{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Q7UGCIKCPQ6L4ITPACAYRB3QOP","short_pith_number":"pith:Q7UGCIKC","schema_version":"1.0","canonical_sha256":"87e86121427c3cbe226f008188877073c21c6d94062c3268c191be7fb7ebd9c3","source":{"kind":"arxiv","id":"1706.00977","version":7},"attestation_state":"computed","paper":{"title":"Thompson Sampling for the MNL-Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Assaf Zeevi, Shipra Agrawal, Vashist Avadhanula, Vineet Goyal","submitted_at":"2017-06-03T16:48:34Z","abstract_excerpt":"We consider a sequential subset selection problem under parameter uncertainty, where at each time step, the decision maker selects a subset of cardinality $K$ from $N$ possible items (arms), and observes a (bandit) feedback in the form of the index of one of the items in said subset, or none. Each item in the index set is ascribed a certain value (reward), and the feedback is governed by a Multinomial Logit (MNL) choice model whose parameters are a priori unknown. The objective of the decision maker is to maximize the expected cumulative rewards over a finite horizon $T$, or alternatively, min"},"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":"1706.00977","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-03T16:48:34Z","cross_cats_sorted":[],"title_canon_sha256":"79bb5b342282651c0af0936576af44bddf2b802f78e801858cd7631c11d71653","abstract_canon_sha256":"8e881ee858c13bec7939c874f1df3fdff6869c3566ef5128ad4c4b94915a4812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:58.847836Z","signature_b64":"bjvrRr+VMgLHDuTVqeZ1jInTfM1wwHF9ZaGcoOMFZDQwX0zFn4EoL2lcY1wEWompB2IJVSkafbHNxW2TRD2TBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87e86121427c3cbe226f008188877073c21c6d94062c3268c191be7fb7ebd9c3","last_reissued_at":"2026-05-17T23:56:58.847135Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:58.847135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling for the MNL-Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Assaf Zeevi, Shipra Agrawal, Vashist Avadhanula, Vineet Goyal","submitted_at":"2017-06-03T16:48:34Z","abstract_excerpt":"We consider a sequential subset selection problem under parameter uncertainty, where at each time step, the decision maker selects a subset of cardinality $K$ from $N$ possible items (arms), and observes a (bandit) feedback in the form of the index of one of the items in said subset, or none. Each item in the index set is ascribed a certain value (reward), and the feedback is governed by a Multinomial Logit (MNL) choice model whose parameters are a priori unknown. The objective of the decision maker is to maximize the expected cumulative rewards over a finite horizon $T$, or alternatively, min"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00977","kind":"arxiv","version":7},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1706.00977","created_at":"2026-05-17T23:56:58.847242+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00977v7","created_at":"2026-05-17T23:56:58.847242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00977","created_at":"2026-05-17T23:56:58.847242+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7UGCIKCPQ6L","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7UGCIKCPQ6L4ITP","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7UGCIKC","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP","json":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP.json","graph_json":"https://pith.science/api/pith-number/Q7UGCIKCPQ6L4ITPACAYRB3QOP/graph.json","events_json":"https://pith.science/api/pith-number/Q7UGCIKCPQ6L4ITPACAYRB3QOP/events.json","paper":"https://pith.science/paper/Q7UGCIKC"},"agent_actions":{"view_html":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP","download_json":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP.json","view_paper":"https://pith.science/paper/Q7UGCIKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00977&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7UGCIKCPQ6L4ITPACAYRB3QOP/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7UGCIKCPQ6L4ITPACAYRB3QOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP/action/storage_attestation","attest_author":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP/action/author_attestation","sign_citation":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP/action/citation_signature","submit_replication":"https://pith.science/pith/Q7UGCIKCPQ6L4ITPACAYRB3QOP/action/replication_record"}},"created_at":"2026-05-17T23:56:58.847242+00:00","updated_at":"2026-05-17T23:56:58.847242+00:00"}