{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S52E3TUQMH7TACJ67ZGNIEE4TF","short_pith_number":"pith:S52E3TUQ","schema_version":"1.0","canonical_sha256":"97744dce9061ff30093efe4cd4109c99579459ff250bf86e840781399ffb22d7","source":{"kind":"arxiv","id":"2608.04536","version":1},"attestation_state":"computed","paper":{"title":"From Research Questions to Columns: Operationalization-Aware Data Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Houming Chen, H. V. Jagadish","submitted_at":"2026-08-05T07:12:33Z","abstract_excerpt":"Researchers often approach a data repository with an abstract concept and ask which columns can measure it. Useful columns may not resemble the query; they may matter only as complementary indicators in a defensible measure. This need differs from schema linking and column retrieval, which begin from more explicit needs and reward direct relevance. We define operationalization-aware data discovery (OADD): given a broad question and a database, optionally under a scope constraint, OADD jointly determines how focal concepts can be measured with available data and identifies supporting columns.\n "},"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":"2608.04536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-05T07:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"09890ec97ee5cc946cccab94546d3f729846570ed6b3a02c7c159e2d7becffb2","abstract_canon_sha256":"acb97cbcde09e97f994e8808935a054fe63be0d527c69151ee42c4af25030192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:47.908544Z","signature_b64":"KDwZPrxgFbDal4sHD4iozWzfuxe8n8wc/MeGO2JK+C+2GulwjmERNDoXqzNo8cEo1oB9Wg1iDgE77XbJSvKcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97744dce9061ff30093efe4cd4109c99579459ff250bf86e840781399ffb22d7","last_reissued_at":"2026-08-06T01:35:47.907069Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:47.907069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Research Questions to Columns: Operationalization-Aware Data Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Houming Chen, H. V. Jagadish","submitted_at":"2026-08-05T07:12:33Z","abstract_excerpt":"Researchers often approach a data repository with an abstract concept and ask which columns can measure it. Useful columns may not resemble the query; they may matter only as complementary indicators in a defensible measure. This need differs from schema linking and column retrieval, which begin from more explicit needs and reward direct relevance. We define operationalization-aware data discovery (OADD): given a broad question and a database, optionally under a scope constraint, OADD jointly determines how focal concepts can be measured with available data and identifies supporting columns.\n "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04536","kind":"arxiv","version":1},"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/2608.04536/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":"2608.04536","created_at":"2026-08-06T01:35:47.908869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04536v1","created_at":"2026-08-06T01:35:47.908869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04536","created_at":"2026-08-06T01:35:47.908869+00:00"},{"alias_kind":"pith_short_12","alias_value":"S52E3TUQMH7T","created_at":"2026-08-06T01:35:47.908869+00:00"},{"alias_kind":"pith_short_16","alias_value":"S52E3TUQMH7TACJ6","created_at":"2026-08-06T01:35:47.908869+00:00"},{"alias_kind":"pith_short_8","alias_value":"S52E3TUQ","created_at":"2026-08-06T01:35:47.908869+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/S52E3TUQMH7TACJ67ZGNIEE4TF","json":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF.json","graph_json":"https://pith.science/api/pith-number/S52E3TUQMH7TACJ67ZGNIEE4TF/graph.json","events_json":"https://pith.science/api/pith-number/S52E3TUQMH7TACJ67ZGNIEE4TF/events.json","paper":"https://pith.science/paper/S52E3TUQ"},"agent_actions":{"view_html":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF","download_json":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF.json","view_paper":"https://pith.science/paper/S52E3TUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04536&json=true","fetch_graph":"https://pith.science/api/pith-number/S52E3TUQMH7TACJ67ZGNIEE4TF/graph.json","fetch_events":"https://pith.science/api/pith-number/S52E3TUQMH7TACJ67ZGNIEE4TF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF/action/storage_attestation","attest_author":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF/action/author_attestation","sign_citation":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF/action/citation_signature","submit_replication":"https://pith.science/pith/S52E3TUQMH7TACJ67ZGNIEE4TF/action/replication_record"}},"created_at":"2026-08-06T01:35:47.908869+00:00","updated_at":"2026-08-06T01:35:47.908869+00:00"}