{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:LLY75P77W6UG4SNZSJLFHEXKY3","short_pith_number":"pith:LLY75P77","canonical_record":{"source":{"id":"1511.00440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2015-11-02T10:57:25Z","cross_cats_sorted":[],"title_canon_sha256":"ec799a57bd76b071018b99b048c1911768c5e6d3dca9f2c0a46c3b1eaf58fc03","abstract_canon_sha256":"b0e42ba9cb25f754a11a4ae18cb6a4d8d9d857c61bf682de6b73c80a5e017444"},"schema_version":"1.0"},"canonical_sha256":"5af1febfffb7a86e49b992565392eac6d66510c0b65410ba5807ed7369ed005c","source":{"kind":"arxiv","id":"1511.00440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.00440","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"1511.00440v1","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.00440","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"LLY75P77W6UG","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LLY75P77W6UG4SNZ","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LLY75P77","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:LLY75P77W6UG4SNZSJLFHEXKY3","target":"record","payload":{"canonical_record":{"source":{"id":"1511.00440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2015-11-02T10:57:25Z","cross_cats_sorted":[],"title_canon_sha256":"ec799a57bd76b071018b99b048c1911768c5e6d3dca9f2c0a46c3b1eaf58fc03","abstract_canon_sha256":"b0e42ba9cb25f754a11a4ae18cb6a4d8d9d857c61bf682de6b73c80a5e017444"},"schema_version":"1.0"},"canonical_sha256":"5af1febfffb7a86e49b992565392eac6d66510c0b65410ba5807ed7369ed005c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:24.770599Z","signature_b64":"SwYWayTmT2b+Hene79SjImFo8pHOugC4Q/kLhPFX0DXVe6MFL8Q2MCCuB7CpdmI57g/qL6JExWwluF53YY4jBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5af1febfffb7a86e49b992565392eac6d66510c0b65410ba5807ed7369ed005c","last_reissued_at":"2026-05-18T01:26:24.770151Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:24.770151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.00440","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":"2026-05-18T01:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPjPtNwtG0BFoeM7TYlFQv+kUe/wbPzZHDDDGdBeIL19o37oSdLc5y2Iq3vK+/O76teMMVvxu7JI8ZW2UJUbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T07:25:49.001210Z"},"content_sha256":"fcb1773a4ee5f0e8b6cff5f96f77aa8fbe6497489eac69aa6f848aae8242bbff","schema_version":"1.0","event_id":"sha256:fcb1773a4ee5f0e8b6cff5f96f77aa8fbe6497489eac69aa6f848aae8242bbff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:LLY75P77W6UG4SNZSJLFHEXKY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZenLDA: An Efficient and Scalable Topic Model Training System on Distributed Data-Parallel Platform","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bo Zhao, Guoqiang Li, Hucheng Zhou, Yihua Huang","submitted_at":"2015-11-02T10:57:25Z","abstract_excerpt":"This paper presents our recent efforts, zenLDA, an efficient and scalable Collapsed Gibbs Sampling system for Latent Dirichlet Allocation training, which is thought to be challenging that both data parallelism and model parallelism are required because of the Big sampling data with up to billions of documents and Big model size with up to trillions of parameters. zenLDA combines both algorithm level improvements and system level optimizations. It first presents a novel CGS algorithm that balances the time complexity, model accuracy and parallelization flexibility. The input corpus in zenLDA is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.00440","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":"2026-05-18T01:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GOhlXO8Mn842wa+BlKmU61GvwdaQAuE7V0+sLA9+HQaKAZBDQfI2B80/Uc6QN7KIw8brZzItRZnYBLIm0wrrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T07:25:49.001918Z"},"content_sha256":"3994d9c8f128ccb67bf80fb253d0067e232c7d2d56dcfc97c0aacdefc7d63ed4","schema_version":"1.0","event_id":"sha256:3994d9c8f128ccb67bf80fb253d0067e232c7d2d56dcfc97c0aacdefc7d63ed4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLY75P77W6UG4SNZSJLFHEXKY3/bundle.json","state_url":"https://pith.science/pith/LLY75