{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7PJLZXBCKHYZ3OR65QD76LGPRY","short_pith_number":"pith:7PJLZXBC","schema_version":"1.0","canonical_sha256":"fbd2bcdc2251f19dba3eec07ff2ccf8e022e35bf463e5099beb4b6323c44713d","source":{"kind":"arxiv","id":"1703.04832","version":1},"attestation_state":"computed","paper":{"title":"A Random Finite Set Model for Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ba-Ngu Bo, Dinh Phung","submitted_at":"2017-03-14T23:35:57Z","abstract_excerpt":"The goal of data clustering is to partition data points into groups to minimize a given objective function. While most existing clustering algorithms treat each data point as vector, in many applications each datum is not a vector but a point pattern or a set of points. Moreover, many existing clustering methods require the user to specify the number of clusters, which is not available in advance. This paper proposes a new class of models for data clustering that addresses set-valued data as well as unknown number of clusters, using a Dirichlet Process mixture of Poisson random finite sets. We"},"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":"1703.04832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-14T23:35:57Z","cross_cats_sorted":[],"title_canon_sha256":"0b288964a5accb58480e803aa7243f187681e6d5e24ea96645c568005693f664","abstract_canon_sha256":"db23d0431a362ec0a8054651aa9cae0b08e5584ce5ae072911d8145b39102a3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:39.156590Z","signature_b64":"Wahc7xqBo85X1MosOWpt/2Mrl8jPcaEyO2V69BQqzm6w6vCkwG38dbfIidLAcvUIetrBQIap1pGmsDplvVthBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbd2bcdc2251f19dba3eec07ff2ccf8e022e35bf463e5099beb4b6323c44713d","last_reissued_at":"2026-05-18T00:48:39.156187Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:39.156187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Random Finite Set Model for Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ba-Ngu Bo, Dinh Phung","submitted_at":"2017-03-14T23:35:57Z","abstract_excerpt":"The goal of data clustering is to partition data points into groups to minimize a given objective function. While most existing clustering algorithms treat each data point as vector, in many applications each datum is not a vector but a point pattern or a set of points. Moreover, many existing clustering methods require the user to specify the number of clusters, which is not available in advance. This paper proposes a new class of models for data clustering that addresses set-valued data as well as unknown number of clusters, using a Dirichlet Process mixture of Poisson random finite sets. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04832","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":"1703.04832","created_at":"2026-05-18T00:48:39.156250+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04832v1","created_at":"2026-05-18T00:48:39.156250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04832","created_at":"2026-05-18T00:48:39.156250+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PJLZXBCKHYZ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PJLZXBCKHYZ3OR6","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PJLZXBC","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09562","citing_title":"Laplace Variational Inference for Dirichlet Process Mixtures of Marked Poisson Point Processes","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY","json":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY.json","graph_json":"https://pith.science/api/pith-number/7PJLZXBCKHYZ3OR65QD76LGPRY/graph.json","events_json":"https://pith.science/api/pith-number/7PJLZXBCKHYZ3OR65QD76LGPRY/events.json","paper":"https://pith.science/paper/7PJLZXBC"},"agent_actions":{"view_html":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY","download_json":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY.json","view_paper":"https://pith.science/paper/7PJLZXBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04832&json=true","fetch_graph":"https://pith.science/api/pith-number/7PJLZXBCKHYZ3OR65QD76LGPRY/graph.json","fetch_events":"https://pith.science/api/pith-number/7PJLZXBCKHYZ3OR65QD76LGPRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY/action/storage_attestation","attest_author":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY/action/author_attestation","sign_citation":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY/action/citation_signature","submit_replication":"https://pith.science/pith/7PJLZXBCKHYZ3OR65QD76LGPRY/action/replication_record"}},"created_at":"2026-05-18T00:48:39.156250+00:00","updated_at":"2026-05-18T00:48:39.156250+00:00"}