{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5VZUL5XRFWM2O2ZQFFVA2RANYI","short_pith_number":"pith:5VZUL5XR","schema_version":"1.0","canonical_sha256":"ed7345f6f12d99a76b30296a0d440dc21b5133006cff20941ff838574e1707ee","source":{"kind":"arxiv","id":"2302.03770","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Hanlin Zhu","submitted_at":"2023-02-07T22:04:55Z","abstract_excerpt":"Goal-conditioned reinforcement learning (GCRL) refers to learning general-purpose skills that aim to reach diverse goals. In particular, offline GCRL only requires purely pre-collected datasets to perform training tasks without additional interactions with the environment. Although offline GCRL has become increasingly prevalent and many previous works have demonstrated its empirical success, the theoretical understanding of efficient offline GCRL algorithms is not well established, especially when the state space is huge and the offline dataset only covers the policy we aim to learn. In this p"},"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":"2302.03770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T22:04:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a666a133fca60ffdf9cdce9a004a7935a071756fad16fd449817d1b1e5c602ea","abstract_canon_sha256":"fcc179891cbb25c6401ccbba9a453f6d551b0b77e96eba9ae06bd8b919972d27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:51.022635Z","signature_b64":"WIqyv3GufZOykenuM5fsks+QVRdNXFo1tyIuQfKv0voekxJRejEgs69XS5ghTqjlzV2dtZSZMw9v4WC3MIS6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed7345f6f12d99a76b30296a0d440dc21b5133006cff20941ff838574e1707ee","last_reissued_at":"2026-07-05T06:59:51.022101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:51.022101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Hanlin Zhu","submitted_at":"2023-02-07T22:04:55Z","abstract_excerpt":"Goal-conditioned reinforcement learning (GCRL) refers to learning general-purpose skills that aim to reach diverse goals. In particular, offline GCRL only requires purely pre-collected datasets to perform training tasks without additional interactions with the environment. Although offline GCRL has become increasingly prevalent and many previous works have demonstrated its empirical success, the theoretical understanding of efficient offline GCRL algorithms is not well established, especially when the state space is huge and the offline dataset only covers the policy we aim to learn. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03770","kind":"arxiv","version":2},"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/2302.03770/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":"2302.03770","created_at":"2026-07-05T06:59:51.022157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03770v2","created_at":"2026-07-05T06:59:51.022157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03770","created_at":"2026-07-05T06:59:51.022157+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VZUL5XRFWM2","created_at":"2026-07-05T06:59:51.022157+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VZUL5XRFWM2O2ZQ","created_at":"2026-07-05T06:59:51.022157+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VZUL5XR","created_at":"2026-07-05T06:59:51.022157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24842","citing_title":"World Models in Pieces: Structural Certification for General Agents","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI","json":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI.json","graph_json":"https://pith.science/api/pith-number/5VZUL5XRFWM2O2ZQFFVA2RANYI/graph.json","events_json":"https://pith.science/api/pith-number/5VZUL5XRFWM2O2ZQFFVA2RANYI/events.json","paper":"https://pith.science/paper/5VZUL5XR"},"agent_actions":{"view_html":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI","download_json":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI.json","view_paper":"https://pith.science/paper/5VZUL5XR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03770&json=true","fetch_graph":"https://pith.science/api/pith-number/5VZUL5XRFWM2O2ZQFFVA2RANYI/graph.json","fetch_events":"https://pith.science/api/pith-number/5VZUL5XRFWM2O2ZQFFVA2RANYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI/action/storage_attestation","attest_author":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI/action/author_attestation","sign_citation":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI/action/citation_signature","submit_replication":"https://pith.science/pith/5VZUL5XRFWM2O2ZQFFVA2RANYI/action/replication_record"}},"created_at":"2026-07-05T06:59:51.022157+00:00","updated_at":"2026-07-05T06:59:51.022157+00:00"}