{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HFMSPIDMQTWMAKSSAYITWIA6SD","short_pith_number":"pith:HFMSPIDM","canonical_record":{"source":{"id":"2011.13885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-27T18:20:04Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"ab59c8e32552f625c9eebc4259b293fa589c197fd5df9fb4ac9caa0ee74ff40a","abstract_canon_sha256":"cfb060f8778083738f0d232c3073fab86cb628a733856cbbb1509311c15b8e14"},"schema_version":"1.0"},"canonical_sha256":"395927a06c84ecc02a5206113b201e90e0a8225d918e97a7daedaea9912e93c7","source":{"kind":"arxiv","id":"2011.13885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13885","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13885v1","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13885","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"HFMSPIDMQTWM","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"HFMSPIDMQTWMAKSS","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"HFMSPIDM","created_at":"2026-07-05T01:54:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HFMSPIDMQTWMAKSSAYITWIA6SD","target":"record","payload":{"canonical_record":{"source":{"id":"2011.13885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-27T18:20:04Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"ab59c8e32552f625c9eebc4259b293fa589c197fd5df9fb4ac9caa0ee74ff40a","abstract_canon_sha256":"cfb060f8778083738f0d232c3073fab86cb628a733856cbbb1509311c15b8e14"},"schema_version":"1.0"},"canonical_sha256":"395927a06c84ecc02a5206113b201e90e0a8225d918e97a7daedaea9912e93c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:59.301458Z","signature_b64":"rHM+XDVfMvoJYdjENYktPLSeozgEGD2geldrxPuesv7HSCTfALXd1ThUYiquf6RY+X5IsO44G2seMSsK2EIyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395927a06c84ecc02a5206113b201e90e0a8225d918e97a7daedaea9912e93c7","last_reissued_at":"2026-07-05T01:54:59.301097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:59.301097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.13885","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":"2026-07-05T01:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLRj3GwlVlIaezCRm52/DYpTfeuRM0d5h8pps1A1O2IEwq070/0JtZ9X5/TTP3BnJHNhuJUyPRwHyINgJrEFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:45:29.105011Z"},"content_sha256":"5ef5167efecd4978024a0fe9c63bfa131c8128a740fc99b50be3d199cad1adea","schema_version":"1.0","event_id":"sha256:5ef5167efecd4978024a0fe9c63bfa131c8128a740fc99b50be3d199cad1adea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HFMSPIDMQTWMAKSSAYITWIA6SD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Learning from Demonstrations and Unlabeled Experience","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Novikov, Caglar Gulcehre, Konrad Zolna, Ksenia Konyushkova, Misha Denil, Nando de Freitas, Scott Reed, Yusuf Aytar, Ziyu Wang","submitted_at":"2020-11-27T18:20:04Z","abstract_excerpt":"Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to as unlabeled experience: data of mixed and unknown quality without reward annotations. This unlabeled data can be generated by a variety of sources such as human teleoperation, scripted policies and other agents on the same robot. Towards data-driven offline robot learning that can use this unlabeled experience, we introduce Offline Reinforced Imitation Learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13885","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/2011.13885/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":"2026-07-05T01:54:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TidEWJUWKp4ZKwWm8ncBFtijagxnGfC+ecTONQbIEEWY7XUNuY0F2il9XirTEiIp9ELUHWPJtTDfFd0n2c42Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:45:29.105518Z"},"content_sha256":"aaa5f8b91e7c707f7e94396668e68d28e40625784d25a2d7027812599558a0ae","schema_version":"1.0","event_id":"sha256:aaa5f8b91e7c707f7e94396668e68d28e40625784d25a2d7027812599558a0ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/bundle.json","state_url":"https://pith.science/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/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":"2026-08-11T20:45:29Z","links":{"resolver":"https://pith.science/pith/HFMSPIDMQTWMAKSSAYITWIA6SD","bundle":"https://pith.science/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/bundle.json","state":"https://pith.science/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFMSPIDMQTWMAKSSAYITWIA6SD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HFMSPIDMQTWMAKSSAYITWIA6SD","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":"cfb060f8778083738f0d232c3073fab86cb628a733856cbbb1509311c15b8e14","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-27T18:20:04Z","title_canon_sha256":"ab59c8e32552f625c9eebc4259b293fa589c197fd5df9fb4ac9caa0ee74ff40a"},"schema_version":"1.0","source":{"id":"2011.13885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13885","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13885v1","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13885","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_12","alias_value":"HFMSPIDMQTWM","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_16","alias_value":"HFMSPIDMQTWMAKSS","created_at":"2026-07-05T01:54:59Z"},{"alias_kind":"pith_short_8","alias_value":"HFMSPIDM","created_at":"2026-07-05T01:54:59Z"}],"graph_snapshots":[{"event_id":"sha256:aaa5f8b91e7c707f7e94396668e68d28e40625784d25a2d7027812599558a0ae","target":"graph","created_at":"2026-07-05T01:54:59Z","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/2011.13885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to as unlabeled experience: data of mixed and unknown quality without reward annotations. This unlabeled data can be generated by a variety of sources such as human teleoperation, scripted policies and other agents on the same robot. Towards data-driven offline robot learning that can use this unlabeled experience, we introduce Offline Reinforced Imitation Learn","authors_text":"Alexander Novikov, Caglar Gulcehre, Konrad Zolna, Ksenia Konyushkova, Misha Denil, Nando de Freitas, Scott Reed, Yusuf Aytar, Ziyu Wang","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-27T18:20:04Z","title":"Offline Learning from Demonstrations and Unlabeled Experience"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13885","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":"sha256:5ef5167efecd4978024a0fe9c63bfa131c8128a740fc99b50be3d199cad1adea","target":"record","created_at":"2026-07-05T01:54:59Z","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":"cfb060f8778083738f0d232c3073fab86cb628a733856cbbb1509311c15b8e14","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-27T18:20:04Z","title_canon_sha256":"ab59c8e32552f625c9eebc4259b293fa589c197fd5df9fb4ac9caa0ee74ff40a"},"schema_version":"1.0","source":{"id":"2011.13885","kind":"arxiv","version":1}},"canonical_sha256":"395927a06c84ecc02a5206113b201e90e0a8225d918e97a7daedaea9912e93c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"395927a06c84ecc02a5206113b201e90e0a8225d918e97a7daedaea9912e93c7","first_computed_at":"2026-07-05T01:54:59.301097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:59.301097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rHM+XDVfMvoJYdjENYktPLSeozgEGD2geldrxPuesv7HSCTfALXd1ThUYiquf6RY+X5IsO44G2seMSsK2EIyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:59.301458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ef5167efecd4978024a0fe9c63bfa131c8128a740fc99b50be3d199cad1adea","sha256:aaa5f8b91e7c707f7e94396668e68d28e40625784d25a2d7027812599558a0ae"],"state_sha256":"68e8bf28a7f03124f2af5352b05d92a99947373abfcecc80990fa81a78c7fed2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDmaz77KggMVoGUOZEFCcPXGNz3T5Hu5joJ8QXnkzi3TpMWjH2fwdkjwO1DSskFaUk5QNn4OQjY/1Xa0BPykAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:45:29.109826Z","bundle_sha256":"453938db0981195a121c0e671500da59b3434477076a081d5c09fc2b752a895e"}}