{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7YIN6ZQZNZBLZCPA2D6JCQZJM","short_pith_number":"pith:H7YIN6ZQ","schema_version":"1.0","canonical_sha256":"3ff086fb30cb7215e44f0687e48a194b2c386fe1618df7921d767c1d2102b18a","source":{"kind":"arxiv","id":"2507.04491","version":1},"attestation_state":"computed","paper":{"title":"A validity-guided workflow for robust large language model research in psychology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.HC","authors_text":"Zhicheng Lin","submitted_at":"2025-07-06T18:06:12Z","abstract_excerpt":"Large language models (LLMs) are rapidly being integrated into psychological research as research tools, evaluation targets, human simulators, and cognitive models. However, recent evidence reveals severe measurement unreliability: Personality assessments collapse under factor analysis, moral preferences reverse with punctuation changes, and theory-of-mind accuracy varies widely with trivial rephrasing. These \"measurement phantoms\"--statistical artifacts masquerading as psychological phenomena--threaten the validity of a growing body of research. Guided by the dual-validity framework that inte"},"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":"2507.04491","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-07-06T18:06:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"6be7d8c5913417ad4a7a43242be6b25620773bd18a33d0ad87b7c6b9589f11f5","abstract_canon_sha256":"7cc0e079493dd98f8960bf81f7b94ea34bb62f461b523fa2fffe80b8308bcece"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:16:48.961487Z","signature_b64":"3kTZJhCdcS4jG+lnOEJZ5LCq7+s3+LcdDqRjDP2Rpw3FVUwoJBZyt9Y3gRynxaUeAK3bvQnFBtOZ6XQBkybyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ff086fb30cb7215e44f0687e48a194b2c386fe1618df7921d767c1d2102b18a","last_reissued_at":"2026-07-03T01:16:48.960929Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:16:48.960929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A validity-guided workflow for robust large language model research in psychology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.HC","authors_text":"Zhicheng Lin","submitted_at":"2025-07-06T18:06:12Z","abstract_excerpt":"Large language models (LLMs) are rapidly being integrated into psychological research as research tools, evaluation targets, human simulators, and cognitive models. However, recent evidence reveals severe measurement unreliability: Personality assessments collapse under factor analysis, moral preferences reverse with punctuation changes, and theory-of-mind accuracy varies widely with trivial rephrasing. These \"measurement phantoms\"--statistical artifacts masquerading as psychological phenomena--threaten the validity of a growing body of research. Guided by the dual-validity framework that inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04491","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/2507.04491/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":"2507.04491","created_at":"2026-07-03T01:16:48.960996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04491v1","created_at":"2026-07-03T01:16:48.960996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04491","created_at":"2026-07-03T01:16:48.960996+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7YIN6ZQZNZB","created_at":"2026-07-03T01:16:48.960996+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7YIN6ZQZNZBLZCP","created_at":"2026-07-03T01:16:48.960996+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7YIN6ZQ","created_at":"2026-07-03T01:16:48.960996+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/H7YIN6ZQZNZBLZCPA2D6JCQZJM","json":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM.json","graph_json":"https://pith.science/api/pith-number/H7YIN6ZQZNZBLZCPA2D6JCQZJM/graph.json","events_json":"https://pith.science/api/pith-number/H7YIN6ZQZNZBLZCPA2D6JCQZJM/events.json","paper":"https://pith.science/paper/H7YIN6ZQ"},"agent_actions":{"view_html":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM","download_json":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM.json","view_paper":"https://pith.science/paper/H7YIN6ZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04491&json=true","fetch_graph":"https://pith.science/api/pith-number/H7YIN6ZQZNZBLZCPA2D6JCQZJM/graph.json","fetch_events":"https://pith.science/api/pith-number/H7YIN6ZQZNZBLZCPA2D6JCQZJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM/action/storage_attestation","attest_author":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM/action/author_attestation","sign_citation":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM/action/citation_signature","submit_replication":"https://pith.science/pith/H7YIN6ZQZNZBLZCPA2D6JCQZJM/action/replication_record"}},"created_at":"2026-07-03T01:16:48.960996+00:00","updated_at":"2026-07-03T01:16:48.960996+00:00"}