{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PDRML6A27B43L74PDZ2WQVIGRN","short_pith_number":"pith:PDRML6A2","schema_version":"1.0","canonical_sha256":"78e2c5f81af879b5ff8f1e756855068b55ffc71d249585dbb385c40e6170c2aa","source":{"kind":"arxiv","id":"2002.00922","version":2},"attestation_state":"computed","paper":{"title":"A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Christopher Zegras, Francisco Camara Pereira, Moshe Ben-Akiva, Yafei Han","submitted_at":"2020-02-03T18:03:54Z","abstract_excerpt":"Discrete choice models (DCMs) require a priori knowledge of the utility functions, especially how tastes vary across individuals. Utility misspecification may lead to biased estimates, inaccurate interpretations and limited predictability. In this paper, we utilize a neural network to learn taste representation. Our formulation consists of two modules: a neural network (TasteNet) that learns taste parameters (e.g., time coefficient) as flexible functions of individual characteristics; and a multinomial logit (MNL) model with utility functions defined with expert knowledge. Taste parameters lea"},"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":"2002.00922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2020-02-03T18:03:54Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"c6242737f97bd9794f921bcc75acabd4f6b784e449c9571fb46af849010f2876","abstract_canon_sha256":"6bbb0a40aece8e98b15778eb0ef918fc3cfe022a7636ff55c604406b1603cf20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:30.952001Z","signature_b64":"Y2OtGFl0IgVoip6W/yKl+Cnn1nO27Vw5WffpJU2lWKIOxl1mOOWS0yU6aixSAX1xfKBKY79J+7f2I2HGJfc0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e2c5f81af879b5ff8f1e756855068b55ffc71d249585dbb385c40e6170c2aa","last_reissued_at":"2026-07-05T04:36:30.951577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:30.951577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"econ.EM","authors_text":"Christopher Zegras, Francisco Camara Pereira, Moshe Ben-Akiva, Yafei Han","submitted_at":"2020-02-03T18:03:54Z","abstract_excerpt":"Discrete choice models (DCMs) require a priori knowledge of the utility functions, especially how tastes vary across individuals. Utility misspecification may lead to biased estimates, inaccurate interpretations and limited predictability. In this paper, we utilize a neural network to learn taste representation. Our formulation consists of two modules: a neural network (TasteNet) that learns taste parameters (e.g., time coefficient) as flexible functions of individual characteristics; and a multinomial logit (MNL) model with utility functions defined with expert knowledge. Taste parameters lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.00922","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/2002.00922/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":"2002.00922","created_at":"2026-07-05T04:36:30.951633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.00922v2","created_at":"2026-07-05T04:36:30.951633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.00922","created_at":"2026-07-05T04:36:30.951633+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDRML6A27B43","created_at":"2026-07-05T04:36:30.951633+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDRML6A27B43L74P","created_at":"2026-07-05T04:36:30.951633+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDRML6A2","created_at":"2026-07-05T04:36:30.951633+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/PDRML6A27B43L74PDZ2WQVIGRN","json":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN.json","graph_json":"https://pith.science/api/pith-number/PDRML6A27B43L74PDZ2WQVIGRN/graph.json","events_json":"https://pith.science/api/pith-number/PDRML6A27B43L74PDZ2WQVIGRN/events.json","paper":"https://pith.science/paper/PDRML6A2"},"agent_actions":{"view_html":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN","download_json":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN.json","view_paper":"https://pith.science/paper/PDRML6A2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.00922&json=true","fetch_graph":"https://pith.science/api/pith-number/PDRML6A27B43L74PDZ2WQVIGRN/graph.json","fetch_events":"https://pith.science/api/pith-number/PDRML6A27B43L74PDZ2WQVIGRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN/action/storage_attestation","attest_author":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN/action/author_attestation","sign_citation":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN/action/citation_signature","submit_replication":"https://pith.science/pith/PDRML6A27B43L74PDZ2WQVIGRN/action/replication_record"}},"created_at":"2026-07-05T04:36:30.951633+00:00","updated_at":"2026-07-05T04:36:30.951633+00:00"}