{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZVYZJHSPNDPCMRWEYTQENHVSAR","short_pith_number":"pith:ZVYZJHSP","schema_version":"1.0","canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","source":{"kind":"arxiv","id":"1508.04562","version":1},"attestation_state":"computed","paper":{"title":"Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aaron Gerow, Jaan Altosaar, James Evans, Jingwei Zhang, Richard Jean So","submitted_at":"2015-08-19T08:30:37Z","abstract_excerpt":"Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models. This paper introduces two probabilistic topic models, Correlated LDA (C-LDA) and Correlated HDP (C-HDP). These address problems that can arise when analyzing large, asymmetric, and potentially weakly-related collections. Topic correlations in weakly-related collections typically lie in the tail of the topic distribution, where they would be overlooked by models unable to fit large numbers of topics. To efficiently model th"},"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":"1508.04562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-19T08:30:37Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3d0fbbecba0f137bcff5670ee9f20f1e2fa0a593400888a04b47d2aa7096795d","abstract_canon_sha256":"fe0f179e256fbd8f6fd8d382440ec05b4d7095c54796c538bea70cc79aeb4518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:02.430112Z","signature_b64":"IB8wTamWJxvk0sAvFieJ8f66Ij2bg28FeMRcAiFZS5j1pFR43HzsSAMyIgz8FXWcMIeBzCFREmA4f1eIM3ptBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","last_reissued_at":"2026-05-18T01:35:02.429582Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:02.429582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aaron Gerow, Jaan Altosaar, James Evans, Jingwei Zhang, Richard Jean So","submitted_at":"2015-08-19T08:30:37Z","abstract_excerpt":"Weak topic correlation across document collections with different numbers of topics in individual collections presents challenges for existing cross-collection topic models. This paper introduces two probabilistic topic models, Correlated LDA (C-LDA) and Correlated HDP (C-HDP). These address problems that can arise when analyzing large, asymmetric, and potentially weakly-related collections. Topic correlations in weakly-related collections typically lie in the tail of the topic distribution, where they would be overlooked by models unable to fit large numbers of topics. To efficiently model th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.04562","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":"1508.04562","created_at":"2026-05-18T01:35:02.429650+00:00"},{"alias_kind":"arxiv_version","alias_value":"1508.04562v1","created_at":"2026-05-18T01:35:02.429650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.04562","created_at":"2026-05-18T01:35:02.429650+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVYZJHSPNDPC","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVYZJHSPNDPCMRWE","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVYZJHSP","created_at":"2026-05-18T12:29:52.810259+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/ZVYZJHSPNDPCMRWEYTQENHVSAR","json":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR.json","graph_json":"https://pith.science/api/pith-number/ZVYZJHSPNDPCMRWEYTQENHVSAR/graph.json","events_json":"https://pith.science/api/pith-number/ZVYZJHSPNDPCMRWEYTQENHVSAR/events.json","paper":"https://pith.science/paper/ZVYZJHSP"},"agent_actions":{"view_html":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR","download_json":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR.json","view_paper":"https://pith.science/paper/ZVYZJHSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1508.04562&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVYZJHSPNDPCMRWEYTQENHVSAR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVYZJHSPNDPCMRWEYTQENHVSAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/action/storage_attestation","attest_author":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/action/author_attestation","sign_citation":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/action/citation_signature","submit_replication":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/action/replication_record"}},"created_at":"2026-05-18T01:35:02.429650+00:00","updated_at":"2026-05-18T01:35:02.429650+00:00"}