{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:TQNRRIPSVBMFA7ZYNAAQQPUNU4","short_pith_number":"pith:TQNRRIPS","canonical_record":{"source":{"id":"1408.4140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-08-18T20:12:09Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"0d0d8a7c47b1631003dba009cff23b6eb2f4c754302eeb320fba89c4d8c5c51a","abstract_canon_sha256":"8b6b201ca6f996230bef9cdf4cd1c5e9196ddf9c1619e2f02e6bb71a7fe07223"},"schema_version":"1.0"},"canonical_sha256":"9c1b18a1f2a858507f386801083e8da736ddb48d03357e8d51ee3ec8647887a0","source":{"kind":"arxiv","id":"1408.4140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.4140","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"arxiv_version","alias_value":"1408.4140v1","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.4140","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"pith_short_12","alias_value":"TQNRRIPSVBMF","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TQNRRIPSVBMFA7ZY","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TQNRRIPS","created_at":"2026-05-18T12:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:TQNRRIPSVBMFA7ZYNAAQQPUNU4","target":"record","payload":{"canonical_record":{"source":{"id":"1408.4140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-08-18T20:12:09Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"0d0d8a7c47b1631003dba009cff23b6eb2f4c754302eeb320fba89c4d8c5c51a","abstract_canon_sha256":"8b6b201ca6f996230bef9cdf4cd1c5e9196ddf9c1619e2f02e6bb71a7fe07223"},"schema_version":"1.0"},"canonical_sha256":"9c1b18a1f2a858507f386801083e8da736ddb48d03357e8d51ee3ec8647887a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:56.001568Z","signature_b64":"1k1yICoxRR2A10YlxIeaD06G/PMQ63QrH1YqrG3nSFDB3pvIPnJWtWItHZzTOmOebrAulgA9wR3l8m1BHCy4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c1b18a1f2a858507f386801083e8da736ddb48d03357e8d51ee3ec8647887a0","last_reissued_at":"2026-05-18T02:44:56.001146Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:56.001146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1408.4140","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":"2026-05-18T02:44:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVP+fQZs5JoTGGzxsuw+rXP5h9D7tt1U0OCHBP3LpWq1lh9OK8IWYEAtwYFM4TTMV/nFJ1Pebgyhl6QG38dpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:05:56.550370Z"},"content_sha256":"fc35f75cbc24be247f40106bd3a18e9cf0c91e4bbb8b2e9fd8d5a419af002b3f","schema_version":"1.0","event_id":"sha256:fc35f75cbc24be247f40106bd3a18e9cf0c91e4bbb8b2e9fd8d5a419af002b3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:TQNRRIPSVBMFA7ZYNAAQQPUNU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BET: Bayesian Ensemble Trees for Clustering and Prediction in Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"stat.ML","authors_text":"John P. Clancy, Leo L. Duan, Rhonda D. Szczesniak","submitted_at":"2014-08-18T20:12:09Z","abstract_excerpt":"We propose a novel \"tree-averaging\" model that utilizes the ensemble of classification and regression trees (CART). Each constituent tree is estimated with a subset of similar data. We treat this grouping of subsets as Bayesian ensemble trees (BET) and model them as an infinite mixture Dirichlet process. We show that BET adapts to data heterogeneity and accurately estimates each component. Compared with the bootstrap-aggregating approach, BET shows improved prediction performance with fewer trees. We develop an efficient estimating procedure with improved sampling strategies in both CART and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.4140","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":"2026-05-18T02:44:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0Ew8GLKpkB27440+OQDOeaOwlFpTw0rVsShnzp2h//NVCdT1Y2V3erfuVTDHBi7Iiyv84guZ/OAYHzUf+NFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T03:05:56.550734Z"},"content_sha256":"4742f12a9dbcc65448525e745d30ddc99920711566b77c8c967b66f25ee5f972","schema_version":"1.0","event_id":"sha256:4742f12a9dbcc65448525e745d30ddc99920711566b77c8c967b66f25ee5f972"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/bundle.json","state_url":"https://pith