{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6XP6OZX5PDZH6RBXLNPDX4U2RJ","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":"9db490dc2645d6ec044d34d0a6d99d6a0dcb2ed4ac2b9a6581b22e5d922fb5cf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","title_canon_sha256":"06072c03dad2437efdef1c5e00a2f6ad82463aa0660253b3133c286bf46d203f"},"schema_version":"1.0","source":{"id":"1912.06088","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.06088","created_at":"2026-07-05T01:39:55Z"},{"alias_kind":"arxiv_version","alias_value":"1912.06088v4","created_at":"2026-07-05T01:39:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06088","created_at":"2026-07-05T01:39:55Z"},{"alias_kind":"pith_short_12","alias_value":"6XP6OZX5PDZH","created_at":"2026-07-05T01:39:55Z"},{"alias_kind":"pith_short_16","alias_value":"6XP6OZX5PDZH6RBX","created_at":"2026-07-05T01:39:55Z"},{"alias_kind":"pith_short_8","alias_value":"6XP6OZX5","created_at":"2026-07-05T01:39:55Z"}],"graph_snapshots":[{"event_id":"sha256:0a373afa952b322a84ef440c7ea8b9f66c4cb744b5667db03c3d8337fcceb07b","target":"graph","created_at":"2026-07-05T01:39:55Z","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/1912.06088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study RL algorithms that use imitation learning to acquire goal reaching policies from scratch, without the need for expert demonstrations or a value function. In lieu of demonstrations, we leverage the property that any trajectory is a successful demonstration for reaching the final ","authors_text":"Abhishek Gupta, Ashwin Reddy, Benjamin Eysenbach, Coline Devin, Dibya Ghosh, Justin Fu, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","title":"Learning to Reach Goals via Iterated Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06088","kind":"arxiv","version":4},"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:ac2706adc45a3411218cfa02cc8c8b8adafb9fa1e52decd163a1db29a6806ab9","target":"record","created_at":"2026-07-05T01:39:55Z","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":"9db490dc2645d6ec044d34d0a6d99d6a0dcb2ed4ac2b9a6581b22e5d922fb5cf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","title_canon_sha256":"06072c03dad2437efdef1c5e00a2f6ad82463aa0660253b3133c286bf46d203f"},"schema_version":"1.0","source":{"id":"1912.06088","kind":"arxiv","version":4}},"canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","first_computed_at":"2026-07-05T01:39:55.326831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:55.326831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+9gWXlBPwrjE9AY2k7u+rNb5Wh2oLi4XrISZlLnOlKPSjFR+UN7vYUTDkLmZW8PInTeCKM5lmKpwKuRYN3cCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:55.327247Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.06088","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac2706adc45a3411218cfa02cc8c8b8adafb9fa1e52decd163a1db29a6806ab9","sha256:0a373afa952b322a84ef440c7ea8b9f66c4cb744b5667db03c3d8337fcceb07b"],"state_sha256":"f4946b5b1dff008b327c7076a85a30bf58e9f0d0928ea66fabc7276a6b1fb4f8"}