{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:XPBB3DZY2Q2L4Z2MAHGFJWL2DX","short_pith_number":"pith:XPBB3DZY","schema_version":"1.0","canonical_sha256":"bbc21d8f38d434be674c01cc54d97a1dfe0a5213ddb8b2ccfffa587eb24cbb9d","source":{"kind":"arxiv","id":"1311.4780","version":2},"attestation_state":"computed","paper":{"title":"Asymptotically Exact, Embarrassingly Parallel MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Chong Wang, Eric Xing, Willie Neiswanger","submitted_at":"2013-11-19T15:23:04Z","abstract_excerpt":"Communication costs, resulting from synchronization requirements during learning, can greatly slow down many parallel machine learning algorithms. In this paper, we present a parallel Markov chain Monte Carlo (MCMC) algorithm in which subsets of data are processed independently, with very little communication. First, we arbitrarily partition data onto multiple machines. Then, on each machine, any classical MCMC method (e.g., Gibbs sampling) may be used to draw samples from a posterior distribution given the data subset. Finally, the samples from each machine are combined to form samples from t"},"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":"1311.4780","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-19T15:23:04Z","cross_cats_sorted":["cs.DC","cs.LG","stat.CO"],"title_canon_sha256":"1bfeb575c3ce0e1f4b5f098b1537222883b2c7f1427f24756286a96543228cab","abstract_canon_sha256":"f690cf3bb5eb7c15f10746c7262b9b53d643348ea6d9d56a46c13818e128b74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:55:57.119859Z","signature_b64":"wnTxPhG7G02Ty6XNDaugxPOiDSPOIRHDbujUg3zCO9+mk0Yrao7+AcrooQM1baLXzDuMYw0MAq4kn1zvJX2zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc21d8f38d434be674c01cc54d97a1dfe0a5213ddb8b2ccfffa587eb24cbb9d","last_reissued_at":"2026-05-18T02:55:57.119226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:55:57.119226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotically Exact, Embarrassingly Parallel MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Chong Wang, Eric Xing, Willie Neiswanger","submitted_at":"2013-11-19T15:23:04Z","abstract_excerpt":"Communication costs, resulting from synchronization requirements during learning, can greatly slow down many parallel machine learning algorithms. In this paper, we present a parallel Markov chain Monte Carlo (MCMC) algorithm in which subsets of data are processed independently, with very little communication. First, we arbitrarily partition data onto multiple machines. Then, on each machine, any classical MCMC method (e.g., Gibbs sampling) may be used to draw samples from a posterior distribution given the data subset. Finally, the samples from each machine are combined to form samples from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.4780","kind":"arxiv","version":2},"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":"1311.4780","created_at":"2026-05-18T02:55:57.119324+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.4780v2","created_at":"2026-05-18T02:55:57.119324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.4780","created_at":"2026-05-18T02:55:57.119324+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPBB3DZY2Q2L","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPBB3DZY2Q2L4Z2M","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPBB3DZY","created_at":"2026-05-18T12:28:06.772260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08528","citing_title":"Analyzing and Storing Network Intrusion Detection Data using Bayesian Coresets: A Preliminary Study in Offline and Streaming Settings","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21782","citing_title":"A Scalable Parametric Item Calibration Engine (SPICE) for Explanatory IRT with Sparse Data","ref_index":144,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX","json":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX.json","graph_json":"https://pith.science/api/pith-number/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/graph.json","events_json":"https://pith.science/api/pith-number/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/events.json","paper":"https://pith.science/paper/XPBB3DZY"},"agent_actions":{"view_html":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX","download_json":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX.json","view_paper":"https://pith.science/paper/XPBB3DZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.4780&json=true","fetch_graph":"https://pith.science/api/pith-number/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/graph.json","fetch_events":"https://pith.science/api/pith-number/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/action/storage_attestation","attest_author":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/action/author_attestation","sign_citation":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/action/citation_signature","submit_replication":"https://pith.science/pith/XPBB3DZY2Q2L4Z2MAHGFJWL2DX/action/replication_record"}},"created_at":"2026-05-18T02:55:57.119324+00:00","updated_at":"2026-05-18T02:55:57.119324+00:00"}