{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BEZTHYZO2P3QFJXH45HIFSKSRH","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":"d1261ac83af234632d785b3e15bf29dabe612bf41ef92068351572fa226f2a36","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-01T20:48:39Z","title_canon_sha256":"f53ebe1aff661abda3913ba47100df4640cb1e05410fc5891c270b3bca7ba98d"},"schema_version":"1.0","source":{"id":"1612.00429","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00429","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00429v2","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00429","created_at":"2026-05-18T00:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"BEZTHYZO2P3Q","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BEZTHYZO2P3QFJXH","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BEZTHYZO","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:06afcf96d923ea6b65a373680519535c51c31f8a6d348a447f73f3ff588898d2","target":"graph","created_at":"2026-05-18T00:48:59Z","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"},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known to achieve remarkable generalization when provided with massive amounts of labeled data, but can we provide this breadth of experience to an RL agent, such as a robot? The robot might continuously learn as it explores the world around it, even while deployed. However, this learning requires access to a reward function, which is often hard to measure in real-w","authors_text":"Chelsea Finn, Justin Fu, Pieter Abbeel, Sergey Levine, Tianhe Yu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-01T20:48:39Z","title":"Generalizing Skills with Semi-Supervised Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00429","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":"sha256:690a1dd0dffe7ad6d75ea68ebaf678b79b2229ae4b4dbe9887f12aa4f55b810d","target":"record","created_at":"2026-05-18T00:48:59Z","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":"d1261ac83af234632d785b3e15bf29dabe612bf41ef92068351572fa226f2a36","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-01T20:48:39Z","title_canon_sha256":"f53ebe1aff661abda3913ba47100df4640cb1e05410fc5891c270b3bca7ba98d"},"schema_version":"1.0","source":{"id":"1612.00429","kind":"arxiv","version":2}},"canonical_sha256":"093333e32ed3f702a6e7e74e82c95289c672f89cf04234d38ee60139d2843eaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"093333e32ed3f702a6e7e74e82c95289c672f89cf04234d38ee60139d2843eaf","first_computed_at":"2026-05-18T00:48:59.597090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:59.597090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w9pkcHEojO6UEFaf7mZD9o36FSG5/KDwVLK4Qbi4GCBtDvy5Jd5bq9taEvEXjFAvasHUl3opJMx0DSQTeMyZDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:59.597769Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00429","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:690a1dd0dffe7ad6d75ea68ebaf678b79b2229ae4b4dbe9887f12aa4f55b810d","sha256:06afcf96d923ea6b65a373680519535c51c31f8a6d348a447f73f3ff588898d2"],"state_sha256":"efeef8b6d0fb6b8de866374798daa93a8b89d583f994be981cfd3c56fa8d8bcd"}