{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:WG6FCPGG7FTFUU2CJMLWK342MA","short_pith_number":"pith:WG6FCPGG","schema_version":"1.0","canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","source":{"kind":"arxiv","id":"1412.1576","version":1},"attestation_state":"computed","paper":{"title":"LightLDA: Big Topic Models on Modest Compute Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric P. Xing, Fei Gao, Jinhui Yuan, Jinliang Wei, Qirong Ho, Tie-Yan Liu, Wei Dai, Wei-Ying Ma, Xun Zheng","submitted_at":"2014-12-04T07:49:12Z","abstract_excerpt":"When building large-scale machine learning (ML) programs, such as big topic models or deep neural nets, one usually assumes such tasks can only be attempted with industrial-sized clusters with thousands of nodes, which are out of reach for most practitioners or academic researchers. We consider this challenge in the context of topic modeling on web-scale corpora, and show that with a modest cluster of as few as 8 machines, we can train a topic model with 1 million topics and a 1-million-word vocabulary (for a total of 1 trillion parameters), on a document collection with 200 billion tokens -- "},"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":"1412.1576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-04T07:49:12Z","cross_cats_sorted":["cs.DC","cs.IR","cs.LG"],"title_canon_sha256":"b0a8b95c5f3b001b1f5926a3426ed83e57d2d1b0d48039be88529f3f6eccb039","abstract_canon_sha256":"6bf3a649077ec67cb5f82a88d83aceb36e846bd6d294852b826263e063b7fd0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:32:06.949363Z","signature_b64":"kyIpTVMVv9PHuZ5/ZYhyzYL5xEk7Png+IXuryQC2uQT0HzjFgqlUlVFYxGJ7A6FYlkVyrLlC/9vdOihuSlUYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","last_reissued_at":"2026-05-18T02:32:06.948945Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:32:06.948945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightLDA: Big Topic Models on Modest Compute Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Eric P. Xing, Fei Gao, Jinhui Yuan, Jinliang Wei, Qirong Ho, Tie-Yan Liu, Wei Dai, Wei-Ying Ma, Xun Zheng","submitted_at":"2014-12-04T07:49:12Z","abstract_excerpt":"When building large-scale machine learning (ML) programs, such as big topic models or deep neural nets, one usually assumes such tasks can only be attempted with industrial-sized clusters with thousands of nodes, which are out of reach for most practitioners or academic researchers. We consider this challenge in the context of topic modeling on web-scale corpora, and show that with a modest cluster of as few as 8 machines, we can train a topic model with 1 million topics and a 1-million-word vocabulary (for a total of 1 trillion parameters), on a document collection with 200 billion tokens -- "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.1576","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":"1412.1576","created_at":"2026-05-18T02:32:06.949010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.1576v1","created_at":"2026-05-18T02:32:06.949010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.1576","created_at":"2026-05-18T02:32:06.949010+00:00"},{"alias_kind":"pith_short_12","alias_value":"WG6FCPGG7FTF","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_16","alias_value":"WG6FCPGG7FTFUU2C","created_at":"2026-05-18T12:28:54.890064+00:00"},{"alias_kind":"pith_short_8","alias_value":"WG6FCPGG","created_at":"2026-05-18T12:28:54.890064+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/WG6FCPGG7FTFUU2CJMLWK342MA","json":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA.json","graph_json":"https://pith.science/api/pith-number/WG6FCPGG7FTFUU2CJMLWK342MA/graph.json","events_json":"https://pith.science/api/pith-number/WG6FCPGG7FTFUU2CJMLWK342MA/events.json","paper":"https://pith.science/paper/WG6FCPGG"},"agent_actions":{"view_html":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA","download_json":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA.json","view_paper":"https://pith.science/paper/WG6FCPGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.1576&json=true","fetch_graph":"https://pith.science/api/pith-number/WG6FCPGG7FTFUU2CJMLWK342MA/graph.json","fetch_events":"https://pith.science/api/pith-number/WG6FCPGG7FTFUU2CJMLWK342MA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/action/storage_attestation","attest_author":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/action/author_attestation","sign_citation":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/action/citation_signature","submit_replication":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/action/replication_record"}},"created_at":"2026-05-18T02:32:06.949010+00:00","updated_at":"2026-05-18T02:32:06.949010+00:00"}