{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3YL6O3M73LJEE5UBTW26N7UNQU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2ad0db08b0721c416ddfa32b2fa6b2cb6165b83d3639d8b8592216243786e0b5","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-03T17:33:24Z","title_canon_sha256":"ed56eb84ba371e77c2f495e7839e4f953da66c4dd9fe56d09abc413e8842c639"},"schema_version":"1.0","source":{"id":"2507.02819","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02819","created_at":"2026-07-05T11:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02819v3","created_at":"2026-07-05T11:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02819","created_at":"2026-07-05T11:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"3YL6O3M73LJE","created_at":"2026-07-05T11:56:05Z"},{"alias_kind":"pith_short_16","alias_value":"3YL6O3M73LJEE5UB","created_at":"2026-07-05T11:56:05Z"},{"alias_kind":"pith_short_8","alias_value":"3YL6O3M7","created_at":"2026-07-05T11:56:05Z"}],"graph_snapshots":[{"event_id":"sha256:548776fe97ea40b12a8de57755bf42e86407f39f4ec1a8ab63f8c50bba903e02","target":"graph","created_at":"2026-07-05T11:56:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.02819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Devansh Saxena, Kenneth Holstein, Luke Guerdan, Stevie Chancellor, Zhiwei Steven Wu","cross_cats":["cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-03T17:33:24Z","title":"Measurement as Bricolage: Examining How Data Scientists Construct Target Variables for Predictive Modeling Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02819","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b1ea12fcb0433884d40b27d8d2edca2cbb740f6f2db2990997a07a27f6b6175","target":"record","created_at":"2026-07-05T11:56:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2ad0db08b0721c416ddfa32b2fa6b2cb6165b83d3639d8b8592216243786e0b5","cross_cats_sorted":["cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-03T17:33:24Z","title_canon_sha256":"ed56eb84ba371e77c2f495e7839e4f953da66c4dd9fe56d09abc413e8842c639"},"schema_version":"1.0","source":{"id":"2507.02819","kind":"arxiv","version":3}},"canonical_sha256":"de17e76d9fdad24276819db5e6fe8d851be7a19abcf61a529b17425d957a4fd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de17e76d9fdad24276819db5e6fe8d851be7a19abcf61a529b17425d957a4fd8","first_computed_at":"2026-07-05T11:56:05.330800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:05.330800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GGGc6GcVygVX0D1u92fkHl8upkj3WkVDQ+BRQ2dRDLOG3WoQM5j02eeQqLPOp1NMo4Fkf5OwF3FNgWTWmpNMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:05.331205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02819","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b1ea12fcb0433884d40b27d8d2edca2cbb740f6f2db2990997a07a27f6b6175","sha256:548776fe97ea40b12a8de57755bf42e86407f39f4ec1a8ab63f8c50bba903e02"],"state_sha256":"5aa8549e451406c2fa4333acb940cde798ff73b18ceb9a51bd8f89eac2e47ca5"}