{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PD32WJXRFAZUT4R6WHT3ZPDQTX","short_pith_number":"pith:PD32WJXR","schema_version":"1.0","canonical_sha256":"78f7ab26f1283349f23eb1e7bcbc709dff969da9028d321958b54f913882779e","source":{"kind":"arxiv","id":"1704.07016","version":3},"attestation_state":"computed","paper":{"title":"Using SVD for Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Minzhe Wang, Zheng Tracy Ke","submitted_at":"2017-04-24T01:45:51Z","abstract_excerpt":"The probabilistic topic model imposes a low-rank structure on the expectation of the corpus matrix. Therefore, singular value decomposition (SVD) is a natural tool of dimension reduction. We propose an SVD-based method for estimating a topic model. Our method constructs an estimate of the topic matrix from only a few leading singular vectors of the corpus matrix, and has a great advantage in memory use and computational cost for large-scale corpora. The core ideas behind our method include a pre-SVD normalization to tackle severe word frequency heterogeneity, a post-SVD normalization to create"},"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":"1704.07016","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-04-24T01:45:51Z","cross_cats_sorted":[],"title_canon_sha256":"fd67969cc8d0c9f154767496a70543494f6161fd772085092309175cadf81f3e","abstract_canon_sha256":"a86017d22ad7f808f992b20361ae7f692c298489f91892e5a6055b97c5a28936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:52:20.999485Z","signature_b64":"UyIiowc9NOor/z1bUiW7KzZoJqpROBMb5t/A7eBhy6uua+LWr/CIjbwyLCIip47Smry0+mMOo9oEC4vpwa1LAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f7ab26f1283349f23eb1e7bcbc709dff969da9028d321958b54f913882779e","last_reissued_at":"2026-07-05T04:52:20.998980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:52:20.998980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using SVD for Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Minzhe Wang, Zheng Tracy Ke","submitted_at":"2017-04-24T01:45:51Z","abstract_excerpt":"The probabilistic topic model imposes a low-rank structure on the expectation of the corpus matrix. Therefore, singular value decomposition (SVD) is a natural tool of dimension reduction. We propose an SVD-based method for estimating a topic model. Our method constructs an estimate of the topic matrix from only a few leading singular vectors of the corpus matrix, and has a great advantage in memory use and computational cost for large-scale corpora. The core ideas behind our method include a pre-SVD normalization to tackle severe word frequency heterogeneity, a post-SVD normalization to create"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07016","kind":"arxiv","version":3},"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/1704.07016/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":"1704.07016","created_at":"2026-07-05T04:52:20.999038+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07016v3","created_at":"2026-07-05T04:52:20.999038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07016","created_at":"2026-07-05T04:52:20.999038+00:00"},{"alias_kind":"pith_short_12","alias_value":"PD32WJXRFAZU","created_at":"2026-07-05T04:52:20.999038+00:00"},{"alias_kind":"pith_short_16","alias_value":"PD32WJXRFAZUT4R6","created_at":"2026-07-05T04:52:20.999038+00:00"},{"alias_kind":"pith_short_8","alias_value":"PD32WJXR","created_at":"2026-07-05T04:52:20.999038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14477","citing_title":"Graph Topic Modeling for Documents with Spatial or Covariate Dependencies","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX","json":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX.json","graph_json":"https://pith.science/api/pith-number/PD32WJXRFAZUT4R6WHT3ZPDQTX/graph.json","events_json":"https://pith.science/api/pith-number/PD32WJXRFAZUT4R6WHT3ZPDQTX/events.json","paper":"https://pith.science/paper/PD32WJXR"},"agent_actions":{"view_html":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX","download_json":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX.json","view_paper":"https://pith.science/paper/PD32WJXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07016&json=true","fetch_graph":"https://pith.science/api/pith-number/PD32WJXRFAZUT4R6WHT3ZPDQTX/graph.json","fetch_events":"https://pith.science/api/pith-number/PD32WJXRFAZUT4R6WHT3ZPDQTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX/action/storage_attestation","attest_author":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX/action/author_attestation","sign_citation":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX/action/citation_signature","submit_replication":"https://pith.science/pith/PD32WJXRFAZUT4R6WHT3ZPDQTX/action/replication_record"}},"created_at":"2026-07-05T04:52:20.999038+00:00","updated_at":"2026-07-05T04:52:20.999038+00:00"}