{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2008:WBAMIG7D5ES5MH6JHDUZ73LQHF","short_pith_number":"pith:WBAMIG7D","schema_version":"1.0","canonical_sha256":"b040c41be3e925d61fc938e99fed703968c951dce78006503a68c4338fe677c7","source":{"kind":"arxiv","id":"0808.0973","version":1},"attestation_state":"computed","paper":{"title":"Text Modeling using Unsupervised Topic Models and Concept Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chaitanya Chemudugunta, Mark Steyvers, Padhraic Smyth","submitted_at":"2008-08-07T07:59:29Z","abstract_excerpt":"Statistical topic models provide a general data-driven framework for automated discovery of high-level knowledge from large collections of text documents. While topic models can potentially discover a broad range of themes in a data set, the interpretability of the learned topics is not always ideal. Human-defined concepts, on the other hand, tend to be semantically richer due to careful selection of words to define concepts but they tend not to cover the themes in a data set exhaustively. In this paper, we propose a probabilistic framework to combine a hierarchy of human-defined semantic conc"},"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":"0808.0973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2008-08-07T07:59:29Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"23e247c2d261dbed4cde9e047b8d2cbd89bd9694d0a40b1636074d0a8531e7b9","abstract_canon_sha256":"a1276006d3bf6de255a7c5f7924e3bd8ccf601741b6fc1b6c581e0dbe224f28f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:13:28.848899Z","signature_b64":"5G9+OpBPyvS3v5QXM1d6/h0HNteVduJspqp5hJC5RWfJl24LSE61wrHyfKm/hKRk/4jDJH4C0YhNyliQC32hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b040c41be3e925d61fc938e99fed703968c951dce78006503a68c4338fe677c7","last_reissued_at":"2026-07-04T15:13:28.848567Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:13:28.848567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Modeling using Unsupervised Topic Models and Concept Hierarchies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chaitanya Chemudugunta, Mark Steyvers, Padhraic Smyth","submitted_at":"2008-08-07T07:59:29Z","abstract_excerpt":"Statistical topic models provide a general data-driven framework for automated discovery of high-level knowledge from large collections of text documents. While topic models can potentially discover a broad range of themes in a data set, the interpretability of the learned topics is not always ideal. Human-defined concepts, on the other hand, tend to be semantically richer due to careful selection of words to define concepts but they tend not to cover the themes in a data set exhaustively. In this paper, we propose a probabilistic framework to combine a hierarchy of human-defined semantic conc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0808.0973","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/0808.0973/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":"0808.0973","created_at":"2026-07-04T15:13:28.848625+00:00"},{"alias_kind":"arxiv_version","alias_value":"0808.0973v1","created_at":"2026-07-04T15:13:28.848625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0808.0973","created_at":"2026-07-04T15:13:28.848625+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBAMIG7D5ES5","created_at":"2026-07-04T15:13:28.848625+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBAMIG7D5ES5MH6J","created_at":"2026-07-04T15:13:28.848625+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBAMIG7D","created_at":"2026-07-04T15:13:28.848625+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/WBAMIG7D5ES5MH6JHDUZ73LQHF","json":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF.json","graph_json":"https://pith.science/api/pith-number/WBAMIG7D5ES5MH6JHDUZ73LQHF/graph.json","events_json":"https://pith.science/api/pith-number/WBAMIG7D5ES5MH6JHDUZ73LQHF/events.json","paper":"https://pith.science/paper/WBAMIG7D"},"agent_actions":{"view_html":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF","download_json":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF.json","view_paper":"https://pith.science/paper/WBAMIG7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0808.0973&json=true","fetch_graph":"https://pith.science/api/pith-number/WBAMIG7D5ES5MH6JHDUZ73LQHF/graph.json","fetch_events":"https://pith.science/api/pith-number/WBAMIG7D5ES5MH6JHDUZ73LQHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF/action/storage_attestation","attest_author":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF/action/author_attestation","sign_citation":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF/action/citation_signature","submit_replication":"https://pith.science/pith/WBAMIG7D5ES5MH6JHDUZ73LQHF/action/replication_record"}},"created_at":"2026-07-04T15:13:28.848625+00:00","updated_at":"2026-07-04T15:13:28.848625+00:00"}