{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HWOYZSUHCMOIJLDKXDADVVXHDK","short_pith_number":"pith:HWOYZSUH","schema_version":"1.0","canonical_sha256":"3d9d8cca87131c84ac6ab8c03ad6e71a837f24965cea2b4b544dce6a2854ccfd","source":{"kind":"arxiv","id":"1709.06304","version":1},"attestation_state":"computed","paper":{"title":"Scalable Estimation of Dirichlet Process Mixture Models on Distributed Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dahua Lin, Ruohui Wang","submitted_at":"2017-09-19T09:05:14Z","abstract_excerpt":"We consider the estimation of Dirichlet Process Mixture Models (DPMMs) in distributed environments, where data are distributed across multiple computing nodes. A key advantage of Bayesian nonparametric models such as DPMMs is that they allow new components to be introduced on the fly as needed. This, however, posts an important challenge to distributed estimation -- how to handle new components efficiently and consistently. To tackle this problem, we propose a new estimation method, which allows new components to be created locally in individual computing nodes. Components corresponding to the"},"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":"1709.06304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-19T09:05:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3eb501404abe926500305ceafe5961417c7db5c8fa0aa832935b610d8258ac8","abstract_canon_sha256":"ca9f5b095749e10cec2061d4901d37ad9c2353005fa9f001bcabb375120933fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:53.624183Z","signature_b64":"rW1b9BHAf3scktc8O67xWcKIhGD4s6QHWbjk0I6q+jWuKXuuEh4OFqGtQJz30Q8gY3+fET8yU+OPplfviiymAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d9d8cca87131c84ac6ab8c03ad6e71a837f24965cea2b4b544dce6a2854ccfd","last_reissued_at":"2026-05-18T00:34:53.623451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:53.623451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Estimation of Dirichlet Process Mixture Models on Distributed Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dahua Lin, Ruohui Wang","submitted_at":"2017-09-19T09:05:14Z","abstract_excerpt":"We consider the estimation of Dirichlet Process Mixture Models (DPMMs) in distributed environments, where data are distributed across multiple computing nodes. A key advantage of Bayesian nonparametric models such as DPMMs is that they allow new components to be introduced on the fly as needed. This, however, posts an important challenge to distributed estimation -- how to handle new components efficiently and consistently. To tackle this problem, we propose a new estimation method, which allows new components to be created locally in individual computing nodes. Components corresponding to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06304","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":"1709.06304","created_at":"2026-05-18T00:34:53.623566+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06304v1","created_at":"2026-05-18T00:34:53.623566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06304","created_at":"2026-05-18T00:34:53.623566+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWOYZSUHCMOI","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWOYZSUHCMOIJLDK","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWOYZSUH","created_at":"2026-05-18T12:31:21.493067+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/HWOYZSUHCMOIJLDKXDADVVXHDK","json":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK.json","graph_json":"https://pith.science/api/pith-number/HWOYZSUHCMOIJLDKXDADVVXHDK/graph.json","events_json":"https://pith.science/api/pith-number/HWOYZSUHCMOIJLDKXDADVVXHDK/events.json","paper":"https://pith.science/paper/HWOYZSUH"},"agent_actions":{"view_html":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK","download_json":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK.json","view_paper":"https://pith.science/paper/HWOYZSUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06304&json=true","fetch_graph":"https://pith.science/api/pith-number/HWOYZSUHCMOIJLDKXDADVVXHDK/graph.json","fetch_events":"https://pith.science/api/pith-number/HWOYZSUHCMOIJLDKXDADVVXHDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK/action/storage_attestation","attest_author":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK/action/author_attestation","sign_citation":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK/action/citation_signature","submit_replication":"https://pith.science/pith/HWOYZSUHCMOIJLDKXDADVVXHDK/action/replication_record"}},"created_at":"2026-05-18T00:34:53.623566+00:00","updated_at":"2026-05-18T00:34:53.623566+00:00"}