{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2ZLJ2LDACIWNWIGGJ35VVNK2KR","short_pith_number":"pith:2ZLJ2LDA","schema_version":"1.0","canonical_sha256":"d6569d2c60122cdb20c64efb5ab55a5466dd4e3c876797c4b5ebf5ae742a08f3","source":{"kind":"arxiv","id":"2312.15595","version":3},"attestation_state":"computed","paper":{"title":"Zero-Inflated Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Haoyu Wei, Lei Shi, Rui Song, Runzhe Wan","submitted_at":"2023-12-25T03:13:21Z","abstract_excerpt":"Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving estimation efficiency in statistics. However, this approach remains under-explored in the context of bandits. To address this gap, we initiate the study of zero-inflated bandits, where the reward is modeled using a classic semi-parametric distribution known as the zero-inflated distribution. We develop algorithms based on the Upper Confidence Bound and Thomps"},"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":"2312.15595","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-25T03:13:21Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"11669a8bd40b82aefe571a24ebb103035110a40b12867e735a3f92bc4c2abd5c","abstract_canon_sha256":"ce9657072476c3ee85111d57cc14fd22545ee4929b894e133ae587baf3ce0c6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:13.450378Z","signature_b64":"iPb/q55MbocIyLhbrCWwG2h6eivK2tDVqPUNg4NzCSqwDXCFKitGlcd0uMp8fbuzhwtZhAzg6+c06/pR0PFwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6569d2c60122cdb20c64efb5ab55a5466dd4e3c876797c4b5ebf5ae742a08f3","last_reissued_at":"2026-07-05T10:08:13.449891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:13.449891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Inflated Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Haoyu Wei, Lei Shi, Rui Song, Runzhe Wan","submitted_at":"2023-12-25T03:13:21Z","abstract_excerpt":"Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving estimation efficiency in statistics. However, this approach remains under-explored in the context of bandits. To address this gap, we initiate the study of zero-inflated bandits, where the reward is modeled using a classic semi-parametric distribution known as the zero-inflated distribution. We develop algorithms based on the Upper Confidence Bound and Thomps"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15595","kind":"arxiv","version":3},"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/2312.15595/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":"2312.15595","created_at":"2026-07-05T10:08:13.449949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15595v3","created_at":"2026-07-05T10:08:13.449949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15595","created_at":"2026-07-05T10:08:13.449949+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZLJ2LDACIWN","created_at":"2026-07-05T10:08:13.449949+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZLJ2LDACIWNWIGG","created_at":"2026-07-05T10:08:13.449949+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZLJ2LDA","created_at":"2026-07-05T10:08:13.449949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02251","citing_title":"Selective Reviews of Bandit Problems in AI via a Statistical View","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR","json":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR.json","graph_json":"https://pith.science/api/pith-number/2ZLJ2LDACIWNWIGGJ35VVNK2KR/graph.json","events_json":"https://pith.science/api/pith-number/2ZLJ2LDACIWNWIGGJ35VVNK2KR/events.json","paper":"https://pith.science/paper/2ZLJ2LDA"},"agent_actions":{"view_html":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR","download_json":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR.json","view_paper":"https://pith.science/paper/2ZLJ2LDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15595&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZLJ2LDACIWNWIGGJ35VVNK2KR/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZLJ2LDACIWNWIGGJ35VVNK2KR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR/action/storage_attestation","attest_author":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR/action/author_attestation","sign_citation":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR/action/citation_signature","submit_replication":"https://pith.science/pith/2ZLJ2LDACIWNWIGGJ35VVNK2KR/action/replication_record"}},"created_at":"2026-07-05T10:08:13.449949+00:00","updated_at":"2026-07-05T10:08:13.449949+00:00"}