{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZSQYMFMZQFFSSGK2LP2BZRYIA","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":"d3214cf2a28cb33a29a4581c44bedadb8a459f0d5400e3ca3eaa944e995c1f5a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T16:32:14Z","title_canon_sha256":"3e4c2512fca0627269c8174e02c47864677010b08b5f4f165b2acb359d2822eb"},"schema_version":"1.0","source":{"id":"2406.03434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03434","created_at":"2026-07-05T08:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03434v1","created_at":"2026-07-05T08:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03434","created_at":"2026-07-05T08:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"DZSQYMFMZQFF","created_at":"2026-07-05T08:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"DZSQYMFMZQFFSSGK","created_at":"2026-07-05T08:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"DZSQYMFM","created_at":"2026-07-05T08:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:493c296f5c4423b05a7a7e390e18787046d48914b402b14fb4d803756890b84e","target":"graph","created_at":"2026-07-05T08:27:56Z","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/2406.03434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this method can produce an estimator with a high variance. A common solution is to regularize the importance weights and learn the policy by minimizing an estimator with penalties derived from generalization bounds specific to the estimator. This approach, known as pessimism, has gained recent attention but lacks a unified framework for analysis. To address this gap, we introduce a comprehensive PAC-Bayesian framework to exami","authors_text":"Anna Korba, David Rohde, Imad Aouali, Victor-Emmanuel Brunel","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T16:32:14Z","title":"Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03434","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:b1d33099824846023151e6f0e8f94db33f8128fd0122ef8336c22d066a7d5dcd","target":"record","created_at":"2026-07-05T08:27:56Z","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":"d3214cf2a28cb33a29a4581c44bedadb8a459f0d5400e3ca3eaa944e995c1f5a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T16:32:14Z","title_canon_sha256":"3e4c2512fca0627269c8174e02c47864677010b08b5f4f165b2acb359d2822eb"},"schema_version":"1.0","source":{"id":"2406.03434","kind":"arxiv","version":1}},"canonical_sha256":"1e650c30accc0a5948cad2dfa0e638403e3eda6ceb07800481da1666b721eeba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e650c30accc0a5948cad2dfa0e638403e3eda6ceb07800481da1666b721eeba","first_computed_at":"2026-07-05T08:27:56.749252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:56.749252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XXig0WjUGXaQScjvHbym9L0i7DYYtd72gae2vydsm51ipm80Fqo54o9q5exw1DnZ3D+YXytXDiUrk8RlH6VWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:56.749682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1d33099824846023151e6f0e8f94db33f8128fd0122ef8336c22d066a7d5dcd","sha256:493c296f5c4423b05a7a7e390e18787046d48914b402b14fb4d803756890b84e"],"state_sha256":"b1839fd9c8857776f4792e9d792317f56788fe7ee25f2252d051f350a95c061d"}