{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SZ3BVGCTPABEVSUJJWJLPPWOFK","short_pith_number":"pith:SZ3BVGCT","schema_version":"1.0","canonical_sha256":"96761a985378024aca894d92b7bece2a8b0167c1e877a29f91127545a0951d55","source":{"kind":"arxiv","id":"2404.17398","version":2},"attestation_state":"computed","paper":{"title":"Online Policy Learning and Inference by Matrix Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Congyuan Duan, Dong Xia, Jingyang Li","submitted_at":"2024-04-26T13:19:27Z","abstract_excerpt":"Is it possible to make online decisions when personalized covariates are unavailable? We take a collaborative-filtering approach for decision-making based on collective preferences. By assuming low-dimensional latent features, we formulate the covariate-free decision-making problem as a matrix completion bandit. We propose a policy learning procedure that combines an $\\varepsilon$-greedy policy for decision-making with an online gradient descent algorithm for bandit parameter estimation. Our novel two-phase design balances policy learning accuracy and regret performance. For policy inference, "},"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":"2404.17398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-04-26T13:19:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"031ffa8afe350027c784373490717abe3fe4796f84ca7b39e30410a8aa275c88","abstract_canon_sha256":"60096e2a32613aeb6b16dd854ed5425708b66b3baf89c0d8c0ebb0a7e5e8ff5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:32.294761Z","signature_b64":"xBzaoULpQUTSxM/oZUvSSX6tj8oT3HfsbxG0gBfhvB/Sq7Ov56PzO4me025QUIIAJq6+4WnZ0mMPSgQ3FlqQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96761a985378024aca894d92b7bece2a8b0167c1e877a29f91127545a0951d55","last_reissued_at":"2026-07-05T09:51:32.294275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:32.294275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Policy Learning and Inference by Matrix Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Congyuan Duan, Dong Xia, Jingyang Li","submitted_at":"2024-04-26T13:19:27Z","abstract_excerpt":"Is it possible to make online decisions when personalized covariates are unavailable? We take a collaborative-filtering approach for decision-making based on collective preferences. By assuming low-dimensional latent features, we formulate the covariate-free decision-making problem as a matrix completion bandit. We propose a policy learning procedure that combines an $\\varepsilon$-greedy policy for decision-making with an online gradient descent algorithm for bandit parameter estimation. Our novel two-phase design balances policy learning accuracy and regret performance. For policy inference, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17398","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/2404.17398/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":"2404.17398","created_at":"2026-07-05T09:51:32.294339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17398v2","created_at":"2026-07-05T09:51:32.294339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17398","created_at":"2026-07-05T09:51:32.294339+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZ3BVGCTPABE","created_at":"2026-07-05T09:51:32.294339+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZ3BVGCTPABEVSUJ","created_at":"2026-07-05T09:51:32.294339+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZ3BVGCT","created_at":"2026-07-05T09:51:32.294339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08843","citing_title":"Precise Asymptotics and Refined Regret of Variance-Aware UCB","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK","json":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK.json","graph_json":"https://pith.science/api/pith-number/SZ3BVGCTPABEVSUJJWJLPPWOFK/graph.json","events_json":"https://pith.science/api/pith-number/SZ3BVGCTPABEVSUJJWJLPPWOFK/events.json","paper":"https://pith.science/paper/SZ3BVGCT"},"agent_actions":{"view_html":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK","download_json":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK.json","view_paper":"https://pith.science/paper/SZ3BVGCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17398&json=true","fetch_graph":"https://pith.science/api/pith-number/SZ3BVGCTPABEVSUJJWJLPPWOFK/graph.json","fetch_events":"https://pith.science/api/pith-number/SZ3BVGCTPABEVSUJJWJLPPWOFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK/action/storage_attestation","attest_author":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK/action/author_attestation","sign_citation":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK/action/citation_signature","submit_replication":"https://pith.science/pith/SZ3BVGCTPABEVSUJJWJLPPWOFK/action/replication_record"}},"created_at":"2026-07-05T09:51:32.294339+00:00","updated_at":"2026-07-05T09:51:32.294339+00:00"}