{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGZF6HUI46EQWY4GWOCK5WHW5K","short_pith_number":"pith:LGZF6HUI","schema_version":"1.0","canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","source":{"kind":"arxiv","id":"2501.13777","version":1},"attestation_state":"computed","paper":{"title":"Topic Modeling for Free-Response Text Data from a Complex Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Namitha V.Pais, Paul A. Parker, Scott H. Holan","submitted_at":"2025-01-23T15:54:54Z","abstract_excerpt":"Topic Modeling is a popular statistical tool commonly used on textual data to identify the hidden thematic structure in a document collection based on the distribution of words. Additionally, it can be used to cluster the documents, with clusters representing distinct topics. The Mixture of Unigrams (MoU) is a standard topic model for clustering document-term data and can be particularly useful for analyzing open-ended survey responses to extract meaningful information from the underlying topics. However, with complex survey designs, where data is often collected on individual (document) chara"},"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":"2501.13777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2025-01-23T15:54:54Z","cross_cats_sorted":[],"title_canon_sha256":"2ccb2f2148ec6790eef026bc6c016ed960877852e7f1c2c5b24cafb2c19cc9ce","abstract_canon_sha256":"e1f9ec95fd707ea67d660c1ef1f9956cbb264eeb834a648fb4e6523b34684e9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:33.879327Z","signature_b64":"XkJZ/yKTksguQCoonKkvPdgRr35xA4/rMX+w22FeP4MGHNod8Zd/9bxWcS4frlXjr46SJl+W79/8vyK9mBXSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b25f1e88e7890b6386b384aed8f6eaa4d9e2d916b291f2d69e31c53c524732","last_reissued_at":"2026-07-05T10:04:33.878873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:33.878873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Modeling for Free-Response Text Data from a Complex Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Namitha V.Pais, Paul A. Parker, Scott H. Holan","submitted_at":"2025-01-23T15:54:54Z","abstract_excerpt":"Topic Modeling is a popular statistical tool commonly used on textual data to identify the hidden thematic structure in a document collection based on the distribution of words. Additionally, it can be used to cluster the documents, with clusters representing distinct topics. The Mixture of Unigrams (MoU) is a standard topic model for clustering document-term data and can be particularly useful for analyzing open-ended survey responses to extract meaningful information from the underlying topics. However, with complex survey designs, where data is often collected on individual (document) chara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13777","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/2501.13777/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":"2501.13777","created_at":"2026-07-05T10:04:33.878928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13777v1","created_at":"2026-07-05T10:04:33.878928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13777","created_at":"2026-07-05T10:04:33.878928+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGZF6HUI46EQ","created_at":"2026-07-05T10:04:33.878928+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGZF6HUI46EQWY4G","created_at":"2026-07-05T10:04:33.878928+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGZF6HUI","created_at":"2026-07-05T10:04:33.878928+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/LGZF6HUI46EQWY4GWOCK5WHW5K","json":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K.json","graph_json":"https://pith.science/api/pith-number/LGZF6HUI46EQWY4GWOCK5WHW5K/graph.json","events_json":"https://pith.science/api/pith-number/LGZF6HUI46EQWY4GWOCK5WHW5K/events.json","paper":"https://pith.science/paper/LGZF6HUI"},"agent_actions":{"view_html":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K","download_json":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K.json","view_paper":"https://pith.science/paper/LGZF6HUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13777&json=true","fetch_graph":"https://pith.science/api/pith-number/LGZF6HUI46EQWY4GWOCK5WHW5K/graph.json","fetch_events":"https://pith.science/api/pith-number/LGZF6HUI46EQWY4GWOCK5WHW5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/action/storage_attestation","attest_author":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/action/author_attestation","sign_citation":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/action/citation_signature","submit_replication":"https://pith.science/pith/LGZF6HUI46EQWY4GWOCK5WHW5K/action/replication_record"}},"created_at":"2026-07-05T10:04:33.878928+00:00","updated_at":"2026-07-05T10:04:33.878928+00:00"}