{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JQ745D3NFGTB2OE34RNCW5BWKR","short_pith_number":"pith:JQ745D3N","schema_version":"1.0","canonical_sha256":"4c3fce8f6d29a61d389be45a2b7436547e1304b150be6773e1dd0381c5a1bf10","source":{"kind":"arxiv","id":"1705.01877","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised model-based clustering with controlled clusters leakage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacek Tabor, {\\L}ukasz Struski, Marek \\'Smieja","submitted_at":"2017-05-04T15:13:28Z","abstract_excerpt":"In this paper, we focus on finding clusters in partially categorized data sets. We propose a semi-supervised version of Gaussian mixture model, called C3L, which retrieves natural subgroups of given categories. In contrast to other semi-supervised models, C3L is parametrized by user-defined leakage level, which controls maximal inconsistency between initial categorization and resulting clustering. Our method can be implemented as a module in practical expert systems to detect clusters, which combine expert knowledge with true distribution of data. Moreover, it can be used for improving the res"},"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":"1705.01877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-04T15:13:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4334fb89de43a14c8a7b6e366968bcc6725aa564bb7c34be31b6c2302ca33c4","abstract_canon_sha256":"c37e77b9c387634a14f760b82a4865a49236d271b8c033b064f645d411d2d1e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:02.127388Z","signature_b64":"71jgnGxqJpp3P6RCeFfQ1tMU3U05x8Q6YvnEwlPuYW1Rwzu/NBN/E69d3hiL006ctcs4LUQFYqgJ5WI/YvcjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c3fce8f6d29a61d389be45a2b7436547e1304b150be6773e1dd0381c5a1bf10","last_reissued_at":"2026-05-18T00:45:02.126944Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:02.126944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised model-based clustering with controlled clusters leakage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacek Tabor, {\\L}ukasz Struski, Marek \\'Smieja","submitted_at":"2017-05-04T15:13:28Z","abstract_excerpt":"In this paper, we focus on finding clusters in partially categorized data sets. We propose a semi-supervised version of Gaussian mixture model, called C3L, which retrieves natural subgroups of given categories. In contrast to other semi-supervised models, C3L is parametrized by user-defined leakage level, which controls maximal inconsistency between initial categorization and resulting clustering. Our method can be implemented as a module in practical expert systems to detect clusters, which combine expert knowledge with true distribution of data. Moreover, it can be used for improving the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01877","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":"1705.01877","created_at":"2026-05-18T00:45:02.127002+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.01877v1","created_at":"2026-05-18T00:45:02.127002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01877","created_at":"2026-05-18T00:45:02.127002+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQ745D3NFGTB","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQ745D3NFGTB2OE3","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQ745D3N","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR","json":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR.json","graph_json":"https://pith.science/api/pith-number/JQ745D3NFGTB2OE34RNCW5BWKR/graph.json","events_json":"https://pith.science/api/pith-number/JQ745D3NFGTB2OE34RNCW5BWKR/events.json","paper":"https://pith.science/paper/JQ745D3N"},"agent_actions":{"view_html":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR","download_json":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR.json","view_paper":"https://pith.science/paper/JQ745D3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.01877&json=true","fetch_graph":"https://pith.science/api/pith-number/JQ745D3NFGTB2OE34RNCW5BWKR/graph.json","fetch_events":"https://pith.science/api/pith-number/JQ745D3NFGTB2OE34RNCW5BWKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR/action/storage_attestation","attest_author":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR/action/author_attestation","sign_citation":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR/action/citation_signature","submit_replication":"https://pith.science/pith/JQ745D3NFGTB2OE34RNCW5BWKR/action/replication_record"}},"created_at":"2026-05-18T00:45:02.127002+00:00","updated_at":"2026-05-18T00:45:02.127002+00:00"}