{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OVJCO7RMMBYBRP2LNDG5X5ZCLB","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":"711b04a3e1b9f285f4a5f77e3a8079a7477c52da036ab69834b629217a9b2a96","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-15T14:21:24Z","title_canon_sha256":"b10e99590b2536ec5fb39d2c6c2a852667606487dfcbdcd511e855dc01b4fbe8"},"schema_version":"1.0","source":{"id":"2308.07795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07795","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07795v1","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07795","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"OVJCO7RMMBYB","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_16","alias_value":"OVJCO7RMMBYBRP2L","created_at":"2026-07-05T06:41:31Z"},{"alias_kind":"pith_short_8","alias_value":"OVJCO7RM","created_at":"2026-07-05T06:41:31Z"}],"graph_snapshots":[{"event_id":"sha256:89153a1b19e6b961046b37354f13df05ff65b70da51d0fb8b237b8f04f6fc5b0","target":"graph","created_at":"2026-07-05T06:41:31Z","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/2308.07795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or robots may convey a lot of implicit information about rewarding action sequences, but a DRL machine that wants to profit from watching such videos must first learn by itself to identify and recognize relevant states/actions/rewards. Without relying on ground-truth annotations, our new method called Deep State Identifier learns to predict returns from episodes ","authors_text":"Bernard Ghanem, Bing Li, Francesco Faccio, Haozhe Liu, J\\\"urgen Schmidhuber, Mingchen Zhuge, Yuhui Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-15T14:21:24Z","title":"Learning to Identify Critical States for Reinforcement Learning from Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07795","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:f9e33e6e21e54e981321cf917680ac726d5dd0cccd1ca43c784d607633771a9f","target":"record","created_at":"2026-07-05T06:41:31Z","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":"711b04a3e1b9f285f4a5f77e3a8079a7477c52da036ab69834b629217a9b2a96","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-15T14:21:24Z","title_canon_sha256":"b10e99590b2536ec5fb39d2c6c2a852667606487dfcbdcd511e855dc01b4fbe8"},"schema_version":"1.0","source":{"id":"2308.07795","kind":"arxiv","version":1}},"canonical_sha256":"7552277e2c607018bf4b68cddbf722584a764b4f61f5f9dc81e9f4370e4c96fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7552277e2c607018bf4b68cddbf722584a764b4f61f5f9dc81e9f4370e4c96fb","first_computed_at":"2026-07-05T06:41:31.487843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:31.487843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S1NrroQCTN4tJNUGY+IzJZmT3Ls0bcG1RcU9yYnqo2p4WV+5ackQcFXYtMIus3p0iFi1e2i4387Zn1rhwrNDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:31.488288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.07795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9e33e6e21e54e981321cf917680ac726d5dd0cccd1ca43c784d607633771a9f","sha256:89153a1b19e6b961046b37354f13df05ff65b70da51d0fb8b237b8f04f6fc5b0"],"state_sha256":"b7885f99dcb55ae0c56e4447607ed58db6dda022527b5a739d4a43ac163c641c"}