{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZVYZJHSPNDPCMRWEYTQENHVSAR","short_pith_number":"pith:ZVYZJHSP","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"},"canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","source":{"kind":"arxiv","id":"1508.04562","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZVYZJHSPNDPCMRWEYTQENHVSAR","target":"record","payload":{"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"},"canonical_sha256":"cd71949e4f68de2646c4c4e0469eb20472159d718a5a2a802bc2b2e8ee131192","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"},"source_kind":"arxiv","source_id":"1508.04562","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GKvgbOLJ4MRZoHWYG+6bAl+US0jW28rjDgWKyeXywh3tjPn4dx9snA/eYuSlUzAoGFQyO8r9h+vA0iJHAQwTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:22:28.253538Z"},"content_sha256":"7a3a461c97fa9c9e35ec4737fc15a8d4b8c5d62983c5175345c7eb370ebc3904","schema_version":"1.0","event_id":"sha256:7a3a461c97fa9c9e35ec4737fc15a8d4b8c5d62983c5175345c7eb370ebc3904"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZVYZJHSPNDPCMRWEYTQENHVSAR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebtrgO+heyTmSDdlkmgLFObIdHY2vXGUV8uaR0Z0KZyhtZLbsz0VqJrVLW/qut2ENpmypb9X9VwHpyenkQ5HDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:22:28.254269Z"},"content_sha256":"5fa744859008196aa46ef349df64aeaf9541360befa45e82b5d4740e5229ff89","schema_version":"1.0","event_id":"sha256:5fa744859008196aa46ef349df64aeaf9541360befa45e82b5d4740e5229ff89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/bundle.json","state_url":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:22:28Z","links":{"resolver":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR","bundle":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/bundle.json","state":"https://pith.science/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVYZJHSPNDPCMRWEYTQENHVSAR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YATP4gLSdrq1z7kfx8cH4e4WM5a2S6DgEvovjThFyfItOtqSO7irRGo2odlpFQu00kaBkwvcz8eQ2MpiDIf+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:22:28.258494Z","bundle_sha256":"f96a7243e3e3ec004b6ad9f3788875ee3c238f1d245f7a9d6fb78f0106532582"}}