{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7C6GE53MYNZXWIQ4FYPMFCJFA6","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":"d05425c73c2f83e50b0b5b135d4a51e529151b02faaa689350dcb5d7cb69478b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-09-03T16:25:45Z","title_canon_sha256":"cb0d1550a96ce75bef0d405ae75e476eba219aa4bf0c592a29c980971a8875ed"},"schema_version":"1.0","source":{"id":"2509.03456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03456","created_at":"2026-06-02T03:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03456v2","created_at":"2026-06-02T03:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03456","created_at":"2026-06-02T03:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"7C6GE53MYNZX","created_at":"2026-06-02T03:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"7C6GE53MYNZXWIQ4","created_at":"2026-06-02T03:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"7C6GE53M","created_at":"2026-06-02T03:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:2f0ec9371cd46870e9ead5f5c68cb206f8de06f2ece3b6869e8341c25f56658c","target":"graph","created_at":"2026-06-02T03:04:34Z","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/2509.03456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that better estimators inherently yield superior policies. Although theoretically justified, this estimator-centric approach neglects a critical practical obstacle: challenging optimization landscapes. In this paper, we provide theoretical insights and empirical evidence showing that current OPL methods encounter severe optimization issues, particularly as the action ","authors_text":"Imad Aouali, Otmane Sakhi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-09-03T16:25:45Z","title":"Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03456","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":"sha256:6f45cbe29fe9e40cd3964906b240063b872f5aa800e033be0b1a2f99cd24a4ae","target":"record","created_at":"2026-06-02T03:04:34Z","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":"d05425c73c2f83e50b0b5b135d4a51e529151b02faaa689350dcb5d7cb69478b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-09-03T16:25:45Z","title_canon_sha256":"cb0d1550a96ce75bef0d405ae75e476eba219aa4bf0c592a29c980971a8875ed"},"schema_version":"1.0","source":{"id":"2509.03456","kind":"arxiv","version":2}},"canonical_sha256":"f8bc62776cc3737b221c2e1ec28925079de79d53c16d6c6a06384cea9f5349d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8bc62776cc3737b221c2e1ec28925079de79d53c16d6c6a06384cea9f5349d7","first_computed_at":"2026-06-02T03:04:34.058168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:34.058168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0b32rGwTvl02W3wCDR5j4c2W7+2kdEQY5MOKh2iLIRRkRaVgHYMz3I8QSwDNwQHF3MQ43cuhKpDiyS4QS94qBw==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:34.058702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f45cbe29fe9e40cd3964906b240063b872f5aa800e033be0b1a2f99cd24a4ae","sha256:2f0ec9371cd46870e9ead5f5c68cb206f8de06f2ece3b6869e8341c25f56658c"],"state_sha256":"0cbdebd493dfa30712452a8d23baf5605557f45882e713413b964761a58db439"}