{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:73A54R2EMX7J7UDEF6Z6WVWOSZ","short_pith_number":"pith:73A54R2E","schema_version":"1.0","canonical_sha256":"fec1de474465fe9fd0642fb3eb56ce96449cee02cd6c574facc494a9d5a2a508","source":{"kind":"arxiv","id":"2211.13496","version":1},"attestation_state":"computed","paper":{"title":"Multi-scale Hybridized Topic Modeling: A Pipeline for Analyzing Unstructured Text Datasets via Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Adrian Leung, Deanna Needell, Joyce Chew, Keyi Cheng, Michael Lindstrom, Michael Perlmutter, Stefan Inzer, Todd Presner, Xiaoxian Shen","submitted_at":"2022-11-24T09:37:45Z","abstract_excerpt":"We propose a multi-scale hybridized topic modeling method to find hidden topics from transcribed interviews more accurately and efficiently than traditional topic modeling methods. Our multi-scale hybridized topic modeling method (MSHTM) approaches data at different scales and performs topic modeling in a hierarchical way utilizing first a classical method, Nonnegative Matrix Factorization, and then a transformer-based method, BERTopic. It harnesses the strengths of both NMF and BERTopic. Our method can help researchers and the public better extract and interpret the interview information. Add"},"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":"2211.13496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2022-11-24T09:37:45Z","cross_cats_sorted":[],"title_canon_sha256":"78dda1e16c31f877a51bce477cbd400233878ea5fe3443872844427a85a0309e","abstract_canon_sha256":"7a9f791c67018b6a5cc634dc8da0db6e1850da1760e550e0d48d6a597c5158ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:22.963600Z","signature_b64":"UF8T08QSc/0i0ZL8CioqryzcT80yzeBJ3VFZvVYhLc1R6zr9iayrdR/qwseewuKP5euQl3kcUaFayGWt9JDRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fec1de474465fe9fd0642fb3eb56ce96449cee02cd6c574facc494a9d5a2a508","last_reissued_at":"2026-07-05T05:19:22.963128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:22.963128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-scale Hybridized Topic Modeling: A Pipeline for Analyzing Unstructured Text Datasets via Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Adrian Leung, Deanna Needell, Joyce Chew, Keyi Cheng, Michael Lindstrom, Michael Perlmutter, Stefan Inzer, Todd Presner, Xiaoxian Shen","submitted_at":"2022-11-24T09:37:45Z","abstract_excerpt":"We propose a multi-scale hybridized topic modeling method to find hidden topics from transcribed interviews more accurately and efficiently than traditional topic modeling methods. Our multi-scale hybridized topic modeling method (MSHTM) approaches data at different scales and performs topic modeling in a hierarchical way utilizing first a classical method, Nonnegative Matrix Factorization, and then a transformer-based method, BERTopic. It harnesses the strengths of both NMF and BERTopic. Our method can help researchers and the public better extract and interpret the interview information. Add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13496","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/2211.13496/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":"2211.13496","created_at":"2026-07-05T05:19:22.963179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13496v1","created_at":"2026-07-05T05:19:22.963179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13496","created_at":"2026-07-05T05:19:22.963179+00:00"},{"alias_kind":"pith_short_12","alias_value":"73A54R2EMX7J","created_at":"2026-07-05T05:19:22.963179+00:00"},{"alias_kind":"pith_short_16","alias_value":"73A54R2EMX7J7UDE","created_at":"2026-07-05T05:19:22.963179+00:00"},{"alias_kind":"pith_short_8","alias_value":"73A54R2E","created_at":"2026-07-05T05:19:22.963179+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/73A54R2EMX7J7UDEF6Z6WVWOSZ","json":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ.json","graph_json":"https://pith.science/api/pith-number/73A54R2EMX7J7UDEF6Z6WVWOSZ/graph.json","events_json":"https://pith.science/api/pith-number/73A54R2EMX7J7UDEF6Z6WVWOSZ/events.json","paper":"https://pith.science/paper/73A54R2E"},"agent_actions":{"view_html":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ","download_json":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ.json","view_paper":"https://pith.science/paper/73A54R2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13496&json=true","fetch_graph":"https://pith.science/api/pith-number/73A54R2EMX7J7UDEF6Z6WVWOSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/73A54R2EMX7J7UDEF6Z6WVWOSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ/action/storage_attestation","attest_author":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ/action/author_attestation","sign_citation":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ/action/citation_signature","submit_replication":"https://pith.science/pith/73A54R2EMX7J7UDEF6Z6WVWOSZ/action/replication_record"}},"created_at":"2026-07-05T05:19:22.963179+00:00","updated_at":"2026-07-05T05:19:22.963179+00:00"}