.science/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/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":"2026-06-12T03:05:56Z","links":{"resolver":"https://pith.science/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4","bundle":"https://pith.science/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/bundle.json","state":"https://pith.science/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQNRRIPSVBMFA7ZYNAAQQPUNU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:TQNRRIPSVBMFA7ZYNAAQQPUNU4","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":"8b6b201ca6f996230bef9cdf4cd1c5e9196ddf9c1619e2f02e6bb71a7fe07223","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-08-18T20:12:09Z","title_canon_sha256":"0d0d8a7c47b1631003dba009cff23b6eb2f4c754302eeb320fba89c4d8c5c51a"},"schema_version":"1.0","source":{"id":"1408.4140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.4140","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"arxiv_version","alias_value":"1408.4140v1","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.4140","created_at":"2026-05-18T02:44:56Z"},{"alias_kind":"pith_short_12","alias_value":"TQNRRIPSVBMF","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TQNRRIPSVBMFA7ZY","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TQNRRIPS","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:4742f12a9dbcc65448525e745d30ddc99920711566b77c8c967b66f25ee5f972","target":"graph","created_at":"2026-05-18T02:44:56Z","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":"We propose a novel \"tree-averaging\" model that utilizes the ensemble of classification and regression trees (CART). Each constituent tree is estimated with a subset of similar data. We treat this grouping of subsets as Bayesian ensemble trees (BET) and model them as an infinite mixture Dirichlet process. We show that BET adapts to data heterogeneity and accurately estimates each component. Compared with the bootstrap-aggregating approach, BET shows improved prediction performance with fewer trees. We develop an efficient estimating procedure with improved sampling strategies in both CART and m","authors_text":"John P. Clancy, Leo L. Duan, Rhonda D. Szczesniak","cross_cats":["stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-08-18T20:12:09Z","title":"BET: Bayesian Ensemble Trees for Clustering and Prediction in Heterogeneous Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.4140","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:fc35f75cbc24be247f40106bd3a18e9cf0c91e4bbb8b2e9fd8d5a419af002b3f","target":"record","created_at":"2026-05-18T02:44:56Z","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":"8b6b201ca6f996230bef9cdf4cd1c5e9196ddf9c1619e2f02e6bb71a7fe07223","cross_cats_sorted":["stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-08-18T20:12:09Z","title_canon_sha256":"0d0d8a7c47b1631003dba009cff23b6eb2f4c754302eeb320fba89c4d8c5c51a"},"schema_version":"1.0","source":{"id":"1408.4140","kind":"arxiv","version":1}},"canonical_sha256":"9c1b18a1f2a858507f386801083e8da736ddb48d03357e8d51ee3ec8647887a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c1b18a1f2a858507f386801083e8da736ddb48d03357e8d51ee3ec8647887a0","first_computed_at":"2026-05-18T02:44:56.001146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:56.001146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1k1yICoxRR2A10YlxIeaD06G/PMQ63QrH1YqrG3nSFDB3pvIPnJWtWItHZzTOmOebrAulgA9wR3l8m1BHCy4Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:56.001568Z","signed_message":"canonical_sha256_bytes"},"source_id":"1408.4140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc35f75cbc24be247f40106bd3a18e9cf0c91e4bbb8b2e9fd8d5a419af002b3f","sha256:4742f12a9dbcc65448525e745d30ddc99920711566b77c8c967b66f25ee5f972"],"state_sha256":"f931bcbbaaf5a44f94fa4b821df3f403bf51ec4122f485158dd2b5cb677c266f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ouoMr/bvJoKGudJwvJdv1Ci4fFjKuJgDqphooW9t2TVk0jPXf+pJSJYvINIoTknwi8UwOUyKW0z2AvZEdxcrDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T03:05:56.552921Z","bundle_sha256":"f388e9b530fe5cee1101ce2cd9e9bd11ff6cbfbcf96b0c3a5ac3d29ee44f8cdb"}}