{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TSIQIDYJ6E4GCR2ICCI57C5VJK","short_pith_number":"pith:TSIQIDYJ","canonical_record":{"source":{"id":"2402.14664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T16:09:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"241db9696588eb9a3f9ad4dc2ab416b1c8e0d2db8310cf5f46d3409ba3c47c8d","abstract_canon_sha256":"83bce6b03b399771c64777b9945cffaf0beb0ab739edddf348debc44c26e8b26"},"schema_version":"1.0"},"canonical_sha256":"9c91040f09f1386147481091df8bb54a90857550a4a2e8ead0bb8474c394c7cd","source":{"kind":"arxiv","id":"2402.14664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14664","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14664v2","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14664","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"TSIQIDYJ6E4G","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"TSIQIDYJ6E4GCR2I","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"TSIQIDYJ","created_at":"2026-07-05T10:46:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TSIQIDYJ6E4GCR2ICCI57C5VJK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T16:09:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"241db9696588eb9a3f9ad4dc2ab416b1c8e0d2db8310cf5f46d3409ba3c47c8d","abstract_canon_sha256":"83bce6b03b399771c64777b9945cffaf0beb0ab739edddf348debc44c26e8b26"},"schema_version":"1.0"},"canonical_sha256":"9c91040f09f1386147481091df8bb54a90857550a4a2e8ead0bb8474c394c7cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:19.133234Z","signature_b64":"lRSDNH1cs1EaSbiQ/1GN7Q5wz/yl7g8PoA4U6IDqlDyMOiBu52ZdezZLtBZ+xnD2s0xVn3sM5CX5xAsftdq1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c91040f09f1386147481091df8bb54a90857550a4a2e8ead0bb8474c394c7cd","last_reissued_at":"2026-07-05T10:46:19.132743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:19.132743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14664","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":"2026-07-05T10:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pGTbwtCqnxmQ71D8mNbTTPO1Yhge1W+YdD/JQ/idzeY/dG72C+8q7eLochdLxTpZGaYcZt8mPLCaappy48jCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:20:56.753668Z"},"content_sha256":"889ce17fe67fb1c9af77501d84500ae2721f755929984287533aefacbe1b564a","schema_version":"1.0","event_id":"sha256:889ce17fe67fb1c9af77501d84500ae2721f755929984287533aefacbe1b564a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TSIQIDYJ6E4GCR2ICCI57C5VJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Korba, David Rohde, Imad Aouali, Victor-Emmanuel Brunel","submitted_at":"2024-02-22T16:09:45Z","abstract_excerpt":"In interactive systems, actions are often correlated, presenting an opportunity for more sample-efficient off-policy evaluation (OPE) and learning (OPL) in large action spaces. We introduce a unified Bayesian framework to capture these correlations through structured and informative priors. In this framework, we propose sDM, a generic Bayesian approach for OPE and OPL, grounded in both algorithmic and theoretical foundations. Notably, sDM leverages action correlations without compromising computational efficiency. Moreover, inspired by online Bayesian bandits, we introduce Bayesian metrics tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14664","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/2402.14664/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":"2026-07-05T10:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52AIEhwcHBtmLzKtDRkOsywHgyMtv41CMVXPcuUL/6A8Z4GBAIMFM0B9tvEVnjRNtx3hl6EFoa+cPjDL8+6lDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:20:56.754226Z"},"content_sha256":"f08e16960759d03f84c482cbcd723bd90628f5859e45dcb790e202ebc4801f31","schema_version":"1.0","event_id":"sha256:f08e16960759d03f84c482cbcd723bd90628f5859e45dcb790e202ebc4801f31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/bundle.json","state_url":"https://pith.science/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/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":"2026-08-06T00:20:56Z","links":{"resolver":"https://pith.science/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK","bundle":"https://pith.science/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/bundle.json","state":"https://pith.science/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSIQIDYJ6E4GCR2ICCI57C5VJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TSIQIDYJ6E4GCR2ICCI57C5VJK","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":"83bce6b03b399771c64777b9945cffaf0beb0ab739edddf348debc44c26e8b26","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T16:09:45Z","title_canon_sha256":"241db9696588eb9a3f9ad4dc2ab416b1c8e0d2db8310cf5f46d3409ba3c47c8d"},"schema_version":"1.0","source":{"id":"2402.14664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14664","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14664v2","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14664","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"TSIQIDYJ6E4G","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"TSIQIDYJ6E4GCR2I","created_at":"2026-07-05T10:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"TSIQIDYJ","created_at":"2026-07-05T10:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:f08e16960759d03f84c482cbcd723bd90628f5859e45dcb790e202ebc4801f31","target":"graph","created_at":"2026-07-05T10:46:19Z","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/2402.14664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In interactive systems, actions are often correlated, presenting an opportunity for more sample-efficient off-policy evaluation (OPE) and learning (OPL) in large action spaces. We introduce a unified Bayesian framework to capture these correlations through structured and informative priors. In this framework, we propose sDM, a generic Bayesian approach for OPE and OPL, grounded in both algorithmic and theoretical foundations. Notably, sDM leverages action correlations without compromising computational efficiency. Moreover, inspired by online Bayesian bandits, we introduce Bayesian metrics tha","authors_text":"Anna Korba, David Rohde, Imad Aouali, Victor-Emmanuel Brunel","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T16:09:45Z","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14664","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":"sha256:889ce17fe67fb1c9af77501d84500ae2721f755929984287533aefacbe1b564a","target":"record","created_at":"2026-07-05T10:46:19Z","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":"83bce6b03b399771c64777b9945cffaf0beb0ab739edddf348debc44c26e8b26","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T16:09:45Z","title_canon_sha256":"241db9696588eb9a3f9ad4dc2ab416b1c8e0d2db8310cf5f46d3409ba3c47c8d"},"schema_version":"1.0","source":{"id":"2402.14664","kind":"arxiv","version":2}},"canonical_sha256":"9c91040f09f1386147481091df8bb54a90857550a4a2e8ead0bb8474c394c7cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c91040f09f1386147481091df8bb54a90857550a4a2e8ead0bb8474c394c7cd","first_computed_at":"2026-07-05T10:46:19.132743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:19.132743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lRSDNH1cs1EaSbiQ/1GN7Q5wz/yl7g8PoA4U6IDqlDyMOiBu52ZdezZLtBZ+xnD2s0xVn3sM5CX5xAsftdq1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:19.133234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:889ce17fe67fb1c9af77501d84500ae2721f755929984287533aefacbe1b564a","sha256:f08e16960759d03f84c482cbcd723bd90628f5859e45dcb790e202ebc4801f31"],"state_sha256":"5fe64d4b73b53a8789791d3d9cc58d84d750ab2931a78b0e7de5849f92b9e325"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QM/Zj+mpxxA9Xl2DabkMZXzTecXeVToSXqigmkER4fHA9Je+BaGrED9AzDxyJl6mnEK1BCRGjgqWKaiOek4JCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:20:56.759667Z","bundle_sha256":"a79598d769c85440bea5f3e040da838b6d2dfee0db1cb69bced24d0b9cc3d704"}}