P77W6UG4SNZSJLFHEXKY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLY75P77W6UG4SNZSJLFHEXKY3/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":"2026-05-25T07:25:49Z","links":{"resolver":"https://pith.science/pith/LLY75P77W6UG4SNZSJLFHEXKY3","bundle":"https://pith.science/pith/LLY75P77W6UG4SNZSJLFHEXKY3/bundle.json","state":"https://pith.science/pith/LLY75P77W6UG4SNZSJLFHEXKY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLY75P77W6UG4SNZSJLFHEXKY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:LLY75P77W6UG4SNZSJLFHEXKY3","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":"b0e42ba9cb25f754a11a4ae18cb6a4d8d9d857c61bf682de6b73c80a5e017444","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2015-11-02T10:57:25Z","title_canon_sha256":"ec799a57bd76b071018b99b048c1911768c5e6d3dca9f2c0a46c3b1eaf58fc03"},"schema_version":"1.0","source":{"id":"1511.00440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.00440","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"1511.00440v1","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.00440","created_at":"2026-05-18T01:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"LLY75P77W6UG","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LLY75P77W6UG4SNZ","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LLY75P77","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:3994d9c8f128ccb67bf80fb253d0067e232c7d2d56dcfc97c0aacdefc7d63ed4","target":"graph","created_at":"2026-05-18T01:26:24Z","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":"This paper presents our recent efforts, zenLDA, an efficient and scalable Collapsed Gibbs Sampling system for Latent Dirichlet Allocation training, which is thought to be challenging that both data parallelism and model parallelism are required because of the Big sampling data with up to billions of documents and Big model size with up to trillions of parameters. zenLDA combines both algorithm level improvements and system level optimizations. It first presents a novel CGS algorithm that balances the time complexity, model accuracy and parallelization flexibility. The input corpus in zenLDA is","authors_text":"Bo Zhao, Guoqiang Li, Hucheng Zhou, Yihua Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2015-11-02T10:57:25Z","title":"ZenLDA: An Efficient and Scalable Topic Model Training System on Distributed Data-Parallel Platform"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.00440","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:fcb1773a4ee5f0e8b6cff5f96f77aa8fbe6497489eac69aa6f848aae8242bbff","target":"record","created_at":"2026-05-18T01:26:24Z","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":"b0e42ba9cb25f754a11a4ae18cb6a4d8d9d857c61bf682de6b73c80a5e017444","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2015-11-02T10:57:25Z","title_canon_sha256":"ec799a57bd76b071018b99b048c1911768c5e6d3dca9f2c0a46c3b1eaf58fc03"},"schema_version":"1.0","source":{"id":"1511.00440","kind":"arxiv","version":1}},"canonical_sha256":"5af1febfffb7a86e49b992565392eac6d66510c0b65410ba5807ed7369ed005c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5af1febfffb7a86e49b992565392eac6d66510c0b65410ba5807ed7369ed005c","first_computed_at":"2026-05-18T01:26:24.770151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:24.770151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SwYWayTmT2b+Hene79SjImFo8pHOugC4Q/kLhPFX0DXVe6MFL8Q2MCCuB7CpdmI57g/qL6JExWwluF53YY4jBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:24.770599Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.00440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcb1773a4ee5f0e8b6cff5f96f77aa8fbe6497489eac69aa6f848aae8242bbff","sha256:3994d9c8f128ccb67bf80fb253d0067e232c7d2d56dcfc97c0aacdefc7d63ed4"],"state_sha256":"deed34a4976c3830ac7490b3948031976b02421ebf3b3f2ca8ed78a0e27e31ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1l3VFMgBnI/5jf3dW57Mn6PKMZFnAzW43V7wjvO/AmwOYs4qkWoZuzKP/FY2WH1r93fm3aF8OYzSKUgcYG3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T07:25:49.005800Z","bundle_sha256":"8625a1df2883b923eb45fd3694dd218ab35417058deaa25c8de810450158def5"}}