{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KSNFZQFTORKIQVOYOHFJ5NEJDY","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":"5be3e9f92b1515591cfa8ac0ac8ca1ff368d0b8d948694d066f58f986ab32dcf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-09T03:01:13Z","title_canon_sha256":"cdf6dd81780449e144754d60362457387adfab2e6326f0ee63f37a32ff5da9b5"},"schema_version":"1.0","source":{"id":"2402.06151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06151","created_at":"2026-07-05T07:43:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06151v1","created_at":"2026-07-05T07:43:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06151","created_at":"2026-07-05T07:43:19Z"},{"alias_kind":"pith_short_12","alias_value":"KSNFZQFTORKI","created_at":"2026-07-05T07:43:19Z"},{"alias_kind":"pith_short_16","alias_value":"KSNFZQFTORKIQVOY","created_at":"2026-07-05T07:43:19Z"},{"alias_kind":"pith_short_8","alias_value":"KSNFZQFT","created_at":"2026-07-05T07:43:19Z"}],"graph_snapshots":[{"event_id":"sha256:7bc0b9f79869f427657dd83242ff67869e2d3d9181e00d642eadd70580aeac51","target":"graph","created_at":"2026-07-05T07:43:19Z","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/2402.06151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study off-policy learning (OPL) of contextual bandit policies in large discrete action spaces where existing methods -- most of which rely crucially on reward-regression models or importance-weighted policy gradients -- fail due to excessive bias or variance. To overcome these issues in OPL, we propose a novel two-stage algorithm, called Policy Optimization via Two-Stage Policy Decomposition (POTEC). It leverages clustering in the action space and learns two different policies via policy- and regression-based approaches, respectively. In particular, we derive a novel low-variance gradient e","authors_text":"Jihan Yao, Thorsten Joachims, Yuta Saito","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-09T03:01:13Z","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06151","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":"sha256:90fd7638b3e0defd52616184f0415583d8af41a8885a8c6c3dc933c2355f856f","target":"record","created_at":"2026-07-05T07:43:19Z","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":"5be3e9f92b1515591cfa8ac0ac8ca1ff368d0b8d948694d066f58f986ab32dcf","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-02-09T03:01:13Z","title_canon_sha256":"cdf6dd81780449e144754d60362457387adfab2e6326f0ee63f37a32ff5da9b5"},"schema_version":"1.0","source":{"id":"2402.06151","kind":"arxiv","version":1}},"canonical_sha256":"549a5cc0b374548855d871ca9eb4891e27c66de9f491fd8c8eea97bd7d2e2e8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"549a5cc0b374548855d871ca9eb4891e27c66de9f491fd8c8eea97bd7d2e2e8e","first_computed_at":"2026-07-05T07:43:19.425775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:19.425775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bg9EsTkvIFFvncFuNYKvoAQVPKbwwsdGX3z0CKhqu72eS/hilBDfUao7yC8hXqE7EXICc1UUTCZ2cSaUzFG/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:19.426210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90fd7638b3e0defd52616184f0415583d8af41a8885a8c6c3dc933c2355f856f","sha256:7bc0b9f79869f427657dd83242ff67869e2d3d9181e00d642eadd70580aeac51"],"state_sha256":"b2130ec728494d47e20635f089699ffe3a928a97ea4d09a84a689342b986f5fe"}