{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:MAGIZS65BZQNMYYODQ7YO2ADWV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"090c645411df6533dc0a83d91893705204a5a7466b36dae05cdbad714d9e8b44","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-05-17T14:36:52Z","title_canon_sha256":"57f50b60bcda5ff1255c360273fd2fd99112a7a5f5fdcd5990ff8c32ece28b24"},"schema_version":"1.0","source":{"id":"1405.4402","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.4402","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"1405.4402v3","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.4402","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"MAGIZS65BZQN","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"MAGIZS65BZQNMYYO","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"MAGIZS65","created_at":"2026-05-18T12:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:8788f97b56d52b6331c73df231e1d69febbfc61f4477749499a5b0d053e50cf8","target":"graph","created_at":"2026-05-18T01:25:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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,","authors_text":"Ching Law, Hao Yan, Jia Zeng, Lifeng Wang, Liubin Wang, Xuemin Zhao, Yang Gao, Yi Wang, Zhenlong Sun, Zhihui Jin","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-05-17T14:36:52Z","title":"Peacock: Learning Long-Tail Topic Features for Industrial Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.4402","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7469b7f624f032f95dadf275bbe267c7d0f3dc93ebc567d1fb9f6e7733e78c8d","target":"record","created_at":"2026-05-18T01:25:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"090c645411df6533dc0a83d91893705204a5a7466b36dae05cdbad714d9e8b44","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-05-17T14:36:52Z","title_canon_sha256":"57f50b60bcda5ff1255c360273fd2fd99112a7a5f5fdcd5990ff8c32ece28b24"},"schema_version":"1.0","source":{"id":"1405.4402","kind":"arxiv","version":3}},"canonical_sha256":"600c8ccbdd0e60d6630e1c3f876803b56db6d06ca8121190b63ab8d73a1a931c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"600c8ccbdd0e60d6630e1c3f876803b56db6d06ca8121190b63ab8d73a1a931c","first_computed_at":"2026-05-18T01:25:16.237302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:16.237302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pz9AeU9O85h7R+OwRoVrJZPPiNCTsb167ZCOa/OusfGNy8OA/P574rSKy20l80PI7nDSvezi/+1TOPiRza5XDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:16.237777Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.4402","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7469b7f624f032f95dadf275bbe267c7d0f3dc93ebc567d1fb9f6e7733e78c8d","sha256:8788f97b56d52b6331c73df231e1d69febbfc61f4477749499a5b0d053e50cf8"],"state_sha256":"3ce4d384c1dcc0975ba6451374722bb9a6fda8722bae35b1cd981bf2095f4870"}