{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDTDOD7S4Y26CRAMNZ2JS5QR4A","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":"2a02e12e17ef22a31595e8de522995d604e5f364d6a10e5dcf5a6fe9e08bd76a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T03:59:13Z","title_canon_sha256":"1f9c78ec3403b425b640ea11905527268787aacb241b60f5cea1d1dc5c746e7e"},"schema_version":"1.0","source":{"id":"2405.16809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16809","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16809v1","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16809","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_12","alias_value":"NDTDOD7S4Y26","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_16","alias_value":"NDTDOD7S4Y26CRAM","created_at":"2026-07-05T08:23:35Z"},{"alias_kind":"pith_short_8","alias_value":"NDTDOD7S","created_at":"2026-07-05T08:23:35Z"}],"graph_snapshots":[{"event_id":"sha256:d1391b2a5d1f478c9ad097d340309f97df1537afab3957b9d7b2c395d4adea95","target":"graph","created_at":"2026-07-05T08:23:35Z","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/2405.16809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^\\pi$-realizability assumption, where the action-value function of every policy is linear with respect to a given $d$-dimensional feature function. The hope in this setting is that learning a good policy will be possible without requiring a sample size that scales with the number of states in the MDP. Foster et al. [2021] have shown this to be impossible even under $\\textit{concentrability}$, a data coverage assumption where a coefficient $C_\\text{conc}$ bounds the extent to which","authors_text":"Csaba Szepesv\\'ari, Gell\\'ert Weisz, Volodymyr Tkachuk","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T03:59:13Z","title":"Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\\pi$-Realizability and Concentrability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16809","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":"sha256:50c42ad5707dcd1aba38e980e5d7f0eccecc3fa901346d746ca814a44fe5c810","target":"record","created_at":"2026-07-05T08:23:35Z","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":"2a02e12e17ef22a31595e8de522995d604e5f364d6a10e5dcf5a6fe9e08bd76a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T03:59:13Z","title_canon_sha256":"1f9c78ec3403b425b640ea11905527268787aacb241b60f5cea1d1dc5c746e7e"},"schema_version":"1.0","source":{"id":"2405.16809","kind":"arxiv","version":1}},"canonical_sha256":"68e6370ff2e635e1440c6e74997611e01ebee2debd8b6223349a01278ea28534","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68e6370ff2e635e1440c6e74997611e01ebee2debd8b6223349a01278ea28534","first_computed_at":"2026-07-05T08:23:35.758285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:35.758285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JWYFSQunbP6ZpAyiQH3y53EbfxTbo0dX+aAIgaml5qAhcPoyQ67BV5C8HpkCPMbx+/ZTSfKD3YntxTHQTx31AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:35.758839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50c42ad5707dcd1aba38e980e5d7f0eccecc3fa901346d746ca814a44fe5c810","sha256:d1391b2a5d1f478c9ad097d340309f97df1537afab3957b9d7b2c395d4adea95"],"state_sha256":"c72fc118fe194d6bee3510a5a4f9f24c49c2f660a7c0b60430cb62038d157ca9"}