{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WBU4HJGD3QEH5R2GMMQ7CVHYMP","short_pith_number":"pith:WBU4HJGD","schema_version":"1.0","canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","source":{"kind":"arxiv","id":"2501.04300","version":3},"attestation_state":"computed","paper":{"title":"HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Wells, Mohamed Reda Bouadjenek, Sunil Aryal, Youran Zhou","submitted_at":"2025-01-08T06:18:32Z","abstract_excerpt":"Handling incomplete and heterogeneous data remains a central challenge in real-world machine learning, where missing values may follow complex mechanisms (MCAR, MAR, MNAR) and features can be of mixed types (numerical and categorical). Existing methods often rely on imputation, which may introduce bias or privacy risks, or fail to jointly address data heterogeneity and structured missingness. We propose the \\textbf{H}eterogeneous \\textbf{I}ncomplete \\textbf{P}robability \\textbf{M}ass \\textbf{K}ernel (\\textbf{HI-PMK}), a novel data-dependent representation learning approach that eliminates the "},"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":"2501.04300","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T06:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"ae39b8afe74b07d3515b49b447a055b93805e772bb527a8ccff941f12b809133","abstract_canon_sha256":"512297b18cd4f21890597773e0ab14e7dc156ae4deef14fbe1e2aaabbb10bdc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:43.998846Z","signature_b64":"CFvmdvmC+R7SIcyQecfELNm/poebwe7H5ZZ6Efhdv19mPSer0LvFC33WvoTynwf4tq4VMGD2rmhjFOMab5WJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","last_reissued_at":"2026-07-05T11:44:43.998339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:43.998339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Wells, Mohamed Reda Bouadjenek, Sunil Aryal, Youran Zhou","submitted_at":"2025-01-08T06:18:32Z","abstract_excerpt":"Handling incomplete and heterogeneous data remains a central challenge in real-world machine learning, where missing values may follow complex mechanisms (MCAR, MAR, MNAR) and features can be of mixed types (numerical and categorical). Existing methods often rely on imputation, which may introduce bias or privacy risks, or fail to jointly address data heterogeneity and structured missingness. We propose the \\textbf{H}eterogeneous \\textbf{I}ncomplete \\textbf{P}robability \\textbf{M}ass \\textbf{K}ernel (\\textbf{HI-PMK}), a novel data-dependent representation learning approach that eliminates the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04300","kind":"arxiv","version":3},"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/2501.04300/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":"2501.04300","created_at":"2026-07-05T11:44:43.998406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04300v3","created_at":"2026-07-05T11:44:43.998406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04300","created_at":"2026-07-05T11:44:43.998406+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBU4HJGD3QEH","created_at":"2026-07-05T11:44:43.998406+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBU4HJGD3QEH5R2G","created_at":"2026-07-05T11:44:43.998406+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBU4HJGD","created_at":"2026-07-05T11:44:43.998406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04740","citing_title":"MissMecha: An All-in-One Python Package for Studying Missing Data Mechanisms","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP","json":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP.json","graph_json":"https://pith.science/api/pith-number/WBU4HJGD3QEH5R2GMMQ7CVHYMP/graph.json","events_json":"https://pith.science/api/pith-number/WBU4HJGD3QEH5R2GMMQ7CVHYMP/events.json","paper":"https://pith.science/paper/WBU4HJGD"},"agent_actions":{"view_html":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP","download_json":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP.json","view_paper":"https://pith.science/paper/WBU4HJGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04300&json=true","fetch_graph":"https://pith.science/api/pith-number/WBU4HJGD3QEH5R2GMMQ7CVHYMP/graph.json","fetch_events":"https://pith.science/api/pith-number/WBU4HJGD3QEH5R2GMMQ7CVHYMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/action/storage_attestation","attest_author":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/action/author_attestation","sign_citation":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/action/citation_signature","submit_replication":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/action/replication_record"}},"created_at":"2026-07-05T11:44:43.998406+00:00","updated_at":"2026-07-05T11:44:43.998406+00:00"}