{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36UQJBQIBLD6J7XWMFBTK2UTPV","short_pith_number":"pith:36UQJBQI","schema_version":"1.0","canonical_sha256":"dfa90486080ac7e4fef66143356a937d7febe2cdef9ee771f91f5cba35c32664","source":{"kind":"arxiv","id":"2509.08920","version":1},"attestation_state":"computed","paper":{"title":"Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Jinsong Chen","submitted_at":"2025-09-10T18:31:37Z","abstract_excerpt":"This research introduces a novel psychometric method for analyzing textual data using large language models. By leveraging contextual embeddings to create contextual scores, we transform textual data into response data suitable for psychometric analysis. Treating documents as individuals and words as items, this approach provides a natural psychometric interpretation under the assumption that certain keywords, whose contextual meanings vary significantly across documents, can effectively differentiate documents within a corpus. The modeling process comprises two stages: obtaining contextual sc"},"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":"2509.08920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T18:31:37Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"95b03c31c6d5222ca5855cab0b085c8ba711524141868393da711d1bb1984ac1","abstract_canon_sha256":"8be8a32f351ad85170ef4efab7c06503f14cb141e888b9293fd1a63d0e048e88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:25.324645Z","signature_b64":"Ok8IAXi63leF19OQV3wm1jcTmRd5Wu0ZfcKmkneudEbfD5W/wk4Em5U9+5yqdBjVXvqTM16J1M6BgfjarbM7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa90486080ac7e4fef66143356a937d7febe2cdef9ee771f91f5cba35c32664","last_reissued_at":"2026-07-05T12:09:25.324134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:25.324134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Documents Are People and Words Are Items: A Psychometric Approach to Textual Data with Contextual Embeddings","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Jinsong Chen","submitted_at":"2025-09-10T18:31:37Z","abstract_excerpt":"This research introduces a novel psychometric method for analyzing textual data using large language models. By leveraging contextual embeddings to create contextual scores, we transform textual data into response data suitable for psychometric analysis. Treating documents as individuals and words as items, this approach provides a natural psychometric interpretation under the assumption that certain keywords, whose contextual meanings vary significantly across documents, can effectively differentiate documents within a corpus. The modeling process comprises two stages: obtaining contextual sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08920","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/2509.08920/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":"2509.08920","created_at":"2026-07-05T12:09:25.324194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08920v1","created_at":"2026-07-05T12:09:25.324194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08920","created_at":"2026-07-05T12:09:25.324194+00:00"},{"alias_kind":"pith_short_12","alias_value":"36UQJBQIBLD6","created_at":"2026-07-05T12:09:25.324194+00:00"},{"alias_kind":"pith_short_16","alias_value":"36UQJBQIBLD6J7XW","created_at":"2026-07-05T12:09:25.324194+00:00"},{"alias_kind":"pith_short_8","alias_value":"36UQJBQI","created_at":"2026-07-05T12:09:25.324194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07141","citing_title":"From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV","json":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV.json","graph_json":"https://pith.science/api/pith-number/36UQJBQIBLD6J7XWMFBTK2UTPV/graph.json","events_json":"https://pith.science/api/pith-number/36UQJBQIBLD6J7XWMFBTK2UTPV/events.json","paper":"https://pith.science/paper/36UQJBQI"},"agent_actions":{"view_html":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV","download_json":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV.json","view_paper":"https://pith.science/paper/36UQJBQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08920&json=true","fetch_graph":"https://pith.science/api/pith-number/36UQJBQIBLD6J7XWMFBTK2UTPV/graph.json","fetch_events":"https://pith.science/api/pith-number/36UQJBQIBLD6J7XWMFBTK2UTPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV/action/storage_attestation","attest_author":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV/action/author_attestation","sign_citation":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV/action/citation_signature","submit_replication":"https://pith.science/pith/36UQJBQIBLD6J7XWMFBTK2UTPV/action/replication_record"}},"created_at":"2026-07-05T12:09:25.324194+00:00","updated_at":"2026-07-05T12:09:25.324194+00:00"}