{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2O63CH4EHG3KRXWUJFMMNOG3TZ","short_pith_number":"pith:2O63CH4E","schema_version":"1.0","canonical_sha256":"d3bdb11f8439b6a8ded44958c6b8db9e4f911a05107a1aabd18e4c76331b54f6","source":{"kind":"arxiv","id":"1506.03784","version":3},"attestation_state":"computed","paper":{"title":"Sparse Partially Collapsed MCMC for Parallel Inference in Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.ML","authors_text":"David Broman, Leif Jonsson, M{\\aa}ns Magnusson, Mattias Villani","submitted_at":"2015-06-11T19:16:01Z","abstract_excerpt":"Topic models, and more specifically the class of Latent Dirichlet Allocation (LDA), are widely used for probabilistic modeling of text. MCMC sampling from the posterior distribution is typically performed using a collapsed Gibbs sampler. We propose a parallel sparse partially collapsed Gibbs sampler and compare its speed and efficiency to state-of-the-art samplers for topic models on five well-known text corpora of differing sizes and properties. In particular, we propose and compare two different strategies for sampling the parameter block with latent topic indicators. The experiments show th"},"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":"1506.03784","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-06-11T19:16:01Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"377588a20ac7e2e779d3d4280d7a9b48133ae59508fbcd93e2286bca35cb8b43","abstract_canon_sha256":"49150169f32b7ae14f3f8befc3bfda94d2fea69b516f9597af0765a05b29ade9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:06.588182Z","signature_b64":"QUML2CEhG/V8ukM3QiASKMDOzUJFfcJJ81OqdqyHtOmnBzJxD7C+DziOrvm+ooyENbgqqdv8z4PIu1+EM02yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3bdb11f8439b6a8ded44958c6b8db9e4f911a05107a1aabd18e4c76331b54f6","last_reissued_at":"2026-05-18T00:38:06.587741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:06.587741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Partially Collapsed MCMC for Parallel Inference in Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.ML","authors_text":"David Broman, Leif Jonsson, M{\\aa}ns Magnusson, Mattias Villani","submitted_at":"2015-06-11T19:16:01Z","abstract_excerpt":"Topic models, and more specifically the class of Latent Dirichlet Allocation (LDA), are widely used for probabilistic modeling of text. MCMC sampling from the posterior distribution is typically performed using a collapsed Gibbs sampler. We propose a parallel sparse partially collapsed Gibbs sampler and compare its speed and efficiency to state-of-the-art samplers for topic models on five well-known text corpora of differing sizes and properties. In particular, we propose and compare two different strategies for sampling the parameter block with latent topic indicators. The experiments show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03784","kind":"arxiv","version":3},"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":"1506.03784","created_at":"2026-05-18T00:38:06.587797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03784v3","created_at":"2026-05-18T00:38:06.587797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03784","created_at":"2026-05-18T00:38:06.587797+00:00"},{"alias_kind":"pith_short_12","alias_value":"2O63CH4EHG3K","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"2O63CH4EHG3KRXWU","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"2O63CH4E","created_at":"2026-05-18T12:29:02.477457+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/2O63CH4EHG3KRXWUJFMMNOG3TZ","json":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ.json","graph_json":"https://pith.science/api/pith-number/2O63CH4EHG3KRXWUJFMMNOG3TZ/graph.json","events_json":"https://pith.science/api/pith-number/2O63CH4EHG3KRXWUJFMMNOG3TZ/events.json","paper":"https://pith.science/paper/2O63CH4E"},"agent_actions":{"view_html":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ","download_json":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ.json","view_paper":"https://pith.science/paper/2O63CH4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03784&json=true","fetch_graph":"https://pith.science/api/pith-number/2O63CH4EHG3KRXWUJFMMNOG3TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2O63CH4EHG3KRXWUJFMMNOG3TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ/action/storage_attestation","attest_author":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ/action/author_attestation","sign_citation":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ/action/citation_signature","submit_replication":"https://pith.science/pith/2O63CH4EHG3KRXWUJFMMNOG3TZ/action/replication_record"}},"created_at":"2026-05-18T00:38:06.587797+00:00","updated_at":"2026-05-18T00:38:06.587797+00:00"}