{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I3TNF43FW557H6GQ43UC5B2724","short_pith_number":"pith:I3TNF43F","canonical_record":{"source":{"id":"1806.00793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-03T13:22:10Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"61dff45eb6b49744d0030ca19af2a1d2f787df61b585e3ad2d54483157ce5bfe","abstract_canon_sha256":"ce22398a43117b36a86e52071ecc9d19a6f7d052985123ddff239abd2a03c589"},"schema_version":"1.0"},"canonical_sha256":"46e6d2f365b77bf3f8d0e6e82e875fd7068501379858541fd120941cb85e2b67","source":{"kind":"arxiv","id":"1806.00793","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00793","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00793v2","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00793","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"I3TNF43FW557","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3TNF43FW557H6GQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3TNF43F","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I3TNF43FW557H6GQ43UC5B2724","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-03T13:22:10Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"61dff45eb6b49744d0030ca19af2a1d2f787df61b585e3ad2d54483157ce5bfe","abstract_canon_sha256":"ce22398a43117b36a86e52071ecc9d19a6f7d052985123ddff239abd2a03c589"},"schema_version":"1.0"},"canonical_sha256":"46e6d2f365b77bf3f8d0e6e82e875fd7068501379858541fd120941cb85e2b67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:17.436932Z","signature_b64":"uvsjgnUG4Qu4NANECSvJiKORwFAvXpIAeRPRIh4DX8qAlV2difrXLfn94AOyX+4ZFoBCN9fBbnlQSUn5sGvfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46e6d2f365b77bf3f8d0e6e82e875fd7068501379858541fd120941cb85e2b67","last_reissued_at":"2026-05-18T00:07:17.436296Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:17.436296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00793","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxVJ3PpLICv79Ltgdwvjqpz1xOJdBK13v568iitH9Ki0Lt/NVRLf8v6R4g1ZyaZ9iz+n2K0x8x7QH4OMKjHbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:17:00.950696Z"},"content_sha256":"84db2e341e270d7b7b083784996921421116f05c3749241e1231403d216fe7ae","schema_version":"1.0","event_id":"sha256:84db2e341e270d7b7b083784996921421116f05c3749241e1231403d216fe7ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I3TNF43FW557H6GQ43UC5B2724","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Alexander Herzog, Peter John, Slava Jankin Mikhaylov","submitted_at":"2018-06-03T13:22:10Z","abstract_excerpt":"Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching meaningful labels to estimated topics. This process of manual labeling is not scalable and suffers from human bias. We present a semi-automatic transfer topic labeling method that seeks to remedy these problems. Domain-specific codebooks form the knowledge-base for automated topic labeling. We demonstrate our approach with a dynamic topic model analysis of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00793","kind":"arxiv","version":2},"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":"2026-05-18T00:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cjZArQOwsf/Lq2O4p1qz3ppmZLeuJV5zmvDxUbugEeb4K0BD83ewlw7i+ojKPySPdlz+psNmgXdP2d7ypNvzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T20:17:00.951041Z"},"content_sha256":"f9f9101f7c1548085d160ae03f1559b2a055468e4b414b428f0bf02f3777782f","schema_version":"1.0","event_id":"sha256:f9f9101f7c1548085d160ae03f1559b2a055468e4b414b428f0bf02f3777782f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3TNF43FW557H6GQ43UC5B2724/bundle.json","state_url":"https://pith.science/pith/I3TNF43FW557H6GQ43UC5B2724/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3TNF43FW557H6GQ43UC5B2724/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":"2026-06-01T20:17:00Z","links":{"resolver":"https://pith.science/pith/I3TNF43FW557H6GQ43UC5B2724","bundle":"https://pith.science/pith/I3TNF43FW557H6GQ43UC5B2724/bundle.json","state":"https://pith.science/pith/I3TNF43FW557H6GQ43UC5B2724/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3TNF43FW557H6GQ43UC5B2724/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I3TNF43FW557H6GQ43UC5B2724","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":"ce22398a43117b36a86e52071ecc9d19a6f7d052985123ddff239abd2a03c589","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-03T13:22:10Z","title_canon_sha256":"61dff45eb6b49744d0030ca19af2a1d2f787df61b585e3ad2d54483157ce5bfe"},"schema_version":"1.0","source":{"id":"1806.00793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00793","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00793v2","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00793","created_at":"2026-05-18T00:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"I3TNF43FW557","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I3TNF43FW557H6GQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I3TNF43F","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:f9f9101f7c1548085d160ae03f1559b2a055468e4b414b428f0bf02f3777782f","target":"graph","created_at":"2026-05-18T00:07:17Z","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":"Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching meaningful labels to estimated topics. This process of manual labeling is not scalable and suffers from human bias. We present a semi-automatic transfer topic labeling method that seeks to remedy these problems. Domain-specific codebooks form the knowledge-base for automated topic labeling. We demonstrate our approach with a dynamic topic model analysis of t","authors_text":"Alexander Herzog, Peter John, Slava Jankin Mikhaylov","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-03T13:22:10Z","title":"Transfer Topic Labeling with Domain-Specific Knowledge Base: An Analysis of UK House of Commons Speeches 1935-2014"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00793","kind":"arxiv","version":2},"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":"sha256:84db2e341e270d7b7b083784996921421116f05c3749241e1231403d216fe7ae","target":"record","created_at":"2026-05-18T00:07:17Z","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":"ce22398a43117b36a86e52071ecc9d19a6f7d052985123ddff239abd2a03c589","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-03T13:22:10Z","title_canon_sha256":"61dff45eb6b49744d0030ca19af2a1d2f787df61b585e3ad2d54483157ce5bfe"},"schema_version":"1.0","source":{"id":"1806.00793","kind":"arxiv","version":2}},"canonical_sha256":"46e6d2f365b77bf3f8d0e6e82e875fd7068501379858541fd120941cb85e2b67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46e6d2f365b77bf3f8d0e6e82e875fd7068501379858541fd120941cb85e2b67","first_computed_at":"2026-05-18T00:07:17.436296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:17.436296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uvsjgnUG4Qu4NANECSvJiKORwFAvXpIAeRPRIh4DX8qAlV2difrXLfn94AOyX+4ZFoBCN9fBbnlQSUn5sGvfBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:17.436932Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84db2e341e270d7b7b083784996921421116f05c3749241e1231403d216fe7ae","sha256:f9f9101f7c1548085d160ae03f1559b2a055468e4b414b428f0bf02f3777782f"],"state_sha256":"b19cff9f30c130399dad6c21d30ca78e1e41d9b2801e9f7bcecef2ed7e236b20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1NKcxJXcZTzRiGQQQrIFaioHGy8JQHvbbuMEOxExnTaCIZuDtyxRop6+Kx4lIFTuJ1vJqkWX5RwOiJwYHy5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T20:17:00.952932Z","bundle_sha256":"d93ac9836b7d2680e2b3ca23cc48524b74510c8662b443f22e345a88c6ae2f38"}}