{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YGMFAJDTLZWN3YNJZVSKIUXMZL","short_pith_number":"pith:YGMFAJDT","canonical_record":{"source":{"id":"2311.02198","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T19:03:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de3be4af5970b5ea05b739b0949993ab8d13b78587b0533dd33d338bf0dc7c20","abstract_canon_sha256":"3c1cb246750518f0dad32b05805d07dc474e9f3140978a3c235a34e555799d6c"},"schema_version":"1.0"},"canonical_sha256":"c1985024735e6cdde1a9cd64a452eccad4abac68093b1e52ffdfcdad3a8a2b2a","source":{"kind":"arxiv","id":"2311.02198","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02198","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02198v6","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02198","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"YGMFAJDTLZWN","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"YGMFAJDTLZWN3YNJ","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"YGMFAJDT","created_at":"2026-07-05T08:21:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YGMFAJDTLZWN3YNJZVSKIUXMZL","target":"record","payload":{"canonical_record":{"source":{"id":"2311.02198","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T19:03:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de3be4af5970b5ea05b739b0949993ab8d13b78587b0533dd33d338bf0dc7c20","abstract_canon_sha256":"3c1cb246750518f0dad32b05805d07dc474e9f3140978a3c235a34e555799d6c"},"schema_version":"1.0"},"canonical_sha256":"c1985024735e6cdde1a9cd64a452eccad4abac68093b1e52ffdfcdad3a8a2b2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:09.353982Z","signature_b64":"wgWMRMy/iiTOqb227dBnOhQjR0+paV6U6Y2j7KvBi6xqdNlIMIr/PYbaJUOfJi5f9zfntr0MC6AgL3JYCG7uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1985024735e6cdde1a9cd64a452eccad4abac68093b1e52ffdfcdad3a8a2b2a","last_reissued_at":"2026-07-05T08:21:09.353610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:09.353610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.02198","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTp4E+Vyz+31sL7QJEVBHweslXdhwOUTPLq5nLRA0VOGW5Vpi8nO8RQ8xMKeXVUBb3gZTDf2zChukrr5kWVZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:21:54.068410Z"},"content_sha256":"3a73f7d31a8798d8b17242a69787565cb0e0f9a8223b30e55b6fbccad01c577c","schema_version":"1.0","event_id":"sha256:3a73f7d31a8798d8b17242a69787565cb0e0f9a8223b30e55b6fbccad01c577c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YGMFAJDTLZWN3YNJZVSKIUXMZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitation Bootstrapped Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dorsa Sadigh, Hengyuan Hu, Suvir Mirchandani","submitted_at":"2023-11-03T19:03:20Z","abstract_excerpt":"Despite the considerable potential of reinforcement learning (RL), robotic control tasks predominantly rely on imitation learning (IL) due to its better sample efficiency. However, it is costly to collect comprehensive expert demonstrations that enable IL to generalize to all possible scenarios, and any distribution shift would require recollecting data for finetuning. Therefore, RL is appealing if it can build upon IL as an efficient autonomous self-improvement procedure. We propose imitation bootstrapped reinforcement learning (IBRL), a novel framework for sample-efficient RL with demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02198","kind":"arxiv","version":6},"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/2311.02198/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":"2026-07-05T08:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcBQjhm8DCbBF+mJrUJKWZU/jaFEn8c7pkBHe2d3WVrNHR55OVQ9Mta5u9GFKXGhxBCBmTPNLkbyvl5WbcDsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:21:54.069426Z"},"content_sha256":"bf082dd51f5338685ca6c19527c3f7a79b0a48623e990765cbe7e632aab7b9aa","schema_version":"1.0","event_id":"sha256:bf082dd51f5338685ca6c19527c3f7a79b0a48623e990765cbe7e632aab7b9aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/bundle.json","state_url":"https://pith.science/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/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":"2026-08-04T14:21:54Z","links":{"resolver":"https://pith.science/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL","bundle":"https://pith.science/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/bundle.json","state":"https://pith.science/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGMFAJDTLZWN3YNJZVSKIUXMZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YGMFAJDTLZWN3YNJZVSKIUXMZL","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":"3c1cb246750518f0dad32b05805d07dc474e9f3140978a3c235a34e555799d6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T19:03:20Z","title_canon_sha256":"de3be4af5970b5ea05b739b0949993ab8d13b78587b0533dd33d338bf0dc7c20"},"schema_version":"1.0","source":{"id":"2311.02198","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02198","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02198v6","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02198","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"YGMFAJDTLZWN","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"YGMFAJDTLZWN3YNJ","created_at":"2026-07-05T08:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"YGMFAJDT","created_at":"2026-07-05T08:21:09Z"}],"graph_snapshots":[{"event_id":"sha256:bf082dd51f5338685ca6c19527c3f7a79b0a48623e990765cbe7e632aab7b9aa","target":"graph","created_at":"2026-07-05T08:21:09Z","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/2311.02198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the considerable potential of reinforcement learning (RL), robotic control tasks predominantly rely on imitation learning (IL) due to its better sample efficiency. However, it is costly to collect comprehensive expert demonstrations that enable IL to generalize to all possible scenarios, and any distribution shift would require recollecting data for finetuning. Therefore, RL is appealing if it can build upon IL as an efficient autonomous self-improvement procedure. We propose imitation bootstrapped reinforcement learning (IBRL), a novel framework for sample-efficient RL with demonstrat","authors_text":"Dorsa Sadigh, Hengyuan Hu, Suvir Mirchandani","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T19:03:20Z","title":"Imitation Bootstrapped Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02198","kind":"arxiv","version":6},"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":"sha256:3a73f7d31a8798d8b17242a69787565cb0e0f9a8223b30e55b6fbccad01c577c","target":"record","created_at":"2026-07-05T08:21:09Z","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":"3c1cb246750518f0dad32b05805d07dc474e9f3140978a3c235a34e555799d6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T19:03:20Z","title_canon_sha256":"de3be4af5970b5ea05b739b0949993ab8d13b78587b0533dd33d338bf0dc7c20"},"schema_version":"1.0","source":{"id":"2311.02198","kind":"arxiv","version":6}},"canonical_sha256":"c1985024735e6cdde1a9cd64a452eccad4abac68093b1e52ffdfcdad3a8a2b2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1985024735e6cdde1a9cd64a452eccad4abac68093b1e52ffdfcdad3a8a2b2a","first_computed_at":"2026-07-05T08:21:09.353610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:09.353610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wgWMRMy/iiTOqb227dBnOhQjR0+paV6U6Y2j7KvBi6xqdNlIMIr/PYbaJUOfJi5f9zfntr0MC6AgL3JYCG7uBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:09.353982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02198","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a73f7d31a8798d8b17242a69787565cb0e0f9a8223b30e55b6fbccad01c577c","sha256:bf082dd51f5338685ca6c19527c3f7a79b0a48623e990765cbe7e632aab7b9aa"],"state_sha256":"b303111f328d394239bae5e97c67b554c3242021ee28ca158bd62ed808f8cb42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYKSMLtR+16IUxerQMWSfZsu3qawBkZ+kSrPyI2Y5wtU2NrVQG54yevd3/FDCLmhTBeyseL9g1hIw1MH0vqDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:21:54.109066Z","bundle_sha256":"c7e2c75f05fe6baddbb7a92a41d5dd64a28c69b287ec14e1745680340d91b4e4"}}