{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SVLR2QKIMOEGQKE34GK6CD2LST","short_pith_number":"pith:SVLR2QKI","schema_version":"1.0","canonical_sha256":"95571d4148638868289be195e10f4b94f099324e15a77aec9603926f0940d852","source":{"kind":"arxiv","id":"2605.23093","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Philip A. Fisher, Sihong Liu, Yan Jiang","submitted_at":"2026-05-21T23:00:40Z","abstract_excerpt":"Topic modeling in applied psychology increasingly spans two methodological traditions: probabilistic bag-of-words models and newer embedding-based approaches. Yet many evaluations of these methods rely on longer and cleaner benchmark corpora, leaving less guidance for short, open-ended survey responses. This paper compares Structural Topic Models (STM), a probabilistic topic model, and BERTopic, an embedding-based model, for analyzing open-ended survey responses. We evaluated three STM conditions and five BERTopic conditions, varying typographical correction, stemming, embedding choice, and co"},"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":"2605.23093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T23:00:40Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"f60e1845d290c69a2d8180f1b10274be67d6a3facb6d88f2f316bb3e33edf8d5","abstract_canon_sha256":"05df48ec9478ca1d131b968f3b7829afe918f5c77d625fdb3ba26516f4aa71e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:37.958079Z","signature_b64":"8E9xiN71PLtyGzpG1LtC6X/4Pilaf9um2K1Zy/suYTTrctbFoGxA/WEr7csSsYjfJl1EcBSXrYUvPukzsYmVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95571d4148638868289be195e10f4b94f099324e15a77aec9603926f0940d852","last_reissued_at":"2026-05-25T02:01:37.957506Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:37.957506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Philip A. Fisher, Sihong Liu, Yan Jiang","submitted_at":"2026-05-21T23:00:40Z","abstract_excerpt":"Topic modeling in applied psychology increasingly spans two methodological traditions: probabilistic bag-of-words models and newer embedding-based approaches. Yet many evaluations of these methods rely on longer and cleaner benchmark corpora, leaving less guidance for short, open-ended survey responses. This paper compares Structural Topic Models (STM), a probabilistic topic model, and BERTopic, an embedding-based model, for analyzing open-ended survey responses. We evaluated three STM conditions and five BERTopic conditions, varying typographical correction, stemming, embedding choice, and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23093","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/2605.23093/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":"2605.23093","created_at":"2026-05-25T02:01:37.957602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23093v1","created_at":"2026-05-25T02:01:37.957602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23093","created_at":"2026-05-25T02:01:37.957602+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVLR2QKIMOEG","created_at":"2026-05-25T02:01:37.957602+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVLR2QKIMOEGQKE3","created_at":"2026-05-25T02:01:37.957602+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVLR2QKI","created_at":"2026-05-25T02:01:37.957602+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/SVLR2QKIMOEGQKE34GK6CD2LST","json":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST.json","graph_json":"https://pith.science/api/pith-number/SVLR2QKIMOEGQKE34GK6CD2LST/graph.json","events_json":"https://pith.science/api/pith-number/SVLR2QKIMOEGQKE34GK6CD2LST/events.json","paper":"https://pith.science/paper/SVLR2QKI"},"agent_actions":{"view_html":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST","download_json":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST.json","view_paper":"https://pith.science/paper/SVLR2QKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23093&json=true","fetch_graph":"https://pith.science/api/pith-number/SVLR2QKIMOEGQKE34GK6CD2LST/graph.json","fetch_events":"https://pith.science/api/pith-number/SVLR2QKIMOEGQKE34GK6CD2LST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST/action/storage_attestation","attest_author":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST/action/author_attestation","sign_citation":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST/action/citation_signature","submit_replication":"https://pith.science/pith/SVLR2QKIMOEGQKE34GK6CD2LST/action/replication_record"}},"created_at":"2026-05-25T02:01:37.957602+00:00","updated_at":"2026-05-25T02:01:37.957602+00:00"}