{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5IRK7JBGRJNGJL5EVHWXVFNAGA","short_pith_number":"pith:5IRK7JBG","canonical_record":{"source":{"id":"2302.14372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T07:55:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"356cffcc511dae48aa8156d8c9a5c2abd48d5c7bdeb39d438d083ecff167cf64","abstract_canon_sha256":"bd24584cc858eeba8fda97992f2007e5d4ee81f1bb6413408478b8353961612c"},"schema_version":"1.0"},"canonical_sha256":"ea22afa4268a5a64afa4a9ed7a95a03015a3f3e0173b690515b12e84f6ceb77f","source":{"kind":"arxiv","id":"2302.14372","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5IRK7JBGRJNGJL5EVHWXVFNAGA","target":"record","payload":{"canonical_record":{"source":{"id":"2302.14372","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T07:55:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"356cffcc511dae48aa8156d8c9a5c2abd48d5c7bdeb39d438d083ecff167cf64","abstract_canon_sha256":"bd24584cc858eeba8fda97992f2007e5d4ee81f1bb6413408478b8353961612c"},"schema_version":"1.0"},"canonical_sha256":"ea22afa4268a5a64afa4a9ed7a95a03015a3f3e0173b690515b12e84f6ceb77f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:32.599267Z","signature_b64":"/xToBuTgMZQI4qhTcLLpc52bbgfhwJc5F+chqUBOvZeOVOJ7BpVEcicTigHXEe5c5HRsbDwWW/gKwEpblEsABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea22afa4268a5a64afa4a9ed7a95a03015a3f3e0173b690515b12e84f6ceb77f","last_reissued_at":"2026-07-05T06:02:32.598858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:32.598858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.14372","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":"2026-07-05T06:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vglmsqiLmDLpIOHcV7kPwZkjQ8pOq8QgnP+XxCC1LXP3xlrlJscf+UBQ3/GfMpZr1EWq/HZRdy7QUl1RCvJBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:58.564326Z"},"content_sha256":"ceacb692fc19889f6e73396c704c76f446d4c5a08e66c6f5f69012e8994a780f","schema_version":"1.0","event_id":"sha256:ceacb692fc19889f6e73396c704c76f446d4c5a08e66c6f5f69012e8994a780f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5IRK7JBGRJNGJL5EVHWXVFNAGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The In-Sample Softmax for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Chenjun Xiao, Han Wang, Martha White, Yangchen Pan","submitted_at":"2023-02-28T07:55:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14372","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/2302.14372/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":"2026-07-05T06:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFdINv2FMqJhkDOurhubUCMndhl4fp6Mjpa3tFtm+nfO49at1kTUXN7YLap+mP+MkY0cnO4v1Nb/QmAcPoyhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:58.564778Z"},"content_sha256":"e5edb5b60b0740ee691992147eae02a9b15c807aadb9be2c4289d52fbd4c044a","schema_version":"1.0","event_id":"sha256:e5edb5b60b0740ee691992147eae02a9b15c807aadb9be2c4289d52fbd4c044a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/bundle.json","state_url":"https://pith.science/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/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":"2026-08-07T01:20:58Z","links":{"resolver":"https://pith.science/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA","bundle":"https://pith.science/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/bundle.json","state":"https://pith.science/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IRK7JBGRJNGJL5EVHWXVFNAGA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvCAtVYLHUqAdQVfU6BuOsH+seWzM+Htl+19aQXU/AdCDFMAv7mUi4j2mtNRwK/j0aN+NJuCUWOzDrpiEZ4tAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:20:58.572575Z","bundle_sha256":"c0694e5b59aaa9b61904fe82fd1e107a83bc4a47600e75eaaa9fba000b46304e"}}