{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3XAMNKPUKHOXPILS3L2AQVIQ56","short_pith_number":"pith:3XAMNKPU","canonical_record":{"source":{"id":"2111.05424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-09T21:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"0d9d42a541edc76f9b0390ceeb6ee0dac26da925196775d8cb6e1fe432b3d946","abstract_canon_sha256":"100537a9db98f1011f041ca99f7c49b1505332cb8aa021bc4ecb819e0dee7a56"},"schema_version":"1.0"},"canonical_sha256":"ddc0c6a9f451dd77a172daf4085510efb81be7c4f734cce09b2cdb6d2a669780","source":{"kind":"arxiv","id":"2111.05424","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05424","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05424v2","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05424","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"3XAMNKPUKHOX","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"3XAMNKPUKHOXPILS","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"3XAMNKPU","created_at":"2026-07-05T03:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3XAMNKPUKHOXPILS3L2AQVIQ56","target":"record","payload":{"canonical_record":{"source":{"id":"2111.05424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-09T21:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"0d9d42a541edc76f9b0390ceeb6ee0dac26da925196775d8cb6e1fe432b3d946","abstract_canon_sha256":"100537a9db98f1011f041ca99f7c49b1505332cb8aa021bc4ecb819e0dee7a56"},"schema_version":"1.0"},"canonical_sha256":"ddc0c6a9f451dd77a172daf4085510efb81be7c4f734cce09b2cdb6d2a669780","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:55.428082Z","signature_b64":"aSzNaD+quGeQbz7a1OJ8O88lSvA2RAcs8VmVtQNtA7eeSJliYZmMou8uGu/jpXRL4/FrZObbrlXjwFAmF+PWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddc0c6a9f451dd77a172daf4085510efb81be7c4f734cce09b2cdb6d2a669780","last_reissued_at":"2026-07-05T03:30:55.427467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:55.427467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.05424","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":"2026-07-05T03:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOCUHR3bIKAFovf6TaLmdXHDjW3kDuCMv6DG2YWJ0vV4zqpqbEdXP/J6UieLKZ9kdyNiAy3X1D7IPFaSBAEaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:56:25.820846Z"},"content_sha256":"d0db0d2a62c204e2e774558857333b0e34c1d0e30ddc12e950531c2578c80a90","schema_version":"1.0","event_id":"sha256:d0db0d2a62c204e2e774558857333b0e34c1d0e30ddc12e950531c2578c80a90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3XAMNKPUKHOXPILS3L2AQVIQ56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alexander Herzog, Alex Irpan, Dmitry Kalashnikov, Eric Jang, Karol Hausman, Mengyuan Yan, Mohi Khansari, Sergey Levine, Ted Xiao, Yao Lu, Yevgen Chebotar","submitted_at":"2021-11-09T21:27:33Z","abstract_excerpt":"Robotic skills can be learned via imitation learning (IL) using user-provided demonstrations, or via reinforcement learning (RL) using large amountsof autonomously collected experience.Both methods have complementarystrengths and weaknesses: RL can reach a high level of performance, but requiresexploration, which can be very time consuming and unsafe; IL does not requireexploration, but only learns skills that are as good as the provided demonstrations.Can a single method combine the strengths of both approaches? A number ofprior methods have aimed to address this question, proposing a variety"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05424","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/2111.05424/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":"2026-07-05T03:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LKJgaQoojxtqnSFFNWsTOSyk4aE8Xi5mLvmrdFLdYa2bxG/UCPGJVgUUfQbpLlM27TaaDPqquiaO3k1/XUWWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:56:25.821723Z"},"content_sha256":"696837d2e0b4adef5ec32b3285ad1677c5e43ffa1c4916ee1cf821cc3d8ad7a5","schema_version":"1.0","event_id":"sha256:696837d2e0b4adef5ec32b3285ad1677c5e43ffa1c4916ee1cf821cc3d8ad7a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/bundle.json","state_url":"https://pith.science/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/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":"2026-08-14T02:56:25Z","links":{"resolver":"https://pith.science/pith/3XAMNKPUKHOXPILS3L2AQVIQ56","bundle":"https://pith.science/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/bundle.json","state":"https://pith.science/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XAMNKPUKHOXPILS3L2AQVIQ56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3XAMNKPUKHOXPILS3L2AQVIQ56","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":"100537a9db98f1011f041ca99f7c49b1505332cb8aa021bc4ecb819e0dee7a56","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-09T21:27:33Z","title_canon_sha256":"0d9d42a541edc76f9b0390ceeb6ee0dac26da925196775d8cb6e1fe432b3d946"},"schema_version":"1.0","source":{"id":"2111.05424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05424","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05424v2","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05424","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"3XAMNKPUKHOX","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"3XAMNKPUKHOXPILS","created_at":"2026-07-05T03:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"3XAMNKPU","created_at":"2026-07-05T03:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:696837d2e0b4adef5ec32b3285ad1677c5e43ffa1c4916ee1cf821cc3d8ad7a5","target":"graph","created_at":"2026-07-05T03:30:55Z","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/2111.05424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robotic skills can be learned via imitation learning (IL) using user-provided demonstrations, or via reinforcement learning (RL) using large amountsof autonomously collected experience.Both methods have complementarystrengths and weaknesses: RL can reach a high level of performance, but requiresexploration, which can be very time consuming and unsafe; IL does not requireexploration, but only learns skills that are as good as the provided demonstrations.Can a single method combine the strengths of both approaches? A number ofprior methods have aimed to address this question, proposing a variety","authors_text":"Alexander Herzog, Alex Irpan, Dmitry Kalashnikov, Eric Jang, Karol Hausman, Mengyuan Yan, Mohi Khansari, Sergey Levine, Ted Xiao, Yao Lu, Yevgen Chebotar","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-09T21:27:33Z","title":"AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05424","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:d0db0d2a62c204e2e774558857333b0e34c1d0e30ddc12e950531c2578c80a90","target":"record","created_at":"2026-07-05T03:30:55Z","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":"100537a9db98f1011f041ca99f7c49b1505332cb8aa021bc4ecb819e0dee7a56","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-09T21:27:33Z","title_canon_sha256":"0d9d42a541edc76f9b0390ceeb6ee0dac26da925196775d8cb6e1fe432b3d946"},"schema_version":"1.0","source":{"id":"2111.05424","kind":"arxiv","version":2}},"canonical_sha256":"ddc0c6a9f451dd77a172daf4085510efb81be7c4f734cce09b2cdb6d2a669780","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddc0c6a9f451dd77a172daf4085510efb81be7c4f734cce09b2cdb6d2a669780","first_computed_at":"2026-07-05T03:30:55.427467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:55.427467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aSzNaD+quGeQbz7a1OJ8O88lSvA2RAcs8VmVtQNtA7eeSJliYZmMou8uGu/jpXRL4/FrZObbrlXjwFAmF+PWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:55.428082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.05424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0db0d2a62c204e2e774558857333b0e34c1d0e30ddc12e950531c2578c80a90","sha256:696837d2e0b4adef5ec32b3285ad1677c5e43ffa1c4916ee1cf821cc3d8ad7a5"],"state_sha256":"10a37424ec218d4b90edc47e93b1c784006a80e6c2f0e8cd2a178c4b0ff85381"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMuwSfSEcLx+oBSw0RIflIF4WaJgtibQmb5PJG1Vw6ZALE/3omBvR3PVQUOVNTnaOoLsHRCS4jQMbSjWtWSsBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:56:25.826849Z","bundle_sha256":"b978757654a0ac620c186c02e670aaccd4f7c768ee5fa8dd8186b85ee0cc54b5"}}