{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FVB4YN3GG65I7ZEWBWKS6DVKI4","short_pith_number":"pith:FVB4YN3G","schema_version":"1.0","canonical_sha256":"2d43cc376637ba8fe4960d952f0eaa470bc0fb15401f955c1bbc5bc024d8b824","source":{"kind":"arxiv","id":"1702.08199","version":1},"attestation_state":"computed","paper":{"title":"Mutual Information based labelling and comparing clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.IR","authors_text":"Rob Koopman, Shenghui Wang","submitted_at":"2017-02-27T09:23:46Z","abstract_excerpt":"After a clustering solution is generated automatically, labelling these clusters becomes important to help understanding the results. In this paper, we propose to use a Mutual Information based method to label clusters of journal articles. Topical terms which have the highest Normalised Mutual Information (NMI) with a certain cluster are selected to be the labels of the cluster. Discussion of the labelling technique with a domain expert was used as a check that the labels are discriminating not only lexical-wise but also semantically. Based on a common set of topical terms, we also propose to "},"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":"1702.08199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-27T09:23:46Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"bc35c85bfbea8c0f6d1084007b09621f0a031679ae67ea77b7bd88bfd74773d2","abstract_canon_sha256":"b6c49b6f6df6b2a4e5aeaf1f375d89a84794aef34858a44c348e07840f76bf61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:55.639218Z","signature_b64":"cXjjMXp7uviy5W6r+ct+zFPnLOWMmvNyvIiTcbTBvzNogADjFC0eOkpEZrdxRQkj/tjp5x9bl/oscpHi8fBmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d43cc376637ba8fe4960d952f0eaa470bc0fb15401f955c1bbc5bc024d8b824","last_reissued_at":"2026-05-18T00:49:55.638371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:55.638371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mutual Information based labelling and comparing clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.IR","authors_text":"Rob Koopman, Shenghui Wang","submitted_at":"2017-02-27T09:23:46Z","abstract_excerpt":"After a clustering solution is generated automatically, labelling these clusters becomes important to help understanding the results. In this paper, we propose to use a Mutual Information based method to label clusters of journal articles. Topical terms which have the highest Normalised Mutual Information (NMI) with a certain cluster are selected to be the labels of the cluster. Discussion of the labelling technique with a domain expert was used as a check that the labels are discriminating not only lexical-wise but also semantically. Based on a common set of topical terms, we also propose to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08199","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":"1702.08199","created_at":"2026-05-18T00:49:55.638504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08199v1","created_at":"2026-05-18T00:49:55.638504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08199","created_at":"2026-05-18T00:49:55.638504+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVB4YN3GG65I","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVB4YN3GG65I7ZEW","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVB4YN3G","created_at":"2026-05-18T12:31:15.632608+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/FVB4YN3GG65I7ZEWBWKS6DVKI4","json":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4.json","graph_json":"https://pith.science/api/pith-number/FVB4YN3GG65I7ZEWBWKS6DVKI4/graph.json","events_json":"https://pith.science/api/pith-number/FVB4YN3GG65I7ZEWBWKS6DVKI4/events.json","paper":"https://pith.science/paper/FVB4YN3G"},"agent_actions":{"view_html":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4","download_json":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4.json","view_paper":"https://pith.science/paper/FVB4YN3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08199&json=true","fetch_graph":"https://pith.science/api/pith-number/FVB4YN3GG65I7ZEWBWKS6DVKI4/graph.json","fetch_events":"https://pith.science/api/pith-number/FVB4YN3GG65I7ZEWBWKS6DVKI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4/action/storage_attestation","attest_author":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4/action/author_attestation","sign_citation":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4/action/citation_signature","submit_replication":"https://pith.science/pith/FVB4YN3GG65I7ZEWBWKS6DVKI4/action/replication_record"}},"created_at":"2026-05-18T00:49:55.638504+00:00","updated_at":"2026-05-18T00:49:55.638504+00:00"}