{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O4UEV6OCSNY7UZ76ZHWBLM3EVE","short_pith_number":"pith:O4UEV6OC","schema_version":"1.0","canonical_sha256":"77284af9c29371fa67fec9ec15b364a9344b85d2c41531501c72876f061384cd","source":{"kind":"arxiv","id":"2606.28574","version":1},"attestation_state":"computed","paper":{"title":"Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Manuel Pita","submitted_at":"2026-06-26T19:58:39Z","abstract_excerpt":"When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability leaves construct validity untouched. The instrument may be theory-naive, reaching the code through a correlate that meets none of the demands the construct's theory makes, and no current method tells that apart from genuine measurement. We propose grain calibration as a method that closes the gap. It decomposes a construct into clause-level components, tests each against the text with extractive evidence, and combines the results through an expl"},"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":"2606.28574","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T19:58:39Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"4b65e3040ed04671b41e6a6eeff13ac3a1cb8a6e03430440006355cce67bd21e","abstract_canon_sha256":"5a59efd10a548f6f8fd26ec66ccb72fc6b003d83f8fd3a24177008ea55849990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:19.572063Z","signature_b64":"nmes5hFk+NeybQVKPldEgl/NOFz5Pmomd2gc1/DFe18McWDsT2C5A1l/q5fqSC9ZPov92bz6F7yxEpXVtd9XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77284af9c29371fa67fec9ec15b364a9344b85d2c41531501c72876f061384cd","last_reissued_at":"2026-06-30T00:15:19.571688Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:19.571688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Manuel Pita","submitted_at":"2026-06-26T19:58:39Z","abstract_excerpt":"When a large language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability leaves construct validity untouched. The instrument may be theory-naive, reaching the code through a correlate that meets none of the demands the construct's theory makes, and no current method tells that apart from genuine measurement. We propose grain calibration as a method that closes the gap. It decomposes a construct into clause-level components, tests each against the text with extractive evidence, and combines the results through an expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28574","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/2606.28574/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":"2606.28574","created_at":"2026-06-30T00:15:19.571745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28574v1","created_at":"2026-06-30T00:15:19.571745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28574","created_at":"2026-06-30T00:15:19.571745+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4UEV6OCSNY7","created_at":"2026-06-30T00:15:19.571745+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4UEV6OCSNY7UZ76","created_at":"2026-06-30T00:15:19.571745+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4UEV6OC","created_at":"2026-06-30T00:15:19.571745+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/O4UEV6OCSNY7UZ76ZHWBLM3EVE","json":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE.json","graph_json":"https://pith.science/api/pith-number/O4UEV6OCSNY7UZ76ZHWBLM3EVE/graph.json","events_json":"https://pith.science/api/pith-number/O4UEV6OCSNY7UZ76ZHWBLM3EVE/events.json","paper":"https://pith.science/paper/O4UEV6OC"},"agent_actions":{"view_html":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE","download_json":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE.json","view_paper":"https://pith.science/paper/O4UEV6OC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28574&json=true","fetch_graph":"https://pith.science/api/pith-number/O4UEV6OCSNY7UZ76ZHWBLM3EVE/graph.json","fetch_events":"https://pith.science/api/pith-number/O4UEV6OCSNY7UZ76ZHWBLM3EVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE/action/storage_attestation","attest_author":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE/action/author_attestation","sign_citation":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE/action/citation_signature","submit_replication":"https://pith.science/pith/O4UEV6OCSNY7UZ76ZHWBLM3EVE/action/replication_record"}},"created_at":"2026-06-30T00:15:19.571745+00:00","updated_at":"2026-06-30T00:15:19.571745+00:00"}