{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:AX3YLHJ6ERD3PE2KXSD2ABDYCX","short_pith_number":"pith:AX3YLHJ6","schema_version":"1.0","canonical_sha256":"05f7859d3e2447b7934abc87a0047815d6a12f54a70563c4fafcc7ac58af3590","source":{"kind":"arxiv","id":"1201.1657","version":1},"attestation_state":"computed","paper":{"title":"A Split-Merge MCMC Algorithm for the Hierarchical Dirichlet Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Chong Wang, David M. Blei","submitted_at":"2012-01-08T20:28:42Z","abstract_excerpt":"The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterior inference is intractable---practitioners use Markov chain Monte Carlo (MCMC) or variational inference. Inspired by the split-merge MCMC algorithm for the Dirichlet process (DP) mixture model, we describe a novel split-merge MCMC sampling algorithm for posterior inference in 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":"1201.1657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-01-08T20:28:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c09ecff2cc841a73fa219d3f0722307baa26f65ce0ca50ff7efd3c3cd5148ce","abstract_canon_sha256":"8f05ed4d0de84b4dd5ba63a2147b3882a3d401d154b4406acdeda4fb5bb87009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:05:02.887851Z","signature_b64":"zcgu+b7LATNNDR04eVVUhQ3rTkIw3q5tpctnwsGtO76TCQf3NR7CkNzcD/AmIY8wSnG5Evvdom0B/F4ZwoCpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f7859d3e2447b7934abc87a0047815d6a12f54a70563c4fafcc7ac58af3590","last_reissued_at":"2026-05-18T04:05:02.887200Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:05:02.887200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Split-Merge MCMC Algorithm for the Hierarchical Dirichlet Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Chong Wang, David M. Blei","submitted_at":"2012-01-08T20:28:42Z","abstract_excerpt":"The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterior inference is intractable---practitioners use Markov chain Monte Carlo (MCMC) or variational inference. Inspired by the split-merge MCMC algorithm for the Dirichlet process (DP) mixture model, we describe a novel split-merge MCMC sampling algorithm for posterior inference in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.1657","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":"1201.1657","created_at":"2026-05-18T04:05:02.887288+00:00"},{"alias_kind":"arxiv_version","alias_value":"1201.1657v1","created_at":"2026-05-18T04:05:02.887288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.1657","created_at":"2026-05-18T04:05:02.887288+00:00"},{"alias_kind":"pith_short_12","alias_value":"AX3YLHJ6ERD3","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_16","alias_value":"AX3YLHJ6ERD3PE2K","created_at":"2026-05-18T12:26:58.693483+00:00"},{"alias_kind":"pith_short_8","alias_value":"AX3YLHJ6","created_at":"2026-05-18T12:26:58.693483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09445","citing_title":"Learning with fuzzy hypergraphs: a topical approach to query-oriented text summarization","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX","json":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX.json","graph_json":"https://pith.science/api/pith-number/AX3YLHJ6ERD3PE2KXSD2ABDYCX/graph.json","events_json":"https://pith.science/api/pith-number/AX3YLHJ6ERD3PE2KXSD2ABDYCX/events.json","paper":"https://pith.science/paper/AX3YLHJ6"},"agent_actions":{"view_html":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX","download_json":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX.json","view_paper":"https://pith.science/paper/AX3YLHJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1201.1657&json=true","fetch_graph":"https://pith.science/api/pith-number/AX3YLHJ6ERD3PE2KXSD2ABDYCX/graph.json","fetch_events":"https://pith.science/api/pith-number/AX3YLHJ6ERD3PE2KXSD2ABDYCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX/action/storage_attestation","attest_author":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX/action/author_attestation","sign_citation":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX/action/citation_signature","submit_replication":"https://pith.science/pith/AX3YLHJ6ERD3PE2KXSD2ABDYCX/action/replication_record"}},"created_at":"2026-05-18T04:05:02.887288+00:00","updated_at":"2026-05-18T04:05:02.887288+00:00"}