{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RDARYRAZC2CDM7MRQCMKWELPC3","short_pith_number":"pith:RDARYRAZ","canonical_record":{"source":{"id":"2202.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T14:00:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"39902ee2724f71cc6e9a12937425d7c513844e7e42ab9782129285209ed9079d","abstract_canon_sha256":"cecaca42350bcde254f25fc655bc2a098f4ba8a6b5ff2bcc626b7eb014e21327"},"schema_version":"1.0"},"canonical_sha256":"88c11c44191684367d918098ab116f16c6709bcb73436be114015b3172813a13","source":{"kind":"arxiv","id":"2202.06317","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06317","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06317v2","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06317","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_12","alias_value":"RDARYRAZC2CD","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_16","alias_value":"RDARYRAZC2CDM7MR","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_8","alias_value":"RDARYRAZ","created_at":"2026-07-05T04:32:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RDARYRAZC2CDM7MRQCMKWELPC3","target":"record","payload":{"canonical_record":{"source":{"id":"2202.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T14:00:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"39902ee2724f71cc6e9a12937425d7c513844e7e42ab9782129285209ed9079d","abstract_canon_sha256":"cecaca42350bcde254f25fc655bc2a098f4ba8a6b5ff2bcc626b7eb014e21327"},"schema_version":"1.0"},"canonical_sha256":"88c11c44191684367d918098ab116f16c6709bcb73436be114015b3172813a13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:14.633333Z","signature_b64":"V/OAgJuBsSqfvI4c/7HixprpBYN2OrbsLtktTKRBlt5VGxNcRz83WzNrMOUKsfGKiOtQas8BPHxBmjCW6dy8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c11c44191684367d918098ab116f16c6709bcb73436be114015b3172813a13","last_reissued_at":"2026-07-05T04:32:14.632850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:14.632850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.06317","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":"2026-07-05T04:32:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QtMy+xLaxGP3ncr9NRR5Mm7IllKRE3MezBUxP4LpveyLzHUylNqIx9G92TNegeQEl73IkQxNdV9zE5ANbf+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:13:54.061714Z"},"content_sha256":"c1946264fe7278bcde09e2e0c8396b380aba4e679273b09554cc726e11f75eb6","schema_version":"1.0","event_id":"sha256:c1946264fe7278bcde09e2e0c8396b380aba4e679273b09554cc726e11f75eb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RDARYRAZC2CDM7MRQCMKWELPC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Thorsten Joachims, Yuta Saito","submitted_at":"2022-02-13T14:00:09Z","abstract_excerpt":"Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in real-world systems, since it enables offline evaluation of new policies using only historic log data. Unfortunately, when the number of actions is large, existing OPE estimators -- most of which are based on inverse propensity score weighting -- degrade severely and can suffer from extreme bias and variance. This foils the use of OPE in many applications from recommender systems to language models. To overcome this issue, we propose a new OPE estimator that leverages marginalized importance weights when action embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06317","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/2202.06317/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":"2026-07-05T04:32:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3pLmzS+e07tAZ9zPVHyAvedBvyozQpM5dugSJZOQ6Z91h9FDZjF7oN6OWmqUWIqeNeaE5ahj/dOID6bXHhx0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:13:54.062292Z"},"content_sha256":"a37a78c729483e8a31597f653d4589fee4e390ad0b7c3532b00a6723a0c96ad6","schema_version":"1.0","event_id":"sha256:a37a78c729483e8a31597f653d4589fee4e390ad0b7c3532b00a6723a0c96ad6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDARYRAZC2CDM7MRQCMKWELPC3/bundle.json","state_url":"https://pith.science/pith/RDARYRAZC2CDM7MRQCMKWELPC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDARYRAZC2CDM7MRQCMKWELPC3/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":"2026-08-05T20:13:54Z","links":{"resolver":"https://pith.science/pith/RDARYRAZC2CDM7MRQCMKWELPC3","bundle":"https://pith.science/pith/RDARYRAZC2CDM7MRQCMKWELPC3/bundle.json","state":"https://pith.science/pith/RDARYRAZC2CDM7MRQCMKWELPC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDARYRAZC2CDM7MRQCMKWELPC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RDARYRAZC2CDM7MRQCMKWELPC3","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":"cecaca42350bcde254f25fc655bc2a098f4ba8a6b5ff2bcc626b7eb014e21327","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T14:00:09Z","title_canon_sha256":"39902ee2724f71cc6e9a12937425d7c513844e7e42ab9782129285209ed9079d"},"schema_version":"1.0","source":{"id":"2202.06317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06317","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06317v2","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06317","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_12","alias_value":"RDARYRAZC2CD","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_16","alias_value":"RDARYRAZC2CDM7MR","created_at":"2026-07-05T04:32:14Z"},{"alias_kind":"pith_short_8","alias_value":"RDARYRAZ","created_at":"2026-07-05T04:32:14Z"}],"graph_snapshots":[{"event_id":"sha256:a37a78c729483e8a31597f653d4589fee4e390ad0b7c3532b00a6723a0c96ad6","target":"graph","created_at":"2026-07-05T04:32:14Z","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/2202.06317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in real-world systems, since it enables offline evaluation of new policies using only historic log data. Unfortunately, when the number of actions is large, existing OPE estimators -- most of which are based on inverse propensity score weighting -- degrade severely and can suffer from extreme bias and variance. This foils the use of OPE in many applications from recommender systems to language models. To overcome this issue, we propose a new OPE estimator that leverages marginalized importance weights when action embeddi","authors_text":"Thorsten Joachims, Yuta Saito","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T14:00:09Z","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06317","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:c1946264fe7278bcde09e2e0c8396b380aba4e679273b09554cc726e11f75eb6","target":"record","created_at":"2026-07-05T04:32:14Z","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":"cecaca42350bcde254f25fc655bc2a098f4ba8a6b5ff2bcc626b7eb014e21327","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T14:00:09Z","title_canon_sha256":"39902ee2724f71cc6e9a12937425d7c513844e7e42ab9782129285209ed9079d"},"schema_version":"1.0","source":{"id":"2202.06317","kind":"arxiv","version":2}},"canonical_sha256":"88c11c44191684367d918098ab116f16c6709bcb73436be114015b3172813a13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88c11c44191684367d918098ab116f16c6709bcb73436be114015b3172813a13","first_computed_at":"2026-07-05T04:32:14.632850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:14.632850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/OAgJuBsSqfvI4c/7HixprpBYN2OrbsLtktTKRBlt5VGxNcRz83WzNrMOUKsfGKiOtQas8BPHxBmjCW6dy8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:14.633333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1946264fe7278bcde09e2e0c8396b380aba4e679273b09554cc726e11f75eb6","sha256:a37a78c729483e8a31597f653d4589fee4e390ad0b7c3532b00a6723a0c96ad6"],"state_sha256":"c1de8f2b5a326c6dced30951d0103714605c8cbf98eb795eb68f20b9699230f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUT1kGApcqT0okpQIarUvXkNqD7ScIhhdfMXvXBwU7F2gI34IfGdIDQz/DxYZRGZGHEgH2Y9zcpFofdLS8y8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:13:54.074504Z","bundle_sha256":"3dfa5c303d234422a0379f2c58523e23d41f96177bea818b680016778fc30779"}}