{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SVLR2QKIMOEGQKE34GK6CD2LST","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"05df48ec9478ca1d131b968f3b7829afe918f5c77d625fdb3ba26516f4aa71e2","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T23:00:40Z","title_canon_sha256":"f60e1845d290c69a2d8180f1b10274be67d6a3facb6d88f2f316bb3e33edf8d5"},"schema_version":"1.0","source":{"id":"2605.23093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23093","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23093v1","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23093","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"SVLR2QKIMOEG","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"SVLR2QKIMOEGQKE3","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"SVLR2QKI","created_at":"2026-05-25T02:01:37Z"}],"graph_snapshots":[{"event_id":"sha256:f27f454eef80652d7dd78a7ff82478000535ca5f05e94c69794e092e098d86b7","target":"graph","created_at":"2026-05-25T02:01:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.23093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Philip A. Fisher, Sihong Liu, Yan Jiang","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T23:00:40Z","title":"A Comparative Evaluation of Structural Topic Models and BERTopic for Short, Open-Ended Survey Responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23093","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:efdd37d564d7ab0e3da27dccb4dff4d77e69d474435f3f478d52381f742d64c8","target":"record","created_at":"2026-05-25T02:01:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"05df48ec9478ca1d131b968f3b7829afe918f5c77d625fdb3ba26516f4aa71e2","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T23:00:40Z","title_canon_sha256":"f60e1845d290c69a2d8180f1b10274be67d6a3facb6d88f2f316bb3e33edf8d5"},"schema_version":"1.0","source":{"id":"2605.23093","kind":"arxiv","version":1}},"canonical_sha256":"95571d4148638868289be195e10f4b94f099324e15a77aec9603926f0940d852","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95571d4148638868289be195e10f4b94f099324e15a77aec9603926f0940d852","first_computed_at":"2026-05-25T02:01:37.957506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:37.957506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8E9xiN71PLtyGzpG1LtC6X/4Pilaf9um2K1Zy/suYTTrctbFoGxA/WEr7csSsYjfJl1EcBSXrYUvPukzsYmVDg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:37.958079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efdd37d564d7ab0e3da27dccb4dff4d77e69d474435f3f478d52381f742d64c8","sha256:f27f454eef80652d7dd78a7ff82478000535ca5f05e94c69794e092e098d86b7"],"state_sha256":"a406e7c5f30f6cf0397b25ae59c1455c31679fd3a7abe980ec9de3b5520133bd"}