{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ON7L3R3R6FB6ASEKIUQFS2M5QW","short_pith_number":"pith:ON7L3R3R","schema_version":"1.0","canonical_sha256":"737ebdc771f143e0488a452059699d85adbd0d84aea8567ce74e0f65238494b4","source":{"kind":"arxiv","id":"1704.02090","version":1},"attestation_state":"computed","paper":{"title":"Conceptualization Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guihua Wen, Heyan Huang, Xian-Ling Mao, Yi-Kun Tang","submitted_at":"2017-04-07T05:12:38Z","abstract_excerpt":"Recently, topic modeling has been widely used to discover the abstract topics in text corpora. Most of the existing topic models are based on the assumption of three-layer hierarchical Bayesian structure, i.e. each document is modeled as a probability distribution over topics, and each topic is a probability distribution over words. However, the assumption is not optimal. Intuitively, it's more reasonable to assume that each topic is a probability distribution over concepts, and then each concept is a probability distribution over words, i.e. adding a latent concept layer between topic layer a"},"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":"1704.02090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-07T05:12:38Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"575915f37c317504398ecde294d89012499562f6d72fc3c266d7c29fa6629651","abstract_canon_sha256":"3cfa00f837e46fa461f60d29bf729feba68eb1daa16ce65667806549353e3b3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:50.810806Z","signature_b64":"fcqMNqsXhNwdt2j8czNqNft+aFxjdyaaN+4Uj9lw6aOd2VYbTJ6sWyvOieVkuDjBKt7dj2BASYiUqh5p/eT2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"737ebdc771f143e0488a452059699d85adbd0d84aea8567ce74e0f65238494b4","last_reissued_at":"2026-05-18T00:46:50.810204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:50.810204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conceptualization Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guihua Wen, Heyan Huang, Xian-Ling Mao, Yi-Kun Tang","submitted_at":"2017-04-07T05:12:38Z","abstract_excerpt":"Recently, topic modeling has been widely used to discover the abstract topics in text corpora. Most of the existing topic models are based on the assumption of three-layer hierarchical Bayesian structure, i.e. each document is modeled as a probability distribution over topics, and each topic is a probability distribution over words. However, the assumption is not optimal. Intuitively, it's more reasonable to assume that each topic is a probability distribution over concepts, and then each concept is a probability distribution over words, i.e. adding a latent concept layer between topic layer a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02090","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":"1704.02090","created_at":"2026-05-18T00:46:50.810325+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02090v1","created_at":"2026-05-18T00:46:50.810325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02090","created_at":"2026-05-18T00:46:50.810325+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON7L3R3R6FB6","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON7L3R3R6FB6ASEK","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON7L3R3R","created_at":"2026-05-18T12:31:34.259226+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/ON7L3R3R6FB6ASEKIUQFS2M5QW","json":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW.json","graph_json":"https://pith.science/api/pith-number/ON7L3R3R6FB6ASEKIUQFS2M5QW/graph.json","events_json":"https://pith.science/api/pith-number/ON7L3R3R6FB6ASEKIUQFS2M5QW/events.json","paper":"https://pith.science/paper/ON7L3R3R"},"agent_actions":{"view_html":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW","download_json":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW.json","view_paper":"https://pith.science/paper/ON7L3R3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02090&json=true","fetch_graph":"https://pith.science/api/pith-number/ON7L3R3R6FB6ASEKIUQFS2M5QW/graph.json","fetch_events":"https://pith.science/api/pith-number/ON7L3R3R6FB6ASEKIUQFS2M5QW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW/action/storage_attestation","attest_author":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW/action/author_attestation","sign_citation":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW/action/citation_signature","submit_replication":"https://pith.science/pith/ON7L3R3R6FB6ASEKIUQFS2M5QW/action/replication_record"}},"created_at":"2026-05-18T00:46:50.810325+00:00","updated_at":"2026-05-18T00:46:50.810325+00:00"}