{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TFIBTHULMUYEOVQ3FKK3IGKRZP","short_pith_number":"pith:TFIBTHUL","schema_version":"1.0","canonical_sha256":"9950199e8b653047561b2a95b41951cbdc299f1ea1fef1f2a89b242295cd1f06","source":{"kind":"arxiv","id":"1701.04273","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke, Maarten Marx, Mostafa Dehghani, Tom Kenter","submitted_at":"2017-01-16T12:59:47Z","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 elements for assessing diversity: words, topics, and documents as collections of words. Topic models play a central role in this approach. Using standard topic models for measuring diversity of documents is suboptimal due to generality and impurity. General topics only include common information from a background corpus and are assigned to most of the documents in the collection. Impure topics contain words th"},"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":"1701.04273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-01-16T12:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"b846ec8fd9b6e712088a01d677802f28017ed21ffc43f867470315ef89ab60a6","abstract_canon_sha256":"c189dc7a6b5c7888666a63212c4f880289a7c80ae862299c3f7ca39c884defa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:47.239459Z","signature_b64":"IzUsm4g0A0y3wnw+e7zJnLZjCBAIdIzFzaM8lXkNNoklL8Ux5hK8kwZakxdLE3BCDMiTm++F100tD63zoXGKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9950199e8b653047561b2a95b41951cbdc299f1ea1fef1f2a89b242295cd1f06","last_reissued_at":"2026-05-18T00:52:47.238688Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:47.238688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Re-estimation of Topic Models for Measuring Topical Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke, Maarten Marx, Mostafa Dehghani, Tom Kenter","submitted_at":"2017-01-16T12:59:47Z","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 elements for assessing diversity: words, topics, and documents as collections of words. Topic models play a central role in this approach. Using standard topic models for measuring diversity of documents is suboptimal due to generality and impurity. General topics only include common information from a background corpus and are assigned to most of the documents in the collection. Impure topics contain words th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.04273","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":"1701.04273","created_at":"2026-05-18T00:52:47.238820+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.04273v1","created_at":"2026-05-18T00:52:47.238820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04273","created_at":"2026-05-18T00:52:47.238820+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFIBTHULMUYE","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFIBTHULMUYEOVQ3","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFIBTHUL","created_at":"2026-05-18T12:31:46.661854+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/TFIBTHULMUYEOVQ3FKK3IGKRZP","json":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP.json","graph_json":"https://pith.science/api/pith-number/TFIBTHULMUYEOVQ3FKK3IGKRZP/graph.json","events_json":"https://pith.science/api/pith-number/TFIBTHULMUYEOVQ3FKK3IGKRZP/events.json","paper":"https://pith.science/paper/TFIBTHUL"},"agent_actions":{"view_html":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP","download_json":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP.json","view_paper":"https://pith.science/paper/TFIBTHUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.04273&json=true","fetch_graph":"https://pith.science/api/pith-number/TFIBTHULMUYEOVQ3FKK3IGKRZP/graph.json","fetch_events":"https://pith.science/api/pith-number/TFIBTHULMUYEOVQ3FKK3IGKRZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP/action/storage_attestation","attest_author":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP/action/author_attestation","sign_citation":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP/action/citation_signature","submit_replication":"https://pith.science/pith/TFIBTHULMUYEOVQ3FKK3IGKRZP/action/replication_record"}},"created_at":"2026-05-18T00:52:47.238820+00:00","updated_at":"2026-05-18T00:52:47.238820+00:00"}