{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:WG6FCPGG7FTFUU2CJMLWK342MA","short_pith_number":"pith:WG6FCPGG","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"},"canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","source":{"kind":"arxiv","id":"1412.1576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.1576","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"arxiv_version","alias_value":"1412.1576v1","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.1576","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"pith_short_12","alias_value":"WG6FCPGG7FTF","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WG6FCPGG7FTFUU2C","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WG6FCPGG","created_at":"2026-05-18T12:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:WG6FCPGG7FTFUU2CJMLWK342MA","target":"record","payload":{"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"},"canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","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"},"source_kind":"arxiv","source_id":"1412.1576","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:32:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RU8L30AjXqls3kGVSbxCOobsHbI5i4VV/mglNxidZsT+uME/a00upGoYvz/DMWmiu4Cpt8AEwp0V7e93rQZIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:22:35.400079Z"},"content_sha256":"5cb0ccd379e162ff41d2b16e380e041d7ad651ee1e4f8921abb89775c3c46728","schema_version":"1.0","event_id":"sha256:5cb0ccd379e162ff41d2b16e380e041d7ad651ee1e4f8921abb89775c3c46728"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:WG6FCPGG7FTFUU2CJMLWK342MA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:32:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfRYscgVk2r+VzJpq5sQlgovU7KExhneSAf2jmgp8bH+usumB/jtN7/TdA7wHA53jF7DPufPls9ko0dD62spCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:22:35.400497Z"},"content_sha256":"f8e964eb0938c3328827d8ed000c0101b11ddfdbce4e69bbf5262bdffbc95646","schema_version":"1.0","event_id":"sha256:f8e964eb0938c3328827d8ed000c0101b11ddfdbce4e69bbf5262bdffbc95646"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/bundle.json","state_url":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WG6FCPGG7FTFUU2CJMLWK342MA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T08:22:35Z","links":{"resolver":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA","bundle":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/bundle.json","state":"https://pith.science/pith/WG6FCPGG7FTFUU2CJMLWK342MA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WG6FCPGG7FTFUU2CJMLWK342MA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:WG6FCPGG7FTFUU2CJMLWK342MA","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":"6bf3a649077ec67cb5f82a88d83aceb36e846bd6d294852b826263e063b7fd0c","cross_cats_sorted":["cs.DC","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-04T07:49:12Z","title_canon_sha256":"b0a8b95c5f3b001b1f5926a3426ed83e57d2d1b0d48039be88529f3f6eccb039"},"schema_version":"1.0","source":{"id":"1412.1576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.1576","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"arxiv_version","alias_value":"1412.1576v1","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.1576","created_at":"2026-05-18T02:32:06Z"},{"alias_kind":"pith_short_12","alias_value":"WG6FCPGG7FTF","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WG6FCPGG7FTFUU2C","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WG6FCPGG","created_at":"2026-05-18T12:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:f8e964eb0938c3328827d8ed000c0101b11ddfdbce4e69bbf5262bdffbc95646","target":"graph","created_at":"2026-05-18T02:32:06Z","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":"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 -- ","authors_text":"Eric P. Xing, Fei Gao, Jinhui Yuan, Jinliang Wei, Qirong Ho, Tie-Yan Liu, Wei Dai, Wei-Ying Ma, Xun Zheng","cross_cats":["cs.DC","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-04T07:49:12Z","title":"LightLDA: Big Topic Models on Modest Compute Clusters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.1576","kind":"arxiv","version":1},"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":"sha256:5cb0ccd379e162ff41d2b16e380e041d7ad651ee1e4f8921abb89775c3c46728","target":"record","created_at":"2026-05-18T02:32:06Z","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":"6bf3a649077ec67cb5f82a88d83aceb36e846bd6d294852b826263e063b7fd0c","cross_cats_sorted":["cs.DC","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-04T07:49:12Z","title_canon_sha256":"b0a8b95c5f3b001b1f5926a3426ed83e57d2d1b0d48039be88529f3f6eccb039"},"schema_version":"1.0","source":{"id":"1412.1576","kind":"arxiv","version":1}},"canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1bc513cc6f9665a53424b17656f9a6028a1aa6c3990c839a8c2abe27027f2f3","first_computed_at":"2026-05-18T02:32:06.948945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:32:06.948945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kyIpTVMVv9PHuZ5/ZYhyzYL5xEk7Png+IXuryQC2uQT0HzjFgqlUlVFYxGJ7A6FYlkVyrLlC/9vdOihuSlUYDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:32:06.949363Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.1576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cb0ccd379e162ff41d2b16e380e041d7ad651ee1e4f8921abb89775c3c46728","sha256:f8e964eb0938c3328827d8ed000c0101b11ddfdbce4e69bbf5262bdffbc95646"],"state_sha256":"8e631d56b74e52413c842147b3cd6910b3984ed58b7bb66720d93f86787671bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBWGsRWJPfcSrFTh1JqUehTOV9fFW6u+dBYPGmPMaaxTk0ELzYxLztj/lqlSieRamMFsAyIGgUHnf6j7FXgMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T08:22:35.402532Z","bundle_sha256":"3581e4ef064d3ab958e701efee046497c5c3613c4cf91e821fbd820b87661eae"}}