{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OO2QEB3GTBRIDLALLJKEN4YLGX","short_pith_number":"pith:OO2QEB3G","schema_version":"1.0","canonical_sha256":"73b5020766986281ac0b5a5446f30b35c89f56d9170df59a298a51f704a7404d","source":{"kind":"arxiv","id":"2606.03357","version":1},"attestation_state":"computed","paper":{"title":"The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Achim Rettinger, Christoph Hau, Nils Schwager, Simon M\\\"unker","submitted_at":"2026-06-02T09:05:25Z","abstract_excerpt":"When prompting SLMs for psychometric assessments, researchers assume the outputs reflect semantic reasoning. We evaluate this premise across 13 open-weights models (0.6B to 14B parameters) using a prompt variation framework that separates semantic signals from prompt artifacts. By systematically varying personas, instructions, items, and option symbols, we find that artifactual variance frequently overpowers the semantic signal. In these cases, models predominantly reflect prompt compliance rather than simulated psychological traits. While these findings limit SLM utility in psychometrics, our"},"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":"2606.03357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T09:05:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8318e83b5f441ae15c2fb2c601e2546173d29daabddee83b98624670ca11441e","abstract_canon_sha256":"a8b32e03d1abd1fe034c494bd3e8ce4544374e5dd445083413fff08b6bb409e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:55.865451Z","signature_b64":"bOdAo3VWJD340zQApwR+YUxDbi7C3eGh4cnAd8WGuoSHZUHK5N1jo9W4JvQ5jM7tXL/OFzQPaC/1jNbHB31FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b5020766986281ac0b5a5446f30b35c89f56d9170df59a298a51f704a7404d","last_reissued_at":"2026-06-03T01:05:55.864997Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:55.864997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Achim Rettinger, Christoph Hau, Nils Schwager, Simon M\\\"unker","submitted_at":"2026-06-02T09:05:25Z","abstract_excerpt":"When prompting SLMs for psychometric assessments, researchers assume the outputs reflect semantic reasoning. We evaluate this premise across 13 open-weights models (0.6B to 14B parameters) using a prompt variation framework that separates semantic signals from prompt artifacts. By systematically varying personas, instructions, items, and option symbols, we find that artifactual variance frequently overpowers the semantic signal. In these cases, models predominantly reflect prompt compliance rather than simulated psychological traits. While these findings limit SLM utility in psychometrics, our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03357","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/2606.03357/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":"2606.03357","created_at":"2026-06-03T01:05:55.865061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03357v1","created_at":"2026-06-03T01:05:55.865061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03357","created_at":"2026-06-03T01:05:55.865061+00:00"},{"alias_kind":"pith_short_12","alias_value":"OO2QEB3GTBRI","created_at":"2026-06-03T01:05:55.865061+00:00"},{"alias_kind":"pith_short_16","alias_value":"OO2QEB3GTBRIDLAL","created_at":"2026-06-03T01:05:55.865061+00:00"},{"alias_kind":"pith_short_8","alias_value":"OO2QEB3G","created_at":"2026-06-03T01:05:55.865061+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/OO2QEB3GTBRIDLALLJKEN4YLGX","json":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX.json","graph_json":"https://pith.science/api/pith-number/OO2QEB3GTBRIDLALLJKEN4YLGX/graph.json","events_json":"https://pith.science/api/pith-number/OO2QEB3GTBRIDLALLJKEN4YLGX/events.json","paper":"https://pith.science/paper/OO2QEB3G"},"agent_actions":{"view_html":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX","download_json":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX.json","view_paper":"https://pith.science/paper/OO2QEB3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03357&json=true","fetch_graph":"https://pith.science/api/pith-number/OO2QEB3GTBRIDLALLJKEN4YLGX/graph.json","fetch_events":"https://pith.science/api/pith-number/OO2QEB3GTBRIDLALLJKEN4YLGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX/action/storage_attestation","attest_author":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX/action/author_attestation","sign_citation":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX/action/citation_signature","submit_replication":"https://pith.science/pith/OO2QEB3GTBRIDLALLJKEN4YLGX/action/replication_record"}},"created_at":"2026-06-03T01:05:55.865061+00:00","updated_at":"2026-06-03T01:05:55.865061+00:00"}