{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E2ZMVUGQQ5F6C6R77FIFLXCX5R","short_pith_number":"pith:E2ZMVUGQ","schema_version":"1.0","canonical_sha256":"26b2cad0d0874be17a3ff95055dc57ec408f4bcc62dab54ef589e4793b1ab051","source":{"kind":"arxiv","id":"2207.12877","version":2},"attestation_state":"computed","paper":{"title":"Representing Random Utility Choice Models with Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Aouad, Antoine D\\'esir","submitted_at":"2022-07-26T13:12:22Z","abstract_excerpt":"Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework. This model formulates the agents' random utility function using a sample average approximation. We show that RUMnets sharply approximate the class of RUM discrete choice models: any model derived from random utility maximization has choice probabilities that can be approximated arbitrarily closely by a RUMnet. Reciprocally, any RUMnet is consistent with the RUM principle. We derive an upper bound on the gene"},"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":"2207.12877","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-26T13:12:22Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6f23ec6dafd9f80aa34179e00caa6ee46ea2f29ea6e517fd269f26c44bdad317","abstract_canon_sha256":"6e6760bd008b05aa6ea772ffe30649c1d500466abda22f1273888ef454344127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:52.222471Z","signature_b64":"/E6w4HAa8Ir5t0Z+RhxWIzxd2CGdkU5t74Z+ADrixcgHQdqS65aFW9htgWghuyEehgjTIgit+fXJuhdwdai7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b2cad0d0874be17a3ff95055dc57ec408f4bcc62dab54ef589e4793b1ab051","last_reissued_at":"2026-07-05T06:32:52.222033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:52.222033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representing Random Utility Choice Models with Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Aouad, Antoine D\\'esir","submitted_at":"2022-07-26T13:12:22Z","abstract_excerpt":"Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework. This model formulates the agents' random utility function using a sample average approximation. We show that RUMnets sharply approximate the class of RUM discrete choice models: any model derived from random utility maximization has choice probabilities that can be approximated arbitrarily closely by a RUMnet. Reciprocally, any RUMnet is consistent with the RUM principle. We derive an upper bound on the gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12877","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/2207.12877/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":"2207.12877","created_at":"2026-07-05T06:32:52.222088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12877v2","created_at":"2026-07-05T06:32:52.222088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12877","created_at":"2026-07-05T06:32:52.222088+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2ZMVUGQQ5F6","created_at":"2026-07-05T06:32:52.222088+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2ZMVUGQQ5F6C6R7","created_at":"2026-07-05T06:32:52.222088+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2ZMVUGQ","created_at":"2026-07-05T06:32:52.222088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2405.10498","citing_title":"A Deep Learning Approach to Heterogeneous Consumer Aesthetics in Fast Fashion","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R","json":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R.json","graph_json":"https://pith.science/api/pith-number/E2ZMVUGQQ5F6C6R77FIFLXCX5R/graph.json","events_json":"https://pith.science/api/pith-number/E2ZMVUGQQ5F6C6R77FIFLXCX5R/events.json","paper":"https://pith.science/paper/E2ZMVUGQ"},"agent_actions":{"view_html":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R","download_json":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R.json","view_paper":"https://pith.science/paper/E2ZMVUGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12877&json=true","fetch_graph":"https://pith.science/api/pith-number/E2ZMVUGQQ5F6C6R77FIFLXCX5R/graph.json","fetch_events":"https://pith.science/api/pith-number/E2ZMVUGQQ5F6C6R77FIFLXCX5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R/action/storage_attestation","attest_author":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R/action/author_attestation","sign_citation":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R/action/citation_signature","submit_replication":"https://pith.science/pith/E2ZMVUGQQ5F6C6R77FIFLXCX5R/action/replication_record"}},"created_at":"2026-07-05T06:32:52.222088+00:00","updated_at":"2026-07-05T06:32:52.222088+00:00"}