{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:73A54R2EMX7J7UDEF6Z6WVWOSZ","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":"7a9f791c67018b6a5cc634dc8da0db6e1850da1760e550e0d48d6a597c5158ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2022-11-24T09:37:45Z","title_canon_sha256":"78dda1e16c31f877a51bce477cbd400233878ea5fe3443872844427a85a0309e"},"schema_version":"1.0","source":{"id":"2211.13496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13496","created_at":"2026-07-05T05:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13496v1","created_at":"2026-07-05T05:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13496","created_at":"2026-07-05T05:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"73A54R2EMX7J","created_at":"2026-07-05T05:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"73A54R2EMX7J7UDE","created_at":"2026-07-05T05:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"73A54R2E","created_at":"2026-07-05T05:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:06d92823c6455878f053c2353fc96eddc9d8f50832f3359a11a04317814f4d10","target":"graph","created_at":"2026-07-05T05:19:22Z","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/2211.13496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adrian Leung, Deanna Needell, Joyce Chew, Keyi Cheng, Michael Lindstrom, Michael Perlmutter, Stefan Inzer, Todd Presner, Xiaoxian Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2022-11-24T09:37:45Z","title":"Multi-scale Hybridized Topic Modeling: A Pipeline for Analyzing Unstructured Text Datasets via Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13496","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":"sha256:8808ec1b40dfecfd904dbcd5911d7dc107c4fd367b31952f6d33cafbf744db2b","target":"record","created_at":"2026-07-05T05:19:22Z","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":"7a9f791c67018b6a5cc634dc8da0db6e1850da1760e550e0d48d6a597c5158ad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2022-11-24T09:37:45Z","title_canon_sha256":"78dda1e16c31f877a51bce477cbd400233878ea5fe3443872844427a85a0309e"},"schema_version":"1.0","source":{"id":"2211.13496","kind":"arxiv","version":1}},"canonical_sha256":"fec1de474465fe9fd0642fb3eb56ce96449cee02cd6c574facc494a9d5a2a508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fec1de474465fe9fd0642fb3eb56ce96449cee02cd6c574facc494a9d5a2a508","first_computed_at":"2026-07-05T05:19:22.963128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:22.963128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UF8T08QSc/0i0ZL8CioqryzcT80yzeBJ3VFZvVYhLc1R6zr9iayrdR/qwseewuKP5euQl3kcUaFayGWt9JDRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:22.963600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8808ec1b40dfecfd904dbcd5911d7dc107c4fd367b31952f6d33cafbf744db2b","sha256:06d92823c6455878f053c2353fc96eddc9d8f50832f3359a11a04317814f4d10"],"state_sha256":"a3429663e23f0d0ee4eb79fda97e8054f79fddd9bb40077ea83a89b8c265dfe0"}