{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FGT5GWFVI3LPLZ6KIUQ3FSOWNF","short_pith_number":"pith:FGT5GWFV","schema_version":"1.0","canonical_sha256":"29a7d358b546d6f5e7ca4521b2c9d66949899f85fb1dac0aa218c16834931433","source":{"kind":"arxiv","id":"2508.14858","version":2},"attestation_state":"computed","paper":{"title":"Data Fusion for High-Resolution Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Amy Guan, Joshua Salomon, Marissa Reitsma, Roshni Sahoo, Stefan Wager","submitted_at":"2025-08-20T17:12:26Z","abstract_excerpt":"High-resolution estimates of population health indicators are critical for precision public health. We propose a method for high-resolution estimation that fuses distinct data sources: an unbiased, low-resolution data source (e.g. aggregated administrative data) and a potentially biased, high-resolution data source (e.g. individual-level online survey responses). We assume that the potentially biased, high-resolution data source is generated from the population under a model of sampling bias where observables can have arbitrary impact on the probability of response but the difference in the lo"},"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":"2508.14858","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-08-20T17:12:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d2e7a6f51d5bfc81a7186c9e41c4571d1c056ac20b316369282beb76fc923ba","abstract_canon_sha256":"b3fa7a5ccf69e8073b4fceaf147a770ff6ab06e5d639ba0f5e9fbd2fe3d7a5af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:15.488361Z","signature_b64":"UEE6UDgthwZFUS/Vd1MorOW+sX2X07qo7sn4qb4NqMwbLy4/Ln7D7DzoE0v77ybk/nlWOWoDKVs3HBClQCMzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a7d358b546d6f5e7ca4521b2c9d66949899f85fb1dac0aa218c16834931433","last_reissued_at":"2026-06-12T01:08:15.487363Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:15.487363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Fusion for High-Resolution Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Amy Guan, Joshua Salomon, Marissa Reitsma, Roshni Sahoo, Stefan Wager","submitted_at":"2025-08-20T17:12:26Z","abstract_excerpt":"High-resolution estimates of population health indicators are critical for precision public health. We propose a method for high-resolution estimation that fuses distinct data sources: an unbiased, low-resolution data source (e.g. aggregated administrative data) and a potentially biased, high-resolution data source (e.g. individual-level online survey responses). We assume that the potentially biased, high-resolution data source is generated from the population under a model of sampling bias where observables can have arbitrary impact on the probability of response but the difference in the lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14858","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/2508.14858/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":"2508.14858","created_at":"2026-06-12T01:08:15.487500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14858v2","created_at":"2026-06-12T01:08:15.487500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14858","created_at":"2026-06-12T01:08:15.487500+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGT5GWFVI3LP","created_at":"2026-06-12T01:08:15.487500+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGT5GWFVI3LPLZ6K","created_at":"2026-06-12T01:08:15.487500+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGT5GWFV","created_at":"2026-06-12T01:08:15.487500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.07285","citing_title":"Transporting treatment effects by calibrating large-scale observational outcomes","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07285","citing_title":"Transporting treatment effects by calibrating large-scale observational outcomes","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF","json":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF.json","graph_json":"https://pith.science/api/pith-number/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/graph.json","events_json":"https://pith.science/api/pith-number/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/events.json","paper":"https://pith.science/paper/FGT5GWFV"},"agent_actions":{"view_html":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF","download_json":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF.json","view_paper":"https://pith.science/paper/FGT5GWFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14858&json=true","fetch_graph":"https://pith.science/api/pith-number/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/graph.json","fetch_events":"https://pith.science/api/pith-number/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/action/storage_attestation","attest_author":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/action/author_attestation","sign_citation":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/action/citation_signature","submit_replication":"https://pith.science/pith/FGT5GWFVI3LPLZ6KIUQ3FSOWNF/action/replication_record"}},"created_at":"2026-06-12T01:08:15.487500+00:00","updated_at":"2026-06-12T01:08:15.487500+00:00"}