{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YL6O3M73LJEE5UBTW26N7UNQU","short_pith_number":"pith:3YL6O3M7","schema_version":"1.0","canonical_sha256":"de17e76d9fdad24276819db5e6fe8d851be7a19abcf61a529b17425d957a4fd8","source":{"kind":"arxiv","id":"2507.02819","version":3},"attestation_state":"computed","paper":{"title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.HC","authors_text":"Devansh Saxena, Kenneth Holstein, Luke Guerdan, Stevie Chancellor, Zhiwei Steven Wu","submitted_at":"2025-07-03T17:33:24Z","abstract_excerpt":"Data scientists often formulate predictive modeling tasks involving fuzzy, hard-to-define concepts, such as the \"authenticity\" of student writing or the \"healthcare need\" of a patient. Yet the process by which data scientists translate fuzzy concepts into a concrete, proxy target variable remains poorly understood. We interview fifteen data scientists in education (N=8) and healthcare (N=7) to understand how they construct target variables for predictive modeling tasks. Our findings suggest that data scientists construct target variables through a bricolage process, in which they use creative "},"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":"2507.02819","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-03T17:33:24Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"ed56eb84ba371e77c2f495e7839e4f953da66c4dd9fe56d09abc413e8842c639","abstract_canon_sha256":"2ad0db08b0721c416ddfa32b2fa6b2cb6165b83d3639d8b8592216243786e0b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:05.331205Z","signature_b64":"GGGc6GcVygVX0D1u92fkHl8upkj3WkVDQ+BRQ2dRDLOG3WoQM5j02eeQqLPOp1NMo4Fkf5OwF3FNgWTWmpNMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de17e76d9fdad24276819db5e6fe8d851be7a19abcf61a529b17425d957a4fd8","last_reissued_at":"2026-07-05T11:56:05.330800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:05.330800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.HC","authors_text":"Devansh Saxena, Kenneth Holstein, Luke Guerdan, Stevie Chancellor, Zhiwei Steven Wu","submitted_at":"2025-07-03T17:33:24Z","abstract_excerpt":"Data scientists often formulate predictive modeling tasks involving fuzzy, hard-to-define concepts, such as the \"authenticity\" of student writing or the \"healthcare need\" of a patient. Yet the process by which data scientists translate fuzzy concepts into a concrete, proxy target variable remains poorly understood. We interview fifteen data scientists in education (N=8) and healthcare (N=7) to understand how they construct target variables for predictive modeling tasks. Our findings suggest that data scientists construct target variables through a bricolage process, in which they use creative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02819","kind":"arxiv","version":3},"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/2507.02819/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":"2507.02819","created_at":"2026-07-05T11:56:05.330858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02819v3","created_at":"2026-07-05T11:56:05.330858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02819","created_at":"2026-07-05T11:56:05.330858+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YL6O3M73LJE","created_at":"2026-07-05T11:56:05.330858+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YL6O3M73LJEE5UB","created_at":"2026-07-05T11:56:05.330858+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YL6O3M7","created_at":"2026-07-05T11:56:05.330858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28053","citing_title":"To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU","json":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU.json","graph_json":"https://pith.science/api/pith-number/3YL6O3M73LJEE5UBTW26N7UNQU/graph.json","events_json":"https://pith.science/api/pith-number/3YL6O3M73LJEE5UBTW26N7UNQU/events.json","paper":"https://pith.science/paper/3YL6O3M7"},"agent_actions":{"view_html":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU","download_json":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU.json","view_paper":"https://pith.science/paper/3YL6O3M7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02819&json=true","fetch_graph":"https://pith.science/api/pith-number/3YL6O3M73LJEE5UBTW26N7UNQU/graph.json","fetch_events":"https://pith.science/api/pith-number/3YL6O3M73LJEE5UBTW26N7UNQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU/action/storage_attestation","attest_author":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU/action/author_attestation","sign_citation":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU/action/citation_signature","submit_replication":"https://pith.science/pith/3YL6O3M73LJEE5UBTW26N7UNQU/action/replication_record"}},"created_at":"2026-07-05T11:56:05.330858+00:00","updated_at":"2026-07-05T11:56:05.330858+00:00"}