{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WBU4HJGD3QEH5R2GMMQ7CVHYMP","short_pith_number":"pith:WBU4HJGD","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"},"canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","source":{"kind":"arxiv","id":"2501.04300","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04300","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04300v3","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04300","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"WBU4HJGD3QEH","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_16","alias_value":"WBU4HJGD3QEH5R2G","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_8","alias_value":"WBU4HJGD","created_at":"2026-07-05T11:44:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WBU4HJGD3QEH5R2GMMQ7CVHYMP","target":"record","payload":{"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"},"canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","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"},"source_kind":"arxiv","source_id":"2501.04300","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XoyLzFa5+X3jVDaeRBjT1Ot9YzAh5C+REv+TTvaRkDkReVaXaL9uTfbGK2kWNbub9+uZcT9qYxR/oNFB0TMEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:33:45.594264Z"},"content_sha256":"9f112587f9f07d3baf41675133e0c94e954a856513edf056b5f5310789162982","schema_version":"1.0","event_id":"sha256:9f112587f9f07d3baf41675133e0c94e954a856513edf056b5f5310789162982"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WBU4HJGD3QEH5R2GMMQ7CVHYMP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PawU0Qf1Nl0+Wf0I83gRtpr806FlSjUErwtNP8iwAAvFsQEWXrWHBi+2vgVJESUPyCLnZIFikUKkutcjkAbSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:33:45.595097Z"},"content_sha256":"d874da9cd53df176dc7648b6acb16f04e53e43ee07359c1e029d012bbe8e2ea2","schema_version":"1.0","event_id":"sha256:d874da9cd53df176dc7648b6acb16f04e53e43ee07359c1e029d012bbe8e2ea2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/bundle.json","state_url":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/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":"2026-08-12T08:33:45Z","links":{"resolver":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP","bundle":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/bundle.json","state":"https://pith.science/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBU4HJGD3QEH5R2GMMQ7CVHYMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WBU4HJGD3QEH5R2GMMQ7CVHYMP","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":"512297b18cd4f21890597773e0ab14e7dc156ae4deef14fbe1e2aaabbb10bdc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T06:18:32Z","title_canon_sha256":"ae39b8afe74b07d3515b49b447a055b93805e772bb527a8ccff941f12b809133"},"schema_version":"1.0","source":{"id":"2501.04300","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04300","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04300v3","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04300","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_12","alias_value":"WBU4HJGD3QEH","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_16","alias_value":"WBU4HJGD3QEH5R2G","created_at":"2026-07-05T11:44:43Z"},{"alias_kind":"pith_short_8","alias_value":"WBU4HJGD","created_at":"2026-07-05T11:44:43Z"}],"graph_snapshots":[{"event_id":"sha256:d874da9cd53df176dc7648b6acb16f04e53e43ee07359c1e029d012bbe8e2ea2","target":"graph","created_at":"2026-07-05T11:44:43Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.04300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jonathan Wells, Mohamed Reda Bouadjenek, Sunil Aryal, Youran Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T06:18:32Z","title":"HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04300","kind":"arxiv","version":3},"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":"sha256:9f112587f9f07d3baf41675133e0c94e954a856513edf056b5f5310789162982","target":"record","created_at":"2026-07-05T11:44:43Z","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":"512297b18cd4f21890597773e0ab14e7dc156ae4deef14fbe1e2aaabbb10bdc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T06:18:32Z","title_canon_sha256":"ae39b8afe74b07d3515b49b447a055b93805e772bb527a8ccff941f12b809133"},"schema_version":"1.0","source":{"id":"2501.04300","kind":"arxiv","version":3}},"canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b069c3a4c3dc087ec7466321f154f863fc391aea3e379d0f0e2b53a30fbbcbed","first_computed_at":"2026-07-05T11:44:43.998339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:43.998339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CFvmdvmC+R7SIcyQecfELNm/poebwe7H5ZZ6Efhdv19mPSer0LvFC33WvoTynwf4tq4VMGD2rmhjFOMab5WJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:43.998846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04300","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f112587f9f07d3baf41675133e0c94e954a856513edf056b5f5310789162982","sha256:d874da9cd53df176dc7648b6acb16f04e53e43ee07359c1e029d012bbe8e2ea2"],"state_sha256":"05f10d2c2f43c9d3646a8903424fe94fc19f85b12db74d6e19ec4688548f7d93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1WTvqYW2umEtUJhgVJErOY2pm3fmM+b5VXxjXT72WS0f2Ia/r9/lrybXzQ1BkJbUnjrvq044SwNaL0tlhyBJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:33:45.602079Z","bundle_sha256":"a4361c40b4f84bcba1bd8f26f7cd53f015550a7803767634c3828865b2b3a2d0"}}