{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:SQ7S4PTGLBX4EI6SMAHM77HMIF","short_pith_number":"pith:SQ7S4PTG","canonical_record":{"source":{"id":"1610.09780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2016-10-31T04:00:11Z","cross_cats_sorted":["math.ST","stat.AP","stat.ML","stat.TH"],"title_canon_sha256":"413045eac35cb4280c18073fde6fb54160f132cb8c5fcb13bc05c63641a94544","abstract_canon_sha256":"70a7f3899763405e513e4d611e4248755e70ea7709d86c79933ac634fa4fd933"},"schema_version":"1.0"},"canonical_sha256":"943f2e3e66586fc223d2600ecffcec41701c269d808d971f69551d73edc78f01","source":{"kind":"arxiv","id":"1610.09780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09780","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09780v1","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09780","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"SQ7S4PTGLBX4","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SQ7S4PTGLBX4EI6S","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SQ7S4PTG","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:SQ7S4PTGLBX4EI6SMAHM77HMIF","target":"record","payload":{"canonical_record":{"source":{"id":"1610.09780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2016-10-31T04:00:11Z","cross_cats_sorted":["math.ST","stat.AP","stat.ML","stat.TH"],"title_canon_sha256":"413045eac35cb4280c18073fde6fb54160f132cb8c5fcb13bc05c63641a94544","abstract_canon_sha256":"70a7f3899763405e513e4d611e4248755e70ea7709d86c79933ac634fa4fd933"},"schema_version":"1.0"},"canonical_sha256":"943f2e3e66586fc223d2600ecffcec41701c269d808d971f69551d73edc78f01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:47.199842Z","signature_b64":"7pVvuJAv08ZshXh6Qi7H1+n1f9/KQlwNchK9ppS94yAtzX7czarA7crCeuSM56rc72OpwEsZZkf8TJP+KmjmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"943f2e3e66586fc223d2600ecffcec41701c269d808d971f69551d73edc78f01","last_reissued_at":"2026-05-18T01:00:47.199446Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:47.199446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.09780","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PM4o1g4/T8Sqhe+HEMsIWBW0RWHraGp7+f75QgsXNnHN+bXd1blLIDKE/fO/m0jeLZqPTOJSMcZaN0PcW3VSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:07:25.169419Z"},"content_sha256":"30b3ab55ae6ea8aac10fa96f30bb039a9d4fd00e7e8de40b1c13e5c6aa54d0ff","schema_version":"1.0","event_id":"sha256:30b3ab55ae6ea8aac10fa96f30bb039a9d4fd00e7e8de40b1c13e5c6aa54d0ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:SQ7S4PTGLBX4EI6SMAHM77HMIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flexible Models for Microclustering with Application to Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.AP","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"Abbas Zaidi, Brenda Betancourt, Giacomo Zanella, Hanna Wallach, Jeffrey Miller, Rebecca C. Steorts","submitted_at":"2016-10-31T04:00:11Z","abstract_excerpt":"Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman--Yor process mixture models make this assumption, as do all other infinitely exchangeable clustering models. However, for some applications, this assumption is inappropriate. For example, when performing entity resolution, the size of each cluster should be unrelated to the size of the data set, and each cluster should contain a negligible fraction of the total number of da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09780","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HLX/NJtseboiuLMlNLRQplsCeOoCHqK38gJEwRWyv47T4Gme1iGHTNFcgtwDe1Pce8Od6h356FCqHwghrv84Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:07:25.170074Z"},"content_sha256":"8c6ec99e1bd9a12e5957890a6aacde88805a3b7817cdbc82f9faec2a613d33cb","schema_version":"1.0","event_id":"sha256:8c6ec99e1bd9a12e5957890a6aacde88805a3b7817cdbc82f9faec2a613d33cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/bundle.json","state_url":"https://pith.science/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T15:07:25Z","links":{"resolver":"https://pith.science/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF","bundle":"https://pith.science/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/bundle.json","state":"https://pith.science/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQ7S4PTGLBX4EI6SMAHM77HMIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:SQ7S4PTGLBX4EI6SMAHM77HMIF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"70a7f3899763405e513e4d611e4248755e70ea7709d86c79933ac634fa4fd933","cross_cats_sorted":["math.ST","stat.AP","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2016-10-31T04:00:11Z","title_canon_sha256":"413045eac35cb4280c18073fde6fb54160f132cb8c5fcb13bc05c63641a94544"},"schema_version":"1.0","source":{"id":"1610.09780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09780","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09780v1","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09780","created_at":"2026-05-18T01:00:47Z"},{"alias_kind":"pith_short_12","alias_value":"SQ7S4PTGLBX4","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SQ7S4PTGLBX4EI6S","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SQ7S4PTG","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:8c6ec99e1bd9a12e5957890a6aacde88805a3b7817cdbc82f9faec2a613d33cb","target":"graph","created_at":"2026-05-18T01:00:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman--Yor process mixture models make this assumption, as do all other infinitely exchangeable clustering models. However, for some applications, this assumption is inappropriate. For example, when performing entity resolution, the size of each cluster should be unrelated to the size of the data set, and each cluster should contain a negligible fraction of the total number of da","authors_text":"Abbas Zaidi, Brenda Betancourt, Giacomo Zanella, Hanna Wallach, Jeffrey Miller, Rebecca C. Steorts","cross_cats":["math.ST","stat.AP","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2016-10-31T04:00:11Z","title":"Flexible Models for Microclustering with Application to Entity Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09780","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30b3ab55ae6ea8aac10fa96f30bb039a9d4fd00e7e8de40b1c13e5c6aa54d0ff","target":"record","created_at":"2026-05-18T01:00:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"70a7f3899763405e513e4d611e4248755e70ea7709d86c79933ac634fa4fd933","cross_cats_sorted":["math.ST","stat.AP","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2016-10-31T04:00:11Z","title_canon_sha256":"413045eac35cb4280c18073fde6fb54160f132cb8c5fcb13bc05c63641a94544"},"schema_version":"1.0","source":{"id":"1610.09780","kind":"arxiv","version":1}},"canonical_sha256":"943f2e3e66586fc223d2600ecffcec41701c269d808d971f69551d73edc78f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"943f2e3e66586fc223d2600ecffcec41701c269d808d971f69551d73edc78f01","first_computed_at":"2026-05-18T01:00:47.199446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:47.199446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7pVvuJAv08ZshXh6Qi7H1+n1f9/KQlwNchK9ppS94yAtzX7czarA7crCeuSM56rc72OpwEsZZkf8TJP+KmjmBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:47.199842Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.09780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30b3ab55ae6ea8aac10fa96f30bb039a9d4fd00e7e8de40b1c13e5c6aa54d0ff","sha256:8c6ec99e1bd9a12e5957890a6aacde88805a3b7817cdbc82f9faec2a613d33cb"],"state_sha256":"9c9df6f5a0cca5845e888b7d334e6caf2a3c04a906577f45e760fc409f0006ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LUzExts/jKZwZYsW7QQEih2RulOsP33KTIUBk86Y6p0KOVdm2JTcyoC4760MvINXyjhq2Jjnr1t+yjMkntpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:07:25.172823Z","bundle_sha256":"7fe4deae87170ae3641dfd2bf1d678b322874311275e43e95b5364c1c69910dd"}}