{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6NLXMZGE4NFQMYIGWRWFGQ53FL","short_pith_number":"pith:6NLXMZGE","schema_version":"1.0","canonical_sha256":"f3577664c4e34b066106b46c5343bb2af5343889a03b192788df4a85f0c80ba2","source":{"kind":"arxiv","id":"2008.07146","version":5},"attestation_state":"computed","paper":{"title":"Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Megumi Matsutani, Shunsuke Aihara, Yusuke Narita, Yuta Saito","submitted_at":"2020-08-17T08:23:50Z","abstract_excerpt":"Off-policy evaluation (OPE) aims to estimate the performance of hypothetical policies using data generated by a different policy. Because of its huge potential impact in practice, there has been growing research interest in this field. There is, however, no real-world public dataset that enables the evaluation of OPE, making its experimental studies unrealistic and irreproducible. With the goal of enabling realistic and reproducible OPE research, we present Open Bandit Dataset, a public logged bandit dataset collected on a large-scale fashion e-commerce platform, ZOZOTOWN. Our dataset is uniqu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.07146","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T08:23:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"02959645cae847a55caa445a0a536cc864af2a76c22e4d89a4dd62bf4e4edf42","abstract_canon_sha256":"c5c8509fd7f5ca9eaf2600ecffecc38e83d96d02402df0e746f82880624ac506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:28.830711Z","signature_b64":"tNUEkk+SV1hPPBMo4S5lJG+MnWRfbZkmADFSG4Z/+YoT8CEenq8UOsPjxRwlhkwg2VSgsVQ5oOnNKfc6pyosAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3577664c4e34b066106b46c5343bb2af5343889a03b192788df4a85f0c80ba2","last_reissued_at":"2026-07-05T03:25:28.830268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:28.830268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Megumi Matsutani, Shunsuke Aihara, Yusuke Narita, Yuta Saito","submitted_at":"2020-08-17T08:23:50Z","abstract_excerpt":"Off-policy evaluation (OPE) aims to estimate the performance of hypothetical policies using data generated by a different policy. Because of its huge potential impact in practice, there has been growing research interest in this field. There is, however, no real-world public dataset that enables the evaluation of OPE, making its experimental studies unrealistic and irreproducible. With the goal of enabling realistic and reproducible OPE research, we present Open Bandit Dataset, a public logged bandit dataset collected on a large-scale fashion e-commerce platform, ZOZOTOWN. Our dataset is uniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07146","kind":"arxiv","version":5},"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/2008.07146/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.07146","created_at":"2026-07-05T03:25:28.830324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.07146v5","created_at":"2026-07-05T03:25:28.830324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07146","created_at":"2026-07-05T03:25:28.830324+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NLXMZGE4NFQ","created_at":"2026-07-05T03:25:28.830324+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NLXMZGE4NFQMYIG","created_at":"2026-07-05T03:25:28.830324+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NLXMZGE","created_at":"2026-07-05T03:25:28.830324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05792","citing_title":"Estimating Causal Effects from Data Generated by Stochastic Algorithms","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22510","citing_title":"Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10187","citing_title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2507.18756","citing_title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07964","citing_title":"Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07964","citing_title":"Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL","json":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL.json","graph_json":"https://pith.science/api/pith-number/6NLXMZGE4NFQMYIGWRWFGQ53FL/graph.json","events_json":"https://pith.science/api/pith-number/6NLXMZGE4NFQMYIGWRWFGQ53FL/events.json","paper":"https://pith.science/paper/6NLXMZGE"},"agent_actions":{"view_html":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL","download_json":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL.json","view_paper":"https://pith.science/paper/6NLXMZGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.07146&json=true","fetch_graph":"https://pith.science/api/pith-number/6NLXMZGE4NFQMYIGWRWFGQ53FL/graph.json","fetch_events":"https://pith.science/api/pith-number/6NLXMZGE4NFQMYIGWRWFGQ53FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL/action/storage_attestation","attest_author":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL/action/author_attestation","sign_citation":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL/action/citation_signature","submit_replication":"https://pith.science/pith/6NLXMZGE4NFQMYIGWRWFGQ53FL/action/replication_record"}},"created_at":"2026-07-05T03:25:28.830324+00:00","updated_at":"2026-07-05T03:25:28.830324+00:00"}