{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NQXHZ64KN3EMYDKNRUXF646SXX","short_pith_number":"pith:NQXHZ64K","schema_version":"1.0","canonical_sha256":"6c2e7cfb8a6ec8cc0d4d8d2e5f73d2bdcf45448f4d8b717138278b413dca8d7c","source":{"kind":"arxiv","id":"2606.09843","version":1},"attestation_state":"computed","paper":{"title":"An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Juan Manuel Contreras","submitted_at":"2026-04-24T04:42:09Z","abstract_excerpt":"Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior. Whether this gap reflects a mismatch between LLMs and human trait constructs, or a deeper property of LLM self-report itself, has been unresolved. We constructed the first psychometric instrument whose constructs are derived bottom-up from LLM behavioral affordances via exploratory factor analysis (EFA). We administered 300 items (240 direct Likert + 60 scenario-based) spanning 12 candidate behavioral dimensions to 25 LLMs across 17 model families, each "},"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":"2606.09843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-04-24T04:42:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"38b8b7d36225c5b25106ab53e7256dba3f017e8a1bd40d00c57474a4b6a0bc83","abstract_canon_sha256":"b3aa3c897e5cb3d17d94f5ba02f681bc47c80c8b9e4ec1f68febe6da3b3ba4fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:28.061582Z","signature_b64":"w2Ec3UPKHnUc9g5dO0IN4CvSRvzIjZhJQvS9HVDRJFsTD8lSv39ciIUnyMG5hplKQ6CRApm0smOW8FOIlIIhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c2e7cfb8a6ec8cc0d4d8d2e5f73d2bdcf45448f4d8b717138278b413dca8d7c","last_reissued_at":"2026-06-10T00:08:28.060759Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:28.060759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.HC","authors_text":"Juan Manuel Contreras","submitted_at":"2026-04-24T04:42:09Z","abstract_excerpt":"Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior. Whether this gap reflects a mismatch between LLMs and human trait constructs, or a deeper property of LLM self-report itself, has been unresolved. We constructed the first psychometric instrument whose constructs are derived bottom-up from LLM behavioral affordances via exploratory factor analysis (EFA). We administered 300 items (240 direct Likert + 60 scenario-based) spanning 12 candidate behavioral dimensions to 25 LLMs across 17 model families, each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09843","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/2606.09843/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":"2606.09843","created_at":"2026-06-10T00:08:28.060886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09843v1","created_at":"2026-06-10T00:08:28.060886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09843","created_at":"2026-06-10T00:08:28.060886+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQXHZ64KN3EM","created_at":"2026-06-10T00:08:28.060886+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQXHZ64KN3EMYDKN","created_at":"2026-06-10T00:08:28.060886+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQXHZ64K","created_at":"2026-06-10T00:08:28.060886+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/NQXHZ64KN3EMYDKNRUXF646SXX","json":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX.json","graph_json":"https://pith.science/api/pith-number/NQXHZ64KN3EMYDKNRUXF646SXX/graph.json","events_json":"https://pith.science/api/pith-number/NQXHZ64KN3EMYDKNRUXF646SXX/events.json","paper":"https://pith.science/paper/NQXHZ64K"},"agent_actions":{"view_html":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX","download_json":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX.json","view_paper":"https://pith.science/paper/NQXHZ64K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09843&json=true","fetch_graph":"https://pith.science/api/pith-number/NQXHZ64KN3EMYDKNRUXF646SXX/graph.json","fetch_events":"https://pith.science/api/pith-number/NQXHZ64KN3EMYDKNRUXF646SXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX/action/storage_attestation","attest_author":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX/action/author_attestation","sign_citation":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX/action/citation_signature","submit_replication":"https://pith.science/pith/NQXHZ64KN3EMYDKNRUXF646SXX/action/replication_record"}},"created_at":"2026-06-10T00:08:28.060886+00:00","updated_at":"2026-06-10T00:08:28.060886+00:00"}