{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RQUODYYJ6TC3SMPSAVNSJ2DQ7A","short_pith_number":"pith:RQUODYYJ","schema_version":"1.0","canonical_sha256":"8c28e1e309f4c5b931f2055b24e870f804d81458be2b86abc115f43e49c02f9e","source":{"kind":"arxiv","id":"1810.05436","version":1},"attestation_state":"computed","paper":{"title":"HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke, Maarten Marx, Mostafa Dehghani, Tom Kenter","submitted_at":"2018-10-12T10:02:23Z","abstract_excerpt":"A high degree of topical diversity is often considered to be an important characteristic of interesting text documents. A recent proposal for measuring topical diversity identifies three distributions for assessing the diversity of documents: distributions of words within documents, words within topics, and topics within documents. Topic models play a central role in this approach and, hence, their quality is crucial to the efficacy of measuring topical diversity. The quality of topic models is affected by two causes: generality and impurity of topics. General topics only include common inform"},"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":"1810.05436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-12T10:02:23Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"5332a9f297df2a84e3571d7f7c4b8a1a7290df7f626ff7b18cb2e41ee4b50a35","abstract_canon_sha256":"bc43ee25593f0e4b82db1bb18a09227223a35149baf1372434efc9c31c740623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:30.568255Z","signature_b64":"f2gQZ9kfowb6DJEHP1hF2PUZNucHVlVpO8lb9Epy56mesD8IRg8xW2XNqOCUX8Hyiw05MN09A8AoMGUkO8EqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c28e1e309f4c5b931f2055b24e870f804d81458be2b86abc115f43e49c02f9e","last_reissued_at":"2026-05-18T00:03:30.567605Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:30.567605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiTR: Hierarchical Topic Model Re-estimation for Measuring Topical Diversity of Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke, Maarten Marx, Mostafa Dehghani, Tom Kenter","submitted_at":"2018-10-12T10:02:23Z","abstract_excerpt":"A high degree of topical diversity is often considered to be an important characteristic of interesting text documents. A recent proposal for measuring topical diversity identifies three distributions for assessing the diversity of documents: distributions of words within documents, words within topics, and topics within documents. Topic models play a central role in this approach and, hence, their quality is crucial to the efficacy of measuring topical diversity. The quality of topic models is affected by two causes: generality and impurity of topics. General topics only include common inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.05436","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":"1810.05436","created_at":"2026-05-18T00:03:30.567735+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.05436v1","created_at":"2026-05-18T00:03:30.567735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.05436","created_at":"2026-05-18T00:03:30.567735+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQUODYYJ6TC3","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQUODYYJ6TC3SMPS","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQUODYYJ","created_at":"2026-05-18T12:32:50.500415+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/RQUODYYJ6TC3SMPSAVNSJ2DQ7A","json":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A.json","graph_json":"https://pith.science/api/pith-number/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/graph.json","events_json":"https://pith.science/api/pith-number/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/events.json","paper":"https://pith.science/paper/RQUODYYJ"},"agent_actions":{"view_html":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A","download_json":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A.json","view_paper":"https://pith.science/paper/RQUODYYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.05436&json=true","fetch_graph":"https://pith.science/api/pith-number/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/action/storage_attestation","attest_author":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/action/author_attestation","sign_citation":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/action/citation_signature","submit_replication":"https://pith.science/pith/RQUODYYJ6TC3SMPSAVNSJ2DQ7A/action/replication_record"}},"created_at":"2026-05-18T00:03:30.567735+00:00","updated_at":"2026-05-18T00:03:30.567735+00:00"}