{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6XP6OZX5PDZH6RBXLNPDX4U2RJ","short_pith_number":"pith:6XP6OZX5","canonical_record":{"source":{"id":"1912.06088","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"06072c03dad2437efdef1c5e00a2f6ad82463aa0660253b3133c286bf46d203f","abstract_canon_sha256":"9db490dc2645d6ec044d34d0a6d99d6a0dcb2ed4ac2b9a6581b22e5d922fb5cf"},"schema_version":"1.0"},"canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","source":{"kind":"arxiv","id":"1912.06088","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6XP6OZX5PDZH6RBXLNPDX4U2RJ","target":"record","payload":{"canonical_record":{"source":{"id":"1912.06088","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T17:26:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"06072c03dad2437efdef1c5e00a2f6ad82463aa0660253b3133c286bf46d203f","abstract_canon_sha256":"9db490dc2645d6ec044d34d0a6d99d6a0dcb2ed4ac2b9a6581b22e5d922fb5cf"},"schema_version":"1.0"},"canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:55.327247Z","signature_b64":"n+9gWXlBPwrjE9AY2k7u+rNb5Wh2oLi4XrISZlLnOlKPSjFR+UN7vYUTDkLmZW8PInTeCKM5lmKpwKuRYN3cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5dfe766fd78f27f44375b5e3bf29a8a485bbe2c17501fc0488c4bd71afc591d","last_reissued_at":"2026-07-05T01:39:55.326831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:55.326831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.06088","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:39:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MLLL61GCiejPGBt0dhRVKXIKurXf+dxbfR2IVKDzUtH+ooFIb9DT5wRB+aqUJ7OJ8mQUnGhS4FyKv38ptlVHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:35:13.895015Z"},"content_sha256":"ac2706adc45a3411218cfa02cc8c8b8adafb9fa1e52decd163a1db29a6806ab9","schema_version":"1.0","event_id":"sha256:ac2706adc45a3411218cfa02cc8c8b8adafb9fa1e52decd163a1db29a6806ab9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6XP6OZX5PDZH6RBXLNPDX4U2RJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Reach Goals via Iterated Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ashwin Reddy, Benjamin Eysenbach, Coline Devin, Dibya Ghosh, Justin Fu, Sergey Levine","submitted_at":"2019-12-12T17:26:47Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06088","kind":"arxiv","version":4},"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/1912.06088/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":"2026-07-05T01:39:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALz9zbVIPdxO5CejX7t+c01b0SQ5X2/JMJEjCQgc3wH3T+uxiaNYbFNqgKgsRM0zGdmZmiqzkN2rjLcXMK8kAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:35:13.895560Z"},"content_sha256":"0a373afa952b322a84ef440c7ea8b9f66c4cb744b5667db03c3d8337fcceb07b","schema_version":"1.0","event_id":"sha256:0a373afa952b322a84ef440c7ea8b9f66c4cb744b5667db03c3d8337fcceb07b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/bundle.json","state_url":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/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":"2026-08-07T18:35:13Z","links":{"resolver":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ","bundle":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/bundle.json","state":"https://pith.science/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XP6OZX5PDZH6RBXLNPDX4U2RJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6msR78UmK/N+4KbOwoVWpDY5x+xBP2kRQswhA0W0ntHWuwwcAdJ4et1XeVdAwycOzl3x4jNW7uleHUh7T9PDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:35:13.900340Z","bundle_sha256":"ea6b526dd8b8afc7a38e7fdd4b04683bc92b9c9925e4589c1189fc47cdb3096a"}}