{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HXOEWEHA464ZJXD2ERYVKAODJ6","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":"42c60c7b8e21c03ff863a6f44b0e3c35c83798be248c7c3b6a4374c463ddf596","cross_cats_sorted":["cs.AI","cs.CC","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T04:48:35Z","title_canon_sha256":"82688a34f78f7b29be04e0f569cf4d1d0e1719359c3287cee78b298f338e3700"},"schema_version":"1.0","source":{"id":"2202.05444","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.05444","created_at":"2026-07-05T04:36:47Z"},{"alias_kind":"arxiv_version","alias_value":"2202.05444v2","created_at":"2026-07-05T04:36:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05444","created_at":"2026-07-05T04:36:47Z"},{"alias_kind":"pith_short_12","alias_value":"HXOEWEHA464Z","created_at":"2026-07-05T04:36:47Z"},{"alias_kind":"pith_short_16","alias_value":"HXOEWEHA464ZJXD2","created_at":"2026-07-05T04:36:47Z"},{"alias_kind":"pith_short_8","alias_value":"HXOEWEHA","created_at":"2026-07-05T04:36:47Z"}],"graph_snapshots":[{"event_id":"sha256:e1729dc83f16f3f0516e22dc01104b171894a65e08f83dc3cb2db6bfff1052b1","target":"graph","created_at":"2026-07-05T04:36:47Z","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/2202.05444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with function approximation has recently achieved tremendous results in applications with large state spaces. This empirical success has motivated a growing body of theoretical work proposing necessary and sufficient conditions under which efficient reinforcement learning is possible. From this line of work, a remarkably simple minimal sufficient condition has emerged for sample efficient reinforcement learning: MDPs with optimal value function $V^*$ and $Q^*$ linear in some known low-dimensional features. In this setting, recent works have designed sample efficient algo","authors_text":"Daniel Kane, Gaurav Mahajan, Shachar Lovett, Sihan Liu","cross_cats":["cs.AI","cs.CC","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T04:48:35Z","title":"Computational-Statistical Gaps in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05444","kind":"arxiv","version":2},"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":"sha256:9699086526d4005a29b5f1a0d7ddb305f919f0b1dd7ee7c0e5d78c8e2622796f","target":"record","created_at":"2026-07-05T04:36:47Z","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":"42c60c7b8e21c03ff863a6f44b0e3c35c83798be248c7c3b6a4374c463ddf596","cross_cats_sorted":["cs.AI","cs.CC","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T04:48:35Z","title_canon_sha256":"82688a34f78f7b29be04e0f569cf4d1d0e1719359c3287cee78b298f338e3700"},"schema_version":"1.0","source":{"id":"2202.05444","kind":"arxiv","version":2}},"canonical_sha256":"3ddc4b10e0e7b994dc7a24715501c34fb1f3945747e81811e55a34ddc9149c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ddc4b10e0e7b994dc7a24715501c34fb1f3945747e81811e55a34ddc9149c20","first_computed_at":"2026-07-05T04:36:47.366746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:47.366746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KLFZFii+l33+aNkzJ0AtDKl5TTsoMtmNMjl3W25Y/lOqVlmMs2AMycPn8uZ/NQu+21OesNHskgMkPFlOekCcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:47.367297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.05444","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9699086526d4005a29b5f1a0d7ddb305f919f0b1dd7ee7c0e5d78c8e2622796f","sha256:e1729dc83f16f3f0516e22dc01104b171894a65e08f83dc3cb2db6bfff1052b1"],"state_sha256":"0bc76f7c220f8c5004cd478311ba2f73d0493e512a2d53f957b618365b563e5c"}