa263","abstract_canon_sha256":"c5006d4cec12f315648dcc289c99a3b5661012da35a3666fbdf4a8ecf9e1611e"},"schema_version":"1.0"},"canonical_sha256":"a5d54a3ca1cde2bd32343f21c8845c66b30e5b3169b67fbd8c555f371e6dda95","source":{"kind":"arxiv","id":"2011.10024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.10024","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2011.10024v1","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10024","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"UXKUUPFBZXRL","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"UXKUUPFBZXRL2MRU","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"UXKUUPFB","created_at":"2026-07-05T01:53:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UXKUUPFBZXRL2MRUH4Q4RBC4M2","target":"record","payload":{"canonical_record":{"source":{"id":"2011.10024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T18:47:40Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"50db4341f2cbf546a94c823e5127a98eee4ea24f5c24ca47ad6cd40cec8fa263","abstract_canon_sha256":"c5006d4cec12f315648dcc289c99a3b5661012da35a3666fbdf4a8ecf9e1611e"},"schema_version":"1.0"},"canonical_sha256":"a5d54a3ca1cde2bd32343f21c8845c66b30e5b3169b67fbd8c555f371e6dda95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:03.931068Z","signature_b64":"BDeIYj+5+SjsxIcQvMV46fo9YMS7ikoI2kqCrVlrhUwSdTTzmWJpUSBK8hfTII0xTSU252FGy+zHnGUfKCAQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d54a3ca1cde2bd32343f21c8845c66b30e5b3169b67fbd8c555f371e6dda95","last_reissued_at":"2026-07-05T01:53:03.930606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:03.930606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.10024","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":"2026-07-05T01:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oDu37HjiErDyPnFh+yWl5W5YNNHK7igvHK2S11qAfdvIhh5GKDbqnk7Ie+bjUW94DYMwjpJGUnP7AHEg6yN3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:39:08.704823Z"},"content_sha256":"89085fb2b943ed10705701a7fbe5883a0cbc3fb72030c0e15348255a7faaa060","schema_version":"1.0","event_id":"sha256:89085fb2b943ed10705701a7fbe5883a0cbc3fb72030c0e15348255a7faaa060"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UXKUUPFBZXRL2MRUH4Q4RBC4M2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Albert Yu, Avi Singh, Gaoyue Zhou, Huihan Liu, Nicholas Rhinehart, Sergey Levine","submitted_at":"2020-11-19T18:47:40Z","abstract_excerpt":"Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10024","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/2011.10024/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":"2026-07-05T01:53:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Qq1bkmYO1FeESYAuO/1aEnZcK+Naq8ixZ0Y0AuSxgaEKoyqy/nmJm740a+RIKr5uBIzXfiHjbLPQ0p7ycvaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:39:08.705498Z"},"content_sha256":"127dd557989e1571f189d41df361bc71521a463f7f9301fc870156efe577c415","schema_version":"1.0","event_id":"sha256:127dd557989e1571f189d41df361bc71521a463f7f9301fc870156efe577c415"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/bundle.json","state_url":"https://pith.science/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/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":"2026-08-03T16:39:08Z","links":{"resolver":"https://pith.science/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2","bundle":"https://pith.science/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/bundle.json","state":"https://pith.science/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXKUUPFBZXRL2MRUH4Q4RBC4M2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UXKUUPFBZXRL2MRUH4Q4RBC4M2","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":"c5006d4cec12f315648dcc289c99a3b5661012da35a3666fbdf4a8ecf9e1611e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T18:47:40Z","title_canon_sha256":"50db4341f2cbf546a94c823e5127a98eee4ea24f5c24ca47ad6cd40cec8fa263"},"schema_version":"1.0","source":{"id":"2011.10024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.10024","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2011.10024v1","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10024","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"UXKUUPFBZXRL","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"UXKUUPFBZXRL2MRU","created_at":"2026-07-05T01:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"UXKUUPFB","created_at":"2026-07-05T01:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:127dd557989e1571f189d41df361bc71521a463f7f9301fc870156efe577c415","target":"graph","created_at":"2026-07-05T01:53:03Z","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/2011.10024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behav","authors_text":"Albert Yu, Avi Singh, Gaoyue Zhou, Huihan Liu, Nicholas Rhinehart, Sergey Levine","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T18:47:40Z","title":"Parrot: Data-Driven Behavioral Priors for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10024","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":"sha256:89085fb2b943ed10705701a7fbe5883a0cbc3fb72030c0e15348255a7faaa060","target":"record","created_at":"2026-07-05T01:53:03Z","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":"c5006d4cec12f315648dcc289c99a3b5661012da35a3666fbdf4a8ecf9e1611e","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T18:47:40Z","title_canon_sha256":"50db4341f2cbf546a94c823e5127a98eee4ea24f5c24ca47ad6cd40cec8fa263"},"schema_version":"1.0","source":{"id":"2011.10024","kind":"arxiv","version":1}},"canonical_sha256":"a5d54a3ca1cde2bd32343f21c8845c66b30e5b3169b67fbd8c555f371e6dda95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5d54a3ca1cde2bd32343f21c8845c66b30e5b3169b67fbd8c555f371e6dda95","first_computed_at":"2026-07-05T01:53:03.930606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:03.930606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDeIYj+5+SjsxIcQvMV46fo9YMS7ikoI2kqCrVlrhUwSdTTzmWJpUSBK8hfTII0xTSU252FGy+zHnGUfKCAQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:03.931068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.10024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89085fb2b943ed10705701a7fbe5883a0cbc3fb72030c0e15348255a7faaa060","sha256:127dd557989e1571f189d41df361bc71521a463f7f9301fc870156efe577c415"],"state_sha256":"834e6a1cc03548b08029fb0ffc9794f4995e2ec9bb51ed2b19ef1698accb4a98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3aMt3OW2m2fyTGoJmmjmr1eDd2OlUIRSCSqzAt+jebhf9a9OeLDeJYL8dFyOKrscEoJ1Ja/fuDdUA+XX5pCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:39:08.710782Z","bundle_sha256":"e69c79c888be55935e3f48990f74709b41fd41c9a0572a2c9b826fa0e890fd01"}}