{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LQC352SCMORDZVXXEPNGWMRHLT","short_pith_number":"pith:LQC352SC","schema_version":"1.0","canonical_sha256":"5c05beea4263a23cd6f723da6b32275cc99792e7765c51ab80eef04fbeb2d78d","source":{"kind":"arxiv","id":"2103.13929","version":1},"attestation_state":"computed","paper":{"title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Garud Iyengar, Min-hwan Oh","submitted_at":"2021-03-25T15:42:25Z","abstract_excerpt":"We consider a sequential assortment selection problem where the user choice is given by a multinomial logit (MNL) choice model whose parameters are unknown. In each period, the learning agent observes a $d$-dimensional contextual information about the user and the $N$ available items, and offers an assortment of size $K$ to the user, and observes the bandit feedback of the item chosen from the assortment. We propose upper confidence bound based algorithms for this MNL contextual bandit. The first algorithm is a simple and practical method which achieves an $\\tilde{\\mathcal{O}}(d\\sqrt{T})$ regr"},"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":"2103.13929","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-03-25T15:42:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3d7ae426c626e1259c36dc4dd5e7b25f971a9602ec1284f9e623c0fd991833e","abstract_canon_sha256":"b892a41693ac63f9f0c89382ae3bd301b92a46a2d040560389ca933d1e61ccd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:23.881330Z","signature_b64":"ta29TgG/WOFyZmX3HcUYz89lX/lrfqIhLBrXE/bmpPmVHOXsD75U1RSv5I4LcVkN6LG2hLKkFHOeULegB+t5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c05beea4263a23cd6f723da6b32275cc99792e7765c51ab80eef04fbeb2d78d","last_reissued_at":"2026-07-05T02:26:23.880957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:23.880957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Garud Iyengar, Min-hwan Oh","submitted_at":"2021-03-25T15:42:25Z","abstract_excerpt":"We consider a sequential assortment selection problem where the user choice is given by a multinomial logit (MNL) choice model whose parameters are unknown. In each period, the learning agent observes a $d$-dimensional contextual information about the user and the $N$ available items, and offers an assortment of size $K$ to the user, and observes the bandit feedback of the item chosen from the assortment. We propose upper confidence bound based algorithms for this MNL contextual bandit. The first algorithm is a simple and practical method which achieves an $\\tilde{\\mathcal{O}}(d\\sqrt{T})$ regr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13929","kind":"arxiv","version":1},"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/2103.13929/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":"2103.13929","created_at":"2026-07-05T02:26:23.881017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13929v1","created_at":"2026-07-05T02:26:23.881017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13929","created_at":"2026-07-05T02:26:23.881017+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQC352SCMORD","created_at":"2026-07-05T02:26:23.881017+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQC352SCMORDZVXX","created_at":"2026-07-05T02:26:23.881017+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQC352SC","created_at":"2026-07-05T02:26:23.881017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.16137","citing_title":"Experimental Assortments for Choice Estimation and Nest Identification","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT","json":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT.json","graph_json":"https://pith.science/api/pith-number/LQC352SCMORDZVXXEPNGWMRHLT/graph.json","events_json":"https://pith.science/api/pith-number/LQC352SCMORDZVXXEPNGWMRHLT/events.json","paper":"https://pith.science/paper/LQC352SC"},"agent_actions":{"view_html":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT","download_json":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT.json","view_paper":"https://pith.science/paper/LQC352SC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13929&json=true","fetch_graph":"https://pith.science/api/pith-number/LQC352SCMORDZVXXEPNGWMRHLT/graph.json","fetch_events":"https://pith.science/api/pith-number/LQC352SCMORDZVXXEPNGWMRHLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT/action/storage_attestation","attest_author":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT/action/author_attestation","sign_citation":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT/action/citation_signature","submit_replication":"https://pith.science/pith/LQC352SCMORDZVXXEPNGWMRHLT/action/replication_record"}},"created_at":"2026-07-05T02:26:23.881017+00:00","updated_at":"2026-07-05T02:26:23.881017+00:00"}