{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7DRHSFEZYUP3UVOHPJCVAALDY","short_pith_number":"pith:F7DRHSFE","schema_version":"1.0","canonical_sha256":"2fc713c8a4ce28fdd2ae3bd22a800b1e0d93905e7d687a87d0e96040a30ca458","source":{"kind":"arxiv","id":"2409.08954","version":1},"attestation_state":"computed","paper":{"title":"A Bayesian Approach to Clustering via the Proper Bayesian Bootstrap: the Bayesian Bagged Clustering (BBC) algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elena ballante, Federico Maria Quetti, Silvia Figini","submitted_at":"2024-09-13T16:14:54Z","abstract_excerpt":"The paper presents a novel approach for unsupervised techniques in the field of clustering. A new method is proposed to enhance existing literature models using the proper Bayesian bootstrap to improve results in terms of robustness and interpretability. Our approach is organized in two steps: k-means clustering is used for prior elicitation, then proper Bayesian bootstrap is applied as resampling method in an ensemble clustering approach. Results are analyzed introducing measures of uncertainty based on Shannon entropy. The proposal provides clear indication on the optimal number of clusters,"},"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":"2409.08954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-09-13T16:14:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"190807657feaf63da3b234daf39135f86eb09177917285067c0de3afc3d6d504","abstract_canon_sha256":"c6125fb1116f8974f8e8d1b66a6ef8805ed223669253bcf48677845f6e724bad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:50.205159Z","signature_b64":"pn/RhscEtncDOAcK1Y5eVgNXmyx4mN7hSisIfMqBBrhDprLZyNIsgMxgh86Lusrf9Uo4ubej9R0tcy4wjSzUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc713c8a4ce28fdd2ae3bd22a800b1e0d93905e7d687a87d0e96040a30ca458","last_reissued_at":"2026-07-05T09:06:50.204785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:50.204785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bayesian Approach to Clustering via the Proper Bayesian Bootstrap: the Bayesian Bagged Clustering (BBC) algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elena ballante, Federico Maria Quetti, Silvia Figini","submitted_at":"2024-09-13T16:14:54Z","abstract_excerpt":"The paper presents a novel approach for unsupervised techniques in the field of clustering. A new method is proposed to enhance existing literature models using the proper Bayesian bootstrap to improve results in terms of robustness and interpretability. Our approach is organized in two steps: k-means clustering is used for prior elicitation, then proper Bayesian bootstrap is applied as resampling method in an ensemble clustering approach. Results are analyzed introducing measures of uncertainty based on Shannon entropy. The proposal provides clear indication on the optimal number of clusters,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08954","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.08954/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2409.08954","created_at":"2026-07-05T09:06:50.204841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08954v1","created_at":"2026-07-05T09:06:50.204841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08954","created_at":"2026-07-05T09:06:50.204841+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7DRHSFEZYUP","created_at":"2026-07-05T09:06:50.204841+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7DRHSFEZYUP3UVO","created_at":"2026-07-05T09:06:50.204841+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7DRHSFE","created_at":"2026-07-05T09:06:50.204841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03458","citing_title":"Understanding the Impact of Evaluation Metrics in Kinetic Models for Consensus-based Segmentation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY","json":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY.json","graph_json":"https://pith.science/api/pith-number/F7DRHSFEZYUP3UVOHPJCVAALDY/graph.json","events_json":"https://pith.science/api/pith-number/F7DRHSFEZYUP3UVOHPJCVAALDY/events.json","paper":"https://pith.science/paper/F7DRHSFE"},"agent_actions":{"view_html":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY","download_json":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY.json","view_paper":"https://pith.science/paper/F7DRHSFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08954&json=true","fetch_graph":"https://pith.science/api/pith-number/F7DRHSFEZYUP3UVOHPJCVAALDY/graph.json","fetch_events":"https://pith.science/api/pith-number/F7DRHSFEZYUP3UVOHPJCVAALDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY/action/storage_attestation","attest_author":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY/action/author_attestation","sign_citation":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY/action/citation_signature","submit_replication":"https://pith.science/pith/F7DRHSFEZYUP3UVOHPJCVAALDY/action/replication_record"}},"created_at":"2026-07-05T09:06:50.204841+00:00","updated_at":"2026-07-05T09:06:50.204841+00:00"}