{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJCRCXZR5NKJEHF2UHYWK5B5LS","short_pith_number":"pith:HJCRCXZR","schema_version":"1.0","canonical_sha256":"3a45115f31eb54921cbaa1f165743d5cabcced9ec930696c54e2396d5b8c4cfc","source":{"kind":"arxiv","id":"2601.05374","version":2},"attestation_state":"computed","paper":{"title":"From Unstructured Data to Demand Counterfactuals: Theory and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"econ.EM","authors_text":"Giovanni Compiani, Timothy Christensen","submitted_at":"2026-01-08T20:55:16Z","abstract_excerpt":"Empirical models of multi-product demand rely on low-dimensional product representations to capture substitution patterns, increasingly using proxies built from unstructured data. When proxies are imperfect, standard workflows yield biased counterfactuals and invalid inference. We develop a practical toolkit to address these issues. Our methods apply to market-level and/or individual data, require minimal additional computation, provide simple standard-error formulas, and accommodate proxies from fine-tuned models. Further, we propose diagnostics to assess proxy quality. Our methods yield mean"},"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":"2601.05374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-01-08T20:55:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d47fdb4f301c2547fa3a55deff18afa3b63aafc0cb3778695f6956850a165f82","abstract_canon_sha256":"427d2ceb440292f891ed21ebe309d09d53f846dc730c125770f56c007e612ee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:45.795918Z","signature_b64":"Epc9nQKuAXnwhHRw0O3p6Qf/OCaG8FrxjjTONBi/mIo/QOyDvjMmxzRhJyW+oQe2b6NSZBUZPPbmYbvjWebJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a45115f31eb54921cbaa1f165743d5cabcced9ec930696c54e2396d5b8c4cfc","last_reissued_at":"2026-06-23T02:12:45.795414Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:45.795414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Unstructured Data to Demand Counterfactuals: Theory and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"econ.EM","authors_text":"Giovanni Compiani, Timothy Christensen","submitted_at":"2026-01-08T20:55:16Z","abstract_excerpt":"Empirical models of multi-product demand rely on low-dimensional product representations to capture substitution patterns, increasingly using proxies built from unstructured data. When proxies are imperfect, standard workflows yield biased counterfactuals and invalid inference. We develop a practical toolkit to address these issues. Our methods apply to market-level and/or individual data, require minimal additional computation, provide simple standard-error formulas, and accommodate proxies from fine-tuned models. Further, we propose diagnostics to assess proxy quality. Our methods yield mean"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05374","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/2601.05374/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":"2601.05374","created_at":"2026-06-23T02:12:45.795478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.05374v2","created_at":"2026-06-23T02:12:45.795478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05374","created_at":"2026-06-23T02:12:45.795478+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJCRCXZR5NKJ","created_at":"2026-06-23T02:12:45.795478+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJCRCXZR5NKJEHF2","created_at":"2026-06-23T02:12:45.795478+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJCRCXZR","created_at":"2026-06-23T02:12:45.795478+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/HJCRCXZR5NKJEHF2UHYWK5B5LS","json":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS.json","graph_json":"https://pith.science/api/pith-number/HJCRCXZR5NKJEHF2UHYWK5B5LS/graph.json","events_json":"https://pith.science/api/pith-number/HJCRCXZR5NKJEHF2UHYWK5B5LS/events.json","paper":"https://pith.science/paper/HJCRCXZR"},"agent_actions":{"view_html":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS","download_json":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS.json","view_paper":"https://pith.science/paper/HJCRCXZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.05374&json=true","fetch_graph":"https://pith.science/api/pith-number/HJCRCXZR5NKJEHF2UHYWK5B5LS/graph.json","fetch_events":"https://pith.science/api/pith-number/HJCRCXZR5NKJEHF2UHYWK5B5LS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS/action/storage_attestation","attest_author":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS/action/author_attestation","sign_citation":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS/action/citation_signature","submit_replication":"https://pith.science/pith/HJCRCXZR5NKJEHF2UHYWK5B5LS/action/replication_record"}},"created_at":"2026-06-23T02:12:45.795478+00:00","updated_at":"2026-06-23T02:12:45.795478+00:00"}