{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5IRK7JBGRJNGJL5EVHWXVFNAGA","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":"bd24584cc858eeba8fda97992f2007e5d4ee81f1bb6413408478b8353961612c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T07:55:02Z","title_canon_sha256":"356cffcc511dae48aa8156d8c9a5c2abd48d5c7bdeb39d438d083ecff167cf64"},"schema_version":"1.0","source":{"id":"2302.14372","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14372","created_at":"2026-07-05T06:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14372v2","created_at":"2026-07-05T06:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14372","created_at":"2026-07-05T06:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"5IRK7JBGRJNG","created_at":"2026-07-05T06:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"5IRK7JBGRJNGJL5E","created_at":"2026-07-05T06:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"5IRK7JBG","created_at":"2026-07-05T06:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:e5edb5b60b0740ee691992147eae02a9b15c807aadb9be2c4289d52fbd4c044a","target":"graph","created_at":"2026-07-05T06:02:32Z","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/2302.14372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents can leverage batches of previously collected data to extract a reasonable control policy. An emerging issue in this offline RL setting, however, is that the bootstrapping update underlying many of our methods suffers from insufficient action-coverage: standard max operator may select a maximal action that has not been seen in the dataset. Bootstrapping from these inaccurate values can lead to overestimation and even divergence. There are a growing number of methods that attempt to approximate an \\emph{in-sample} max, that only uses actions well-covered by the","authors_text":"Adam White, Chenjun Xiao, Han Wang, Martha White, Yangchen Pan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T07:55:02Z","title":"The In-Sample Softmax for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14372","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:ceacb692fc19889f6e73396c704c76f446d4c5a08e66c6f5f69012e8994a780f","target":"record","created_at":"2026-07-05T06:02:32Z","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":"bd24584cc858eeba8fda97992f2007e5d4ee81f1bb6413408478b8353961612c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T07:55:02Z","title_canon_sha256":"356cffcc511dae48aa8156d8c9a5c2abd48d5c7bdeb39d438d083ecff167cf64"},"schema_version":"1.0","source":{"id":"2302.14372","kind":"arxiv","version":2}},"canonical_sha256":"ea22afa4268a5a64afa4a9ed7a95a03015a3f3e0173b690515b12e84f6ceb77f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea22afa4268a5a64afa4a9ed7a95a03015a3f3e0173b690515b12e84f6ceb77f","first_computed_at":"2026-07-05T06:02:32.598858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:32.598858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/xToBuTgMZQI4qhTcLLpc52bbgfhwJc5F+chqUBOvZeOVOJ7BpVEcicTigHXEe5c5HRsbDwWW/gKwEpblEsABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:32.599267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14372","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceacb692fc19889f6e73396c704c76f446d4c5a08e66c6f5f69012e8994a780f","sha256:e5edb5b60b0740ee691992147eae02a9b15c807aadb9be2c4289d52fbd4c044a"],"state_sha256":"2f34ee7eec12c91c86f0d8e0e0831c12f7efb6f0cc837e879ebf5124771a849d"}