{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TD7DHQ2GDFSKZIVGGUAUA7YCFM","short_pith_number":"pith:TD7DHQ2G","schema_version":"1.0","canonical_sha256":"98fe33c3461964aca2a63501407f022b3b948244759f735f3ea90dec7eb2f58a","source":{"kind":"arxiv","id":"2307.11949","version":4},"attestation_state":"computed","paper":{"title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Dibya Ghosh, Seohong Park, Sergey Levine","submitted_at":"2023-07-22T00:17:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.11949","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-22T00:17:36Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e61789c27cfdb8eb0d4dfe5135f9543151f8d79efdce6d956862af9351988d4a","abstract_canon_sha256":"9b86cb8992bff3bcfd61c2be76b69a7b4fa3ca469bcf468371c9120c93239aeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:02.409703Z","signature_b64":"nq8jjvuhXElqqwwpboSKZBa085B82nYq+MHEHgwKfMJwhBUp3z4hkppj2LMgMhi9KocTyOgzSPINlEGfLLfaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fe33c3461964aca2a63501407f022b3b948244759f735f3ea90dec7eb2f58a","last_reissued_at":"2026-07-05T07:54:02.409251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:02.409251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Dibya Ghosh, Seohong Park, Sergey Levine","submitted_at":"2023-07-22T00:17:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11949","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/2307.11949/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.11949","created_at":"2026-07-05T07:54:02.409309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11949v4","created_at":"2026-07-05T07:54:02.409309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11949","created_at":"2026-07-05T07:54:02.409309+00:00"},{"alias_kind":"pith_short_12","alias_value":"TD7DHQ2GDFSK","created_at":"2026-07-05T07:54:02.409309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TD7DHQ2GDFSKZIVG","created_at":"2026-07-05T07:54:02.409309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TD7DHQ2G","created_at":"2026-07-05T07:54:02.409309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04188","citing_title":"Dual Advantage Fields","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":156,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM","json":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM.json","graph_json":"https://pith.science/api/pith-number/TD7DHQ2GDFSKZIVGGUAUA7YCFM/graph.json","events_json":"https://pith.science/api/pith-number/TD7DHQ2GDFSKZIVGGUAUA7YCFM/events.json","paper":"https://pith.science/paper/TD7DHQ2G"},"agent_actions":{"view_html":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM","download_json":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM.json","view_paper":"https://pith.science/paper/TD7DHQ2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11949&json=true","fetch_graph":"https://pith.science/api/pith-number/TD7DHQ2GDFSKZIVGGUAUA7YCFM/graph.json","fetch_events":"https://pith.science/api/pith-number/TD7DHQ2GDFSKZIVGGUAUA7YCFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM/action/storage_attestation","attest_author":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM/action/author_attestation","sign_citation":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM/action/citation_signature","submit_replication":"https://pith.science/pith/TD7DHQ2GDFSKZIVGGUAUA7YCFM/action/replication_record"}},"created_at":"2026-07-05T07:54:02.409309+00:00","updated_at":"2026-07-05T07:54:02.409309+00:00"}