{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TD7DHQ2GDFSKZIVGGUAUA7YCFM","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":"9b86cb8992bff3bcfd61c2be76b69a7b4fa3ca469bcf468371c9120c93239aeb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T00:17:36Z","title_canon_sha256":"e61789c27cfdb8eb0d4dfe5135f9543151f8d79efdce6d956862af9351988d4a"},"schema_version":"1.0","source":{"id":"2307.11949","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11949","created_at":"2026-07-05T07:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11949v4","created_at":"2026-07-05T07:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11949","created_at":"2026-07-05T07:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"TD7DHQ2GDFSK","created_at":"2026-07-05T07:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"TD7DHQ2GDFSKZIVG","created_at":"2026-07-05T07:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"TD7DHQ2G","created_at":"2026-07-05T07:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:c39ca605f149313563fc6c48367db7773447f997bde4ac13cfcdeae1ddeffc61","target":"graph","created_at":"2026-07-05T07:54:02Z","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/2307.11949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pre-training has recently become the bedrock for computer vision and natural language processing. In reinforcement learning (RL), goal-conditioned RL can potentially provide an analogous self-supervised approach for making use of large quantities of unlabeled (reward-free) data. However, building effective algorithms for goal-conditioned RL that can learn directly from diverse offline data is challenging, because it is hard to accurately estimate the exact value function for faraway goals. Nonetheless, goal-reaching problems exhibit structure, such that reaching distant goals enta","authors_text":"Benjamin Eysenbach, Dibya Ghosh, Seohong Park, Sergey Levine","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T00:17:36Z","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11949","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":"sha256:6b9bc081686cc22fb22ea9dc0fd4097f0dbe0fd09c5896cf62fd00131054c376","target":"record","created_at":"2026-07-05T07:54:02Z","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":"9b86cb8992bff3bcfd61c2be76b69a7b4fa3ca469bcf468371c9120c93239aeb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T00:17:36Z","title_canon_sha256":"e61789c27cfdb8eb0d4dfe5135f9543151f8d79efdce6d956862af9351988d4a"},"schema_version":"1.0","source":{"id":"2307.11949","kind":"arxiv","version":4}},"canonical_sha256":"98fe33c3461964aca2a63501407f022b3b948244759f735f3ea90dec7eb2f58a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98fe33c3461964aca2a63501407f022b3b948244759f735f3ea90dec7eb2f58a","first_computed_at":"2026-07-05T07:54:02.409251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:02.409251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nq8jjvuhXElqqwwpboSKZBa085B82nYq+MHEHgwKfMJwhBUp3z4hkppj2LMgMhi9KocTyOgzSPINlEGfLLfaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:02.409703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11949","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b9bc081686cc22fb22ea9dc0fd4097f0dbe0fd09c5896cf62fd00131054c376","sha256:c39ca605f149313563fc6c48367db7773447f997bde4ac13cfcdeae1ddeffc61"],"state_sha256":"469e15292949ced67da7342d491db08cd5b773bdc63a7c3fc0eba89a86f1d93a"}