{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WCJQWZTUAI7Z7ERKCB72FPVQAG","short_pith_number":"pith:WCJQWZTU","schema_version":"1.0","canonical_sha256":"b0930b6674023f9f922a107fa2beb001b8530049eb6b7a09560b9ec32c5b7288","source":{"kind":"arxiv","id":"1706.03880","version":2},"attestation_state":"computed","paper":{"title":"MNL-Bandit: A Dynamic Learning Approach to Assortment Selection","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":"2017-06-13T00:54:47Z","abstract_excerpt":"We consider a dynamic assortment selection problem, where in every round the retailer offers a subset (assortment) of $N$ substitutable products to a consumer, who selects one of these products according to a multinomial logit (MNL) choice model. The retailer observes this choice and the objective is to dynamically learn the model parameters, while optimizing cumulative revenues over a selling horizon of length $T$. We refer to this exploration-exploitation formulation as the MNL-Bandit problem. Existing methods for this problem follow an \"explore-then-exploit\" approach, which estimate paramet"},"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":"1706.03880","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-13T00:54:47Z","cross_cats_sorted":[],"title_canon_sha256":"56cc7be063968ef561e0aa7511b3945795dab91e8dfad141975c8d298d3ef209","abstract_canon_sha256":"90c85281b3b6b03aca3b0750f371931af47e3201cfa24275541189cef542480e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:58.231787Z","signature_b64":"MkoLGxwrJ5InW3kEPBB67cdfMMH5FUMI5Y+2c5Pu8I+JW7WZ27RDiJW6pnHOZOcwHiOa2vW6iUtLteua+tGOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0930b6674023f9f922a107fa2beb001b8530049eb6b7a09560b9ec32c5b7288","last_reissued_at":"2026-05-18T00:11:58.231098Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:58.231098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MNL-Bandit: A Dynamic Learning Approach to Assortment Selection","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":"2017-06-13T00:54:47Z","abstract_excerpt":"We consider a dynamic assortment selection problem, where in every round the retailer offers a subset (assortment) of $N$ substitutable products to a consumer, who selects one of these products according to a multinomial logit (MNL) choice model. The retailer observes this choice and the objective is to dynamically learn the model parameters, while optimizing cumulative revenues over a selling horizon of length $T$. We refer to this exploration-exploitation formulation as the MNL-Bandit problem. Existing methods for this problem follow an \"explore-then-exploit\" approach, which estimate paramet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03880","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":""},"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":"1706.03880","created_at":"2026-05-18T00:11:58.231204+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.03880v2","created_at":"2026-05-18T00:11:58.231204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03880","created_at":"2026-05-18T00:11:58.231204+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCJQWZTUAI7Z","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCJQWZTUAI7Z7ERK","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCJQWZTU","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17126","citing_title":"Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG","json":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG.json","graph_json":"https://pith.science/api/pith-number/WCJQWZTUAI7Z7ERKCB72FPVQAG/graph.json","events_json":"https://pith.science/api/pith-number/WCJQWZTUAI7Z7ERKCB72FPVQAG/events.json","paper":"https://pith.science/paper/WCJQWZTU"},"agent_actions":{"view_html":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG","download_json":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG.json","view_paper":"https://pith.science/paper/WCJQWZTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.03880&json=true","fetch_graph":"https://pith.science/api/pith-number/WCJQWZTUAI7Z7ERKCB72FPVQAG/graph.json","fetch_events":"https://pith.science/api/pith-number/WCJQWZTUAI7Z7ERKCB72FPVQAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG/action/storage_attestation","attest_author":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG/action/author_attestation","sign_citation":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG/action/citation_signature","submit_replication":"https://pith.science/pith/WCJQWZTUAI7Z7ERKCB72FPVQAG/action/replication_record"}},"created_at":"2026-05-18T00:11:58.231204+00:00","updated_at":"2026-05-18T00:11:58.231204+00:00"}