{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P7OKCDDQIWFKVQAQB6FLJNFB4C","short_pith_number":"pith:P7OKCDDQ","canonical_record":{"source":{"id":"2412.12864","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T12:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"e1e98fab3a2b0fede1de04a599999648b116706be2e57d36603cf233de32f173","abstract_canon_sha256":"ad0c1cef73bc95c27206ff73b9c52335ed64c304a36cdf18466298558ab4cbf9"},"schema_version":"1.0"},"canonical_sha256":"7fdca10c70458aaac0100f8ab4b4a1e0a1bbe454bd9f3711141903bdb867634d","source":{"kind":"arxiv","id":"2412.12864","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12864","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12864v2","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12864","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_12","alias_value":"P7OKCDDQIWFK","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_16","alias_value":"P7OKCDDQIWFKVQAQ","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_8","alias_value":"P7OKCDDQ","created_at":"2026-07-05T10:52:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P7OKCDDQIWFKVQAQB6FLJNFB4C","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12864","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T12:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"e1e98fab3a2b0fede1de04a599999648b116706be2e57d36603cf233de32f173","abstract_canon_sha256":"ad0c1cef73bc95c27206ff73b9c52335ed64c304a36cdf18466298558ab4cbf9"},"schema_version":"1.0"},"canonical_sha256":"7fdca10c70458aaac0100f8ab4b4a1e0a1bbe454bd9f3711141903bdb867634d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:57.341791Z","signature_b64":"ZghZOndPqfiiybuG+3Hl6ePTsCe2PCLtoKp4FirudSSudzK7aIrzjnzpo73Y39/z9ZbgEikGkhMpUU6HFNoMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fdca10c70458aaac0100f8ab4b4a1e0a1bbe454bd9f3711141903bdb867634d","last_reissued_at":"2026-07-05T10:52:57.341265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:57.341265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12864","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XhDHEfG+N+CoJtWwW1Owlm0fPuxu52pFNRqHDYU/nWE9iCXs2jx6LOq3pSeIlQKjT66YF68NYumNTRqTOt9NDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:47:05.010669Z"},"content_sha256":"f302dde325f3f6bccad9e8bf27a963105a2d3b71d759542d9947d2faed870199","schema_version":"1.0","event_id":"sha256:f302dde325f3f6bccad9e8bf27a963105a2d3b71d759542d9947d2faed870199"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P7OKCDDQIWFKVQAQB6FLJNFB4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yongjae Lee, Yoontae Hwang","submitted_at":"2024-12-17T12:47:53Z","abstract_excerpt":"Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationships within such data. We propose GFTab (Geodesic Flow Kernels for Semi- Supervised Learning on Mixed-Variable Tabular Dataset), a semi-supervised framework specifically designed for tabular datasets. GFTab incorporates three key innovations: 1) Variable-specific corruption methods tailored to the distinct properties of continuous and categorical variables, 2) A Geodesic flow ke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12864","kind":"arxiv","version":2},"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/2412.12864/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":"2026-07-05T10:52:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkIiGDL0ZHF95po9rtV8T5pLQZ+YQfYCNmshUF39uPJPfyG1Yi6yeTM05LParrTxlkDdKcMBM+zznYPkUx8tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:47:05.011529Z"},"content_sha256":"64f4c3498d8d6fd747cf92e0e274782eab7669cc5424416cb24d5ba75eed8ba5","schema_version":"1.0","event_id":"sha256:64f4c3498d8d6fd747cf92e0e274782eab7669cc5424416cb24d5ba75eed8ba5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/bundle.json","state_url":"https://pith.science/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/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":"2026-08-17T08:47:05Z","links":{"resolver":"https://pith.science/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C","bundle":"https://pith.science/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/bundle.json","state":"https://pith.science/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7OKCDDQIWFKVQAQB6FLJNFB4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P7OKCDDQIWFKVQAQB6FLJNFB4C","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":"ad0c1cef73bc95c27206ff73b9c52335ed64c304a36cdf18466298558ab4cbf9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T12:47:53Z","title_canon_sha256":"e1e98fab3a2b0fede1de04a599999648b116706be2e57d36603cf233de32f173"},"schema_version":"1.0","source":{"id":"2412.12864","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12864","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12864v2","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12864","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_12","alias_value":"P7OKCDDQIWFK","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_16","alias_value":"P7OKCDDQIWFKVQAQ","created_at":"2026-07-05T10:52:57Z"},{"alias_kind":"pith_short_8","alias_value":"P7OKCDDQ","created_at":"2026-07-05T10:52:57Z"}],"graph_snapshots":[{"event_id":"sha256:64f4c3498d8d6fd747cf92e0e274782eab7669cc5424416cb24d5ba75eed8ba5","target":"graph","created_at":"2026-07-05T10:52:57Z","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/2412.12864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data poses unique challenges due to its heterogeneous nature, combining both continuous and categorical variables. Existing approaches often struggle to effectively capture the underlying structure and relationships within such data. We propose GFTab (Geodesic Flow Kernels for Semi- Supervised Learning on Mixed-Variable Tabular Dataset), a semi-supervised framework specifically designed for tabular datasets. GFTab incorporates three key innovations: 1) Variable-specific corruption methods tailored to the distinct properties of continuous and categorical variables, 2) A Geodesic flow ke","authors_text":"Yongjae Lee, Yoontae Hwang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T12:47:53Z","title":"Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12864","kind":"arxiv","version":2},"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:f302dde325f3f6bccad9e8bf27a963105a2d3b71d759542d9947d2faed870199","target":"record","created_at":"2026-07-05T10:52:57Z","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":"ad0c1cef73bc95c27206ff73b9c52335ed64c304a36cdf18466298558ab4cbf9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T12:47:53Z","title_canon_sha256":"e1e98fab3a2b0fede1de04a599999648b116706be2e57d36603cf233de32f173"},"schema_version":"1.0","source":{"id":"2412.12864","kind":"arxiv","version":2}},"canonical_sha256":"7fdca10c70458aaac0100f8ab4b4a1e0a1bbe454bd9f3711141903bdb867634d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fdca10c70458aaac0100f8ab4b4a1e0a1bbe454bd9f3711141903bdb867634d","first_computed_at":"2026-07-05T10:52:57.341265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:57.341265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZghZOndPqfiiybuG+3Hl6ePTsCe2PCLtoKp4FirudSSudzK7aIrzjnzpo73Y39/z9ZbgEikGkhMpUU6HFNoMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:57.341791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12864","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f302dde325f3f6bccad9e8bf27a963105a2d3b71d759542d9947d2faed870199","sha256:64f4c3498d8d6fd747cf92e0e274782eab7669cc5424416cb24d5ba75eed8ba5"],"state_sha256":"421d3c4a3620041bf0acfdcafa54865bc9f30fc0ed5b744017ea137c4b6213f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRJDjKrDFon68wuddLmYut9sbItMFuo9S/vcouk1FMGZBLUo5JzTXO6XR3VhXQEO/Lz8m4A/U7Ib2b+46dp/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:47:05.019842Z","bundle_sha256":"d0c4b353f4e234b747b9267eacf194ec842e430921a466925ae846cfe27e0c88"}}