{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DP2SXSCSVE2PZYJ27ZW7RCZK2I","short_pith_number":"pith:DP2SXSCS","schema_version":"1.0","canonical_sha256":"1bf52bc852a934fce13afe6df88b2ad23a6d96bc54357e2e07f21a99fb59e1b5","source":{"kind":"arxiv","id":"2510.22170","version":3},"attestation_state":"computed","paper":{"title":"Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Situational judgment tests combined with multidimensional item response theory extract stable latent behavioral tendencies from persona-conditioned large language models.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandra Yost, Allen Roush, Amirali Abdullah, Grant Corser, Jacqueline Hammack, Nina Xu, Ravid Shwartz-Ziv, Shivam Raval, Shreyans Jain","submitted_at":"2025-10-25T05:45:10Z","abstract_excerpt":"Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure or superficial variation. We propose a framework to measure consistent behavioral tendencies using situational judgment tests (SJTs), multidimensional item response theory (MIRT), and structured synthetic personas, treating responses as observations of latent behavioral variables.\n  Across large-scale SJT and persona datasets, we find that persona-conditioned behaviors are stable across runs, latent trait scores predict external benchmarks (e.g., Tr"},"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":true},"canonical_record":{"source":{"id":"2510.22170","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-25T05:45:10Z","cross_cats_sorted":[],"title_canon_sha256":"2e3648f1a9798797790b145e87802116eed64f56e42beeb3158815142929d85b","abstract_canon_sha256":"57c76391ff39adb2728e1173ffc594c3c2d088bef551084767ac120cf583701a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bf52bc852a934fce13afe6df88b2ad23a6d96bc54357e2e07f21a99fb59e1b5","last_reissued_at":"2026-07-30T01:19:15.242007Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:15.242007Z"},"graph_snapshot":{"paper":{"title":"Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Situational judgment tests combined with multidimensional item response theory extract stable latent behavioral tendencies from persona-conditioned large language models.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandra Yost, Allen Roush, Amirali Abdullah, Grant Corser, Jacqueline Hammack, Nina Xu, Ravid Shwartz-Ziv, Shivam Raval, Shreyans Jain","submitted_at":"2025-10-25T05:45:10Z","abstract_excerpt":"Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure or superficial variation. We propose a framework to measure consistent behavioral tendencies using situational judgment tests (SJTs), multidimensional item response theory (MIRT), and structured synthetic personas, treating responses as observations of latent behavioral variables.\n  Across large-scale SJT and persona datasets, we find that persona-conditioned behaviors are stable across runs, latent trait scores predict external benchmarks (e.g., Tr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Persona-conditioned behaviors are stable across runs, latent trait scores predict external benchmarks (e.g., TruthfulQA, EmoBench), and MIRT reveals consistent latent structure.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That responses to situational judgment tests can be treated as observations of stable latent behavioral variables in LLMs rather than prompt-dependent or superficial patterns.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Proposes SJTs and MIRT to measure consistent latent behavioral tendencies in LLMs, showing stability and predictive validity on external benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Situational judgment tests combined with multidimensional item response theory extract stable latent behavioral tendencies from persona-conditioned large language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4b6bb8530b9e8dca1bc4011f60b4f45b99f7986e5e5005bde33fc575561e62c4"},"source":{"id":"2510.22170","kind":"arxiv","version":3},"verdict":{"id":"4ee7c384-e35e-4319-b714-ec5e106ce582","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T04:49:24.475383Z","strongest_claim":"Persona-conditioned behaviors are stable across runs, latent trait scores predict external benchmarks (e.g., TruthfulQA, EmoBench), and MIRT reveals consistent latent structure.","one_line_summary":"Proposes SJTs and MIRT to measure consistent latent behavioral tendencies in LLMs, showing stability and predictive validity on external benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That responses to situational judgment tests can be treated as observations of stable latent behavioral variables in LLMs rather than prompt-dependent or superficial patterns.","pith_extraction_headline":"Situational judgment tests combined with multidimensional item response theory extract stable latent behavioral tendencies from persona-conditioned large language models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.22170/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":2,"snapshot_sha256":"7100164c901550f5249dab3e8b9ca674d373c70582bf7081f61cfdb60b1d9a2c"},"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":"2510.22170","created_at":"2026-07-30T01:19:15.247566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.22170v3","created_at":"2026-07-30T01:19:15.247566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22170","created_at":"2026-07-30T01:19:15.247566+00:00"},{"alias_kind":"pith_short_12","alias_value":"DP2SXSCSVE2P","created_at":"2026-07-30T01:19:15.247566+00:00"},{"alias_kind":"pith_short_16","alias_value":"DP2SXSCSVE2PZYJ2","created_at":"2026-07-30T01:19:15.247566+00:00"},{"alias_kind":"pith_short_8","alias_value":"DP2SXSCS","created_at":"2026-07-30T01:19:15.247566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I","json":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I.json","graph_json":"https://pith.science/api/pith-number/DP2SXSCSVE2PZYJ27ZW7RCZK2I/graph.json","events_json":"https://pith.science/api/pith-number/DP2SXSCSVE2PZYJ27ZW7RCZK2I/events.json","paper":"https://pith.science/paper/DP2SXSCS"},"agent_actions":{"view_html":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I","download_json":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I.json","view_paper":"https://pith.science/paper/DP2SXSCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.22170&json=true","fetch_graph":"https://pith.science/api/pith-number/DP2SXSCSVE2PZYJ27ZW7RCZK2I/graph.json","fetch_events":"https://pith.science/api/pith-number/DP2SXSCSVE2PZYJ27ZW7RCZK2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I/action/storage_attestation","attest_author":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I/action/author_attestation","sign_citation":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I/action/citation_signature","submit_replication":"https://pith.science/pith/DP2SXSCSVE2PZYJ27ZW7RCZK2I/action/replication_record"}},"created_at":"2026-07-30T01:19:15.247566+00:00","updated_at":"2026-07-30T01:19:15.247566+00:00"}