{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KFUS35FQDSZNWQVKXQGALXT4TG","short_pith_number":"pith:KFUS35FQ","schema_version":"1.0","canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","source":{"kind":"arxiv","id":"1808.08098","version":1},"attestation_state":"computed","paper":{"title":"Measuring LDA Topic Stability from Clusters of Replicated Runs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ma\\\"elick Claes, Mika M\\\"antyl\\\"a, Umar Farooq","submitted_at":"2018-08-24T11:37:40Z","abstract_excerpt":"Background: Unstructured and textual data is increasing rapidly and Latent Dirichlet Allocation (LDA) topic modeling is a popular data analysis methods for it. Past work suggests that instability of LDA topics may lead to systematic errors. Aim: We propose a method that relies on replicated LDA runs, clustering, and providing a stability metric for the topics. Method: We generate k LDA topics and replicate this process n times resulting in n*k topics. Then we use K-medioids to cluster the n*k topics to k clusters. The k clusters now represent the original LDA topics and we present them like no"},"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":"1808.08098","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-24T11:37:40Z","cross_cats_sorted":[],"title_canon_sha256":"e67a3e4bc6f1bd2910054a81e01ed9b09cde658672cc29939a21106769b98f7a","abstract_canon_sha256":"d73df10d65e64334810cb4daae4036b8ea53dd6b99962a396e5ee2025b36c845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:44.428127Z","signature_b64":"CpsZZiDLUekK6KKongrZs1FJcV/MQ6ooOpcDr/E73/SKcEfR2ZwmyeNbCQd+hZrZwDKAhdAyr7zJIjlNGwbCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51692df4b01cb2db42aabc0c05de7c9980ef02bf00e2f2cda1a612c8a457ccf0","last_reissued_at":"2026-05-18T00:06:44.427734Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:44.427734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring LDA Topic Stability from Clusters of Replicated Runs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ma\\\"elick Claes, Mika M\\\"antyl\\\"a, Umar Farooq","submitted_at":"2018-08-24T11:37:40Z","abstract_excerpt":"Background: Unstructured and textual data is increasing rapidly and Latent Dirichlet Allocation (LDA) topic modeling is a popular data analysis methods for it. Past work suggests that instability of LDA topics may lead to systematic errors. Aim: We propose a method that relies on replicated LDA runs, clustering, and providing a stability metric for the topics. Method: We generate k LDA topics and replicate this process n times resulting in n*k topics. Then we use K-medioids to cluster the n*k topics to k clusters. The k clusters now represent the original LDA topics and we present them like no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08098","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":""},"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":"1808.08098","created_at":"2026-05-18T00:06:44.427792+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08098v1","created_at":"2026-05-18T00:06:44.427792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08098","created_at":"2026-05-18T00:06:44.427792+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFUS35FQDSZN","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFUS35FQDSZNWQVK","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFUS35FQ","created_at":"2026-05-18T12:32:33.847187+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/KFUS35FQDSZNWQVKXQGALXT4TG","json":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG.json","graph_json":"https://pith.science/api/pith-number/KFUS35FQDSZNWQVKXQGALXT4TG/graph.json","events_json":"https://pith.science/api/pith-number/KFUS35FQDSZNWQVKXQGALXT4TG/events.json","paper":"https://pith.science/paper/KFUS35FQ"},"agent_actions":{"view_html":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG","download_json":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG.json","view_paper":"https://pith.science/paper/KFUS35FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08098&json=true","fetch_graph":"https://pith.science/api/pith-number/KFUS35FQDSZNWQVKXQGALXT4TG/graph.json","fetch_events":"https://pith.science/api/pith-number/KFUS35FQDSZNWQVKXQGALXT4TG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/action/storage_attestation","attest_author":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/action/author_attestation","sign_citation":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/action/citation_signature","submit_replication":"https://pith.science/pith/KFUS35FQDSZNWQVKXQGALXT4TG/action/replication_record"}},"created_at":"2026-05-18T00:06:44.427792+00:00","updated_at":"2026-05-18T00:06:44.427792+00:00"}