{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AAY46KIG6IH3BWUBX4RJAMM4QY","short_pith_number":"pith:AAY46KIG","schema_version":"1.0","canonical_sha256":"0031cf2906f20fb0da81bf2290319c863ce6fd243bf65a9ead100cb8fd17ce3b","source":{"kind":"arxiv","id":"2510.07175","version":2},"attestation_state":"computed","paper":{"title":"Quantifying Data Contamination in Psychometric Evaluations of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonggeun Lee, Jongwook Han, Woojung Song, Yohan Jo","submitted_at":"2025-10-08T16:16:20Z","abstract_excerpt":"Recent studies apply psychometric questionnaires to Large Language Models (LLMs) to assess high-level psychological constructs such as values, personality, moral foundations, and dark traits. Although prior work has raised concerns about possible data contamination from psychometric inventories, which may threaten the reliability of such evaluations, there has been no systematic attempt to quantify the extent of this contamination. To address this gap, we propose a framework to systematically measure data contamination in psychometric evaluations of LLMs, evaluating three aspects: (1) item mem"},"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":"2510.07175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-08T16:16:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fb442d43981df89d20caebf356413423989d44cb0d10286cc76af51b8d99d71","abstract_canon_sha256":"d73aa46e091b65323262b0ee3aaf8476871e80bdc294f436d1b9e2f884770299"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:46.738544Z","signature_b64":"BguA6tGkyidYKRjXCGr6MRkmzfv4U4wdwZe8wyQ74glhoJv+7bhhom3w9Ztqk60GKZm6j5AaK1utccdT7mx8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0031cf2906f20fb0da81bf2290319c863ce6fd243bf65a9ead100cb8fd17ce3b","last_reissued_at":"2026-07-14T01:20:46.737590Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:46.737590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Data Contamination in Psychometric Evaluations of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonggeun Lee, Jongwook Han, Woojung Song, Yohan Jo","submitted_at":"2025-10-08T16:16:20Z","abstract_excerpt":"Recent studies apply psychometric questionnaires to Large Language Models (LLMs) to assess high-level psychological constructs such as values, personality, moral foundations, and dark traits. Although prior work has raised concerns about possible data contamination from psychometric inventories, which may threaten the reliability of such evaluations, there has been no systematic attempt to quantify the extent of this contamination. To address this gap, we propose a framework to systematically measure data contamination in psychometric evaluations of LLMs, evaluating three aspects: (1) item mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07175","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/2510.07175/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":"2510.07175","created_at":"2026-07-14T01:20:46.738036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.07175v2","created_at":"2026-07-14T01:20:46.738036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07175","created_at":"2026-07-14T01:20:46.738036+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAY46KIG6IH3","created_at":"2026-07-14T01:20:46.738036+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAY46KIG6IH3BWUB","created_at":"2026-07-14T01:20:46.738036+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAY46KIG","created_at":"2026-07-14T01:20:46.738036+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/AAY46KIG6IH3BWUBX4RJAMM4QY","json":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY.json","graph_json":"https://pith.science/api/pith-number/AAY46KIG6IH3BWUBX4RJAMM4QY/graph.json","events_json":"https://pith.science/api/pith-number/AAY46KIG6IH3BWUBX4RJAMM4QY/events.json","paper":"https://pith.science/paper/AAY46KIG"},"agent_actions":{"view_html":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY","download_json":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY.json","view_paper":"https://pith.science/paper/AAY46KIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.07175&json=true","fetch_graph":"https://pith.science/api/pith-number/AAY46KIG6IH3BWUBX4RJAMM4QY/graph.json","fetch_events":"https://pith.science/api/pith-number/AAY46KIG6IH3BWUBX4RJAMM4QY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY/action/storage_attestation","attest_author":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY/action/author_attestation","sign_citation":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY/action/citation_signature","submit_replication":"https://pith.science/pith/AAY46KIG6IH3BWUBX4RJAMM4QY/action/replication_record"}},"created_at":"2026-07-14T01:20:46.738036+00:00","updated_at":"2026-07-14T01:20:46.738036+00:00"}