{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F2SKHER4BOF4DYNNYTU2G2HEUB","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":"4ced5af5ecc59abe8a126d2a22fcf8e512356ae959373756b5b4ba813e7ab7fc","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-12T17:15:48Z","title_canon_sha256":"f46356e47934f592824e106e80d5ad04b811fc41c598389690e72bc4013e7343"},"schema_version":"1.0","source":{"id":"2011.06507","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06507","created_at":"2026-07-05T03:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06507v2","created_at":"2026-07-05T03:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06507","created_at":"2026-07-05T03:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"F2SKHER4BOF4","created_at":"2026-07-05T03:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"F2SKHER4BOF4DYNN","created_at":"2026-07-05T03:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"F2SKHER4","created_at":"2026-07-05T03:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:343af22f8e3977788f1c43ed6862421ca6a1468e7ff0980e4e8fd85b4f03cf34","target":"graph","created_at":"2026-07-05T03:29:14Z","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/2011.06507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that are needed for robots to generalize broadly. Videos of humans, on the other hand, are a readily available source of broad and interesting experiences. In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans? This problem is particularly difficult, as such videos are not annotated with actions an","authors_text":"Chelsea Finn, Karl Schmeckpeper, Kostas Daniilidis, Oleh Rybkin, Sergey Levine","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-12T17:15:48Z","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06507","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":"sha256:6908d43c7edd4cc90cb4d930dc749a73c273a4c3bee070e76ade55124388e5ab","target":"record","created_at":"2026-07-05T03:29:14Z","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":"4ced5af5ecc59abe8a126d2a22fcf8e512356ae959373756b5b4ba813e7ab7fc","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-12T17:15:48Z","title_canon_sha256":"f46356e47934f592824e106e80d5ad04b811fc41c598389690e72bc4013e7343"},"schema_version":"1.0","source":{"id":"2011.06507","kind":"arxiv","version":2}},"canonical_sha256":"2ea4a3923c0b8bc1e1adc4e9a368e4a07e190fc1359f217048fae4a92784ca37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ea4a3923c0b8bc1e1adc4e9a368e4a07e190fc1359f217048fae4a92784ca37","first_computed_at":"2026-07-05T03:29:14.537715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:14.537715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3CG9LNMxzDhb4hbYI8ky/eA4+vBBX7elUyBja2SqR7g82OH0K28AtB1z/sQYiaSvDUROEWx46U5jeEVPWVQuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:14.538101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06507","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6908d43c7edd4cc90cb4d930dc749a73c273a4c3bee070e76ade55124388e5ab","sha256:343af22f8e3977788f1c43ed6862421ca6a1468e7ff0980e4e8fd85b4f03cf34"],"state_sha256":"f81e1fc3d0fcbfa1094c21e661ac64d9fb934cca4a73908c9de246ef56211daf"}