{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4IR44P6O53ZCG6UYWGDRRBALST","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":"aace12237179ab34dd5e8c8216ff7b8ee7409d1980dcb442d386efc421b703d6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T01:00:01Z","title_canon_sha256":"f66cbda926ee387bc240a34178db49861650b6e797da47fcfd985309d62791d0"},"schema_version":"1.0","source":{"id":"2310.15433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15433","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15433v1","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15433","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"4IR44P6O53ZC","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"4IR44P6O53ZCG6UY","created_at":"2026-07-05T07:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"4IR44P6O","created_at":"2026-07-05T07:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:f40924a66c42c378452b3a053fb122c4a74a4c519670306059eba262f7e0fca2","target":"graph","created_at":"2026-07-05T07:04:25Z","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/2310.15433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target policy that we aim to evaluate. Typically, techniques for correcting distribution shift involve some form of importance sampling. This approach results in unbiased value estimation but often comes with the trade-off of high variance, even in the simpler case of one-step contextual bandits. Furthermore, importance sampling relies on the common support assumptio","authors_text":"Dawen Liang, Julian McAuley, Lequn Wang, Nathan Kallus, Noveen Sachdeva","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T01:00:01Z","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15433","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":"sha256:620e2dd5de0dcbf3689b69ceabfc46fd0c4ff37e0b907db65cb5495ead5b729e","target":"record","created_at":"2026-07-05T07:04:25Z","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":"aace12237179ab34dd5e8c8216ff7b8ee7409d1980dcb442d386efc421b703d6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T01:00:01Z","title_canon_sha256":"f66cbda926ee387bc240a34178db49861650b6e797da47fcfd985309d62791d0"},"schema_version":"1.0","source":{"id":"2310.15433","kind":"arxiv","version":1}},"canonical_sha256":"e223ce3fceeef2237a98b18718840b94d23569881c475f5b67d43b899dabf827","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e223ce3fceeef2237a98b18718840b94d23569881c475f5b67d43b899dabf827","first_computed_at":"2026-07-05T07:04:25.925593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:25.925593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hPxAHc3rSQ62T4iTSDSEpAAz+HfL4Rjd/iFckG4H7USKMM5J4CKJv0vrDbdvEQ7q66UeIt49PJ1MUEIXKCu1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:25.925969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:620e2dd5de0dcbf3689b69ceabfc46fd0c4ff37e0b907db65cb5495ead5b729e","sha256:f40924a66c42c378452b3a053fb122c4a74a4c519670306059eba262f7e0fca2"],"state_sha256":"0777afa7090e707b6dee7577bd1fc4f39d608999468b0f819eeb6f1122795101"}