{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZVYZJHSPNDPCMRWEYTQENHVSAR","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":"fe0f179e256fbd8f6fd8d382440ec05b4d7095c54796c538bea70cc79aeb4518","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-19T08:30:37Z","title_canon_sha256":"3d0fbbecba0f137bcff5670ee9f20f1e2fa0a593400888a04b47d2aa7096795d"},"schema_version":"1.0","source":{"id":"1508.04562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.04562","created_at":"2026-05-18T01:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"1508.04562v1","created_at":"2026-05-18T01:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.04562","created_at":"2026-05-18T01:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZVYZJHSPNDPC","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZVYZJHSPNDPCMRWE","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZVYZJHSP","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:5fa744859008196aa46ef349df64aeaf9541360befa45e82b5d4740e5229ff89","target":"graph","created_at":"2026-05-18T01:35:02Z","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"},"paper":{"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","authors_text":"Aaron Gerow, Jaan Altosaar, James Evans, Jingwei Zhang, Richard Jean So","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-19T08:30:37Z","title":"Fast, Flexible Models for Discovering Topic Correlation across Weakly-Related Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.04562","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":"sha256:7a3a461c97fa9c9e35ec4737fc15a8d4b8c5d62983c5175345c7eb370ebc3904","target":"record","created_at":"2026-05-18T01:35:02Z","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":"fe0f179e256fbd8f6fd8d382440ec05b4d7095c54796c538bea70cc79aeb4518","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-19T08:30:37Z","title_canon_sha256":"3d0fbbecba0f137bcff5670ee9f20f1e2fa0a593400888a04b47d2aa7096795d"},"schema_version":"1.0","source":{"id":"1508.04562","kind":"arxiv","version":1}},"canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","first_computed_at":"2026-05-18T01:35:02.429582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:02.429582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IB8wTamWJxvk0sAvFieJ8f66Ij2bg28FeMRcAiFZS5j1pFR43HzsSAMyIgz8FXWcMIeBzCFREmA4f1eIM3ptBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:02.430112Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.04562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a3a461c97fa9c9e35ec4737fc15a8d4b8c5d62983c5175345c7eb370ebc3904","sha256:5fa744859008196aa46ef349df64aeaf9541360befa45e82b5d4740e5229ff89"],"state_sha256":"bbf1a1fac48a594f47750f0837ab1ea18aa85b610ad4ec4fb50c39c41d9d7d8d"}