{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:MAGIZS65BZQNMYYODQ7YO2ADWV","short_pith_number":"pith:MAGIZS65","schema_version":"1.0","canonical_sha256":"600c8ccbdd0e60d6630e1c3f876803b56db6d06ca8121190b63ab8d73a1a931c","source":{"kind":"arxiv","id":"1405.4402","version":3},"attestation_state":"computed","paper":{"title":"Peacock: Learning Long-Tail Topic Features for Industrial Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.IR","authors_text":"Ching Law, Hao Yan, Jia Zeng, Lifeng Wang, Liubin Wang, Xuemin Zhao, Yang Gao, Yi Wang, Zhenlong Sun, Zhihui Jin","submitted_at":"2014-05-17T14:36:52Z","abstract_excerpt":"Latent Dirichlet allocation (LDA) is a popular topic modeling technique in academia but less so in industry, especially in large-scale applications involving search engine and online advertising systems. A main underlying reason is that the topic models used have been too small in scale to be useful; for example, some of the largest LDA models reported in literature have up to $10^3$ topics, which cover difficultly the long-tail semantic word sets. In this paper, we show that the number of topics is a key factor that can significantly boost the utility of topic-modeling systems. In particular,"},"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":"1405.4402","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-05-17T14:36:52Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"57f50b60bcda5ff1255c360273fd2fd99112a7a5f5fdcd5990ff8c32ece28b24","abstract_canon_sha256":"090c645411df6533dc0a83d91893705204a5a7466b36dae05cdbad714d9e8b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:16.237777Z","signature_b64":"pz9AeU9O85h7R+OwRoVrJZPPiNCTsb167ZCOa/OusfGNy8OA/P574rSKy20l80PI7nDSvezi/+1TOPiRza5XDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600c8ccbdd0e60d6630e1c3f876803b56db6d06ca8121190b63ab8d73a1a931c","last_reissued_at":"2026-05-18T01:25:16.237302Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:16.237302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Peacock: Learning Long-Tail Topic Features for Industrial Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.IR","authors_text":"Ching Law, Hao Yan, Jia Zeng, Lifeng Wang, Liubin Wang, Xuemin Zhao, Yang Gao, Yi Wang, Zhenlong Sun, Zhihui Jin","submitted_at":"2014-05-17T14:36:52Z","abstract_excerpt":"Latent Dirichlet allocation (LDA) is a popular topic modeling technique in academia but less so in industry, especially in large-scale applications involving search engine and online advertising systems. A main underlying reason is that the topic models used have been too small in scale to be useful; for example, some of the largest LDA models reported in literature have up to $10^3$ topics, which cover difficultly the long-tail semantic word sets. In this paper, we show that the number of topics is a key factor that can significantly boost the utility of topic-modeling systems. In particular,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.4402","kind":"arxiv","version":3},"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":"1405.4402","created_at":"2026-05-18T01:25:16.237392+00:00"},{"alias_kind":"arxiv_version","alias_value":"1405.4402v3","created_at":"2026-05-18T01:25:16.237392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.4402","created_at":"2026-05-18T01:25:16.237392+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAGIZS65BZQN","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAGIZS65BZQNMYYO","created_at":"2026-05-18T12:28:38.356838+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAGIZS65","created_at":"2026-05-18T12:28:38.356838+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/MAGIZS65BZQNMYYODQ7YO2ADWV","json":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV.json","graph_json":"https://pith.science/api/pith-number/MAGIZS65BZQNMYYODQ7YO2ADWV/graph.json","events_json":"https://pith.science/api/pith-number/MAGIZS65BZQNMYYODQ7YO2ADWV/events.json","paper":"https://pith.science/paper/MAGIZS65"},"agent_actions":{"view_html":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV","download_json":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV.json","view_paper":"https://pith.science/paper/MAGIZS65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1405.4402&json=true","fetch_graph":"https://pith.science/api/pith-number/MAGIZS65BZQNMYYODQ7YO2ADWV/graph.json","fetch_events":"https://pith.science/api/pith-number/MAGIZS65BZQNMYYODQ7YO2ADWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV/action/storage_attestation","attest_author":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV/action/author_attestation","sign_citation":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV/action/citation_signature","submit_replication":"https://pith.science/pith/MAGIZS65BZQNMYYODQ7YO2ADWV/action/replication_record"}},"created_at":"2026-05-18T01:25:16.237392+00:00","updated_at":"2026-05-18T01:25:16.237392+00:00"}