{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KQ42UFCRUPFC7IXYMLPORR6WM3","short_pith_number":"pith:KQ42UFCR","canonical_record":{"source":{"id":"2406.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:04:06Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"be5ed95a47f47b0162c9616a4f41cf2e1bdfba7b6c6b640ffd331fd1d7c0d145","abstract_canon_sha256":"9799769bc5139b43cf63ca645eeabfddf2c0e1bd12cb091b161f0bf6f4816c8b"},"schema_version":"1.0"},"canonical_sha256":"5439aa1451a3ca2fa2f862dee8c7d666d7c0ce74a1a95adfc0cfbf707e4eda94","source":{"kind":"arxiv","id":"2406.11686","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11686","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11686v2","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11686","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_12","alias_value":"KQ42UFCRUPFC","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_16","alias_value":"KQ42UFCRUPFC7IXY","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_8","alias_value":"KQ42UFCR","created_at":"2026-07-05T08:33:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KQ42UFCRUPFC7IXYMLPORR6WM3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11686","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:04:06Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"be5ed95a47f47b0162c9616a4f41cf2e1bdfba7b6c6b640ffd331fd1d7c0d145","abstract_canon_sha256":"9799769bc5139b43cf63ca645eeabfddf2c0e1bd12cb091b161f0bf6f4816c8b"},"schema_version":"1.0"},"canonical_sha256":"5439aa1451a3ca2fa2f862dee8c7d666d7c0ce74a1a95adfc0cfbf707e4eda94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:41.823579Z","signature_b64":"alcGlr6tiksO4hv0LudhDEfhMInmQxMSwJPhFdVci1XEtIro7ZdXMDYDNErjeFafl/CmRZbiqCAnlJLwuMetCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5439aa1451a3ca2fa2f862dee8c7d666d7c0ce74a1a95adfc0cfbf707e4eda94","last_reissued_at":"2026-07-05T08:33:41.823117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:41.823117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11686","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z4B/5mE1SNBpMorBdn8DpFhhtv8en56o19l0HgC3BzzYJHYdEUr25aNC9eLNwDY51cYfeqp64XGMQCvD2Yz9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:24:47.728482Z"},"content_sha256":"2d7bc8a639ffcb592b9eaec3236947c90756e69a0c5091145afc65ea21c50a25","schema_version":"1.0","event_id":"sha256:2d7bc8a639ffcb592b9eaec3236947c90756e69a0c5091145afc65ea21c50a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KQ42UFCRUPFC7IXYMLPORR6WM3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankur Moitra, Noah Golowich","submitted_at":"2024-06-17T16:04:06Z","abstract_excerpt":"In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates that linear value functions have linear Bellman backups with respect to the greedy policy. This assumption is natural in that it is essentially the minimal assumption required for value iteration to succeed. We give a computationally efficient algorithm which succeeds under a single-policy coverage condition on the dataset, namely which outputs a policy whose value is at least that of any policy which is well-covered "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11686","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/2406.11686/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVDhN3tik8dvhc9DsNkHtGnTDL0RJFyZFb5molZZ3bSzyf8bWAjg5/8VLwhiPl9fT0z816q1xUQF8TWrzrsmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:24:47.728859Z"},"content_sha256":"a35055d3f7dad5e50b4c66bb965ca826a299dda3086ae612bfd079a7caddc160","schema_version":"1.0","event_id":"sha256:a35055d3f7dad5e50b4c66bb965ca826a299dda3086ae612bfd079a7caddc160"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/bundle.json","state_url":"https://pith.science/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T13:24:47Z","links":{"resolver":"https://pith.science/pith/KQ42UFCRUPFC7IXYMLPORR6WM3","bundle":"https://pith.science/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/bundle.json","state":"https://pith.science/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQ42UFCRUPFC7IXYMLPORR6WM3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KQ42UFCRUPFC7IXYMLPORR6WM3","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":"9799769bc5139b43cf63ca645eeabfddf2c0e1bd12cb091b161f0bf6f4816c8b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:04:06Z","title_canon_sha256":"be5ed95a47f47b0162c9616a4f41cf2e1bdfba7b6c6b640ffd331fd1d7c0d145"},"schema_version":"1.0","source":{"id":"2406.11686","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11686","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11686v2","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11686","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_12","alias_value":"KQ42UFCRUPFC","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_16","alias_value":"KQ42UFCRUPFC7IXY","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_8","alias_value":"KQ42UFCR","created_at":"2026-07-05T08:33:41Z"}],"graph_snapshots":[{"event_id":"sha256:a35055d3f7dad5e50b4c66bb965ca826a299dda3086ae612bfd079a7caddc160","target":"graph","created_at":"2026-07-05T08:33:41Z","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/2406.11686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates that linear value functions have linear Bellman backups with respect to the greedy policy. This assumption is natural in that it is essentially the minimal assumption required for value iteration to succeed. We give a computationally efficient algorithm which succeeds under a single-policy coverage condition on the dataset, namely which outputs a policy whose value is at least that of any policy which is well-covered ","authors_text":"Ankur Moitra, Noah Golowich","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:04:06Z","title":"The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11686","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":"sha256:2d7bc8a639ffcb592b9eaec3236947c90756e69a0c5091145afc65ea21c50a25","target":"record","created_at":"2026-07-05T08:33:41Z","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":"9799769bc5139b43cf63ca645eeabfddf2c0e1bd12cb091b161f0bf6f4816c8b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T16:04:06Z","title_canon_sha256":"be5ed95a47f47b0162c9616a4f41cf2e1bdfba7b6c6b640ffd331fd1d7c0d145"},"schema_version":"1.0","source":{"id":"2406.11686","kind":"arxiv","version":2}},"canonical_sha256":"5439aa1451a3ca2fa2f862dee8c7d666d7c0ce74a1a95adfc0cfbf707e4eda94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5439aa1451a3ca2fa2f862dee8c7d666d7c0ce74a1a95adfc0cfbf707e4eda94","first_computed_at":"2026-07-05T08:33:41.823117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:41.823117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"alcGlr6tiksO4hv0LudhDEfhMInmQxMSwJPhFdVci1XEtIro7ZdXMDYDNErjeFafl/CmRZbiqCAnlJLwuMetCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:41.823579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11686","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d7bc8a639ffcb592b9eaec3236947c90756e69a0c5091145afc65ea21c50a25","sha256:a35055d3f7dad5e50b4c66bb965ca826a299dda3086ae612bfd079a7caddc160"],"state_sha256":"24c4a823d8a2070c6386c094f3d00af0a05bd0ddddf005aa47e07f81c3c6da3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4HAc39Et//D7UZydvZXrHjsv7HWmvnYEzXm92cflzHaCeKicUd/SmEzKqsQdxE3A+bthfL58P68IoQL1o+pCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:24:47.730808Z","bundle_sha256":"c57ae4ec418f2fb15a18a4a0d4ece91c53a0d6ddccb38adfaf7756dc58d0559a"}}