{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:J7GPFHJDJUBB3YCYHD4L53LSIS","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":"772fba2f8b0591df474e70c605d6044e87ee3e9e0fb56e9f96f521f1a705435d","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:32:13Z","title_canon_sha256":"7aeab13797028b480ff1735c99877996b3d784ba8d58a3a210e7581fe72248d1"},"schema_version":"1.0","source":{"id":"2010.11895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11895","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11895v1","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11895","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_12","alias_value":"J7GPFHJDJUBB","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_16","alias_value":"J7GPFHJDJUBB3YCY","created_at":"2026-07-05T01:45:21Z"},{"alias_kind":"pith_short_8","alias_value":"J7GPFHJD","created_at":"2026-07-05T01:45:21Z"}],"graph_snapshots":[{"event_id":"sha256:de08a763d639a38a19080c6f30d9f6d94979fc36e28da69876ca6a6d20fe15a3","target":"graph","created_at":"2026-07-05T01:45:21Z","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/2010.11895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation methods (to deal with the curse of dimensionality) can provide a means to help alleviate the excessive sample complexity burden in modern sequential decision making problems. However, the extent to which this broader approach can be effective is not well understood, where the literature largely consists of sufficient conditions.\n  This work focuses on the basic qu","authors_text":"Dean P. Foster, Ruosong Wang, Sham M. Kakade","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:32:13Z","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11895","kind":"arxiv","version":1},"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":"sha256:36c6d1544cb688ecd934313fe1601befa8f1885f8d836c7e631ff9f94730938e","target":"record","created_at":"2026-07-05T01:45:21Z","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":"772fba2f8b0591df474e70c605d6044e87ee3e9e0fb56e9f96f521f1a705435d","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:32:13Z","title_canon_sha256":"7aeab13797028b480ff1735c99877996b3d784ba8d58a3a210e7581fe72248d1"},"schema_version":"1.0","source":{"id":"2010.11895","kind":"arxiv","version":1}},"canonical_sha256":"4fccf29d234d021de05838f8beed7244bdaa31a879e46641be32967b339fe005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fccf29d234d021de05838f8beed7244bdaa31a879e46641be32967b339fe005","first_computed_at":"2026-07-05T01:45:21.967649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:21.967649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FQ2aWXK1uNhK9M/hwnxPvC+JckvpocDbZqDWBlOaa3C6dj2ZHAUoLZDcNMStRwXgOixA3t9K997f8gWNVL2/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:21.967997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36c6d1544cb688ecd934313fe1601befa8f1885f8d836c7e631ff9f94730938e","sha256:de08a763d639a38a19080c6f30d9f6d94979fc36e28da69876ca6a6d20fe15a3"],"state_sha256":"62a1d68d9fd4fbda0cfa45d1e06b223370c3274313384d5dc9f4aa0e04e389b6"}