{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O556WQOWLB7GBCUOJPCEIH4E6X","short_pith_number":"pith:O556WQOW","canonical_record":{"source":{"id":"2501.13786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T16:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"9bfcba99b1c1e53e06d7bdb5c4532b1d5b26805229f350e9fde82db105ff9ef4","abstract_canon_sha256":"7be737dd937c89c4611a84601f86c08868b1b5a51c278a994c259c05de807e00"},"schema_version":"1.0"},"canonical_sha256":"777beb41d6587e608a8e4bc4441f84f5eb46684a7f6e6a33b646f2807b7ba6a5","source":{"kind":"arxiv","id":"2501.13786","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13786","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13786v2","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13786","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"O556WQOWLB7G","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"O556WQOWLB7GBCUO","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"O556WQOW","created_at":"2026-07-05T11:03:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O556WQOWLB7GBCUOJPCEIH4E6X","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T16:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"9bfcba99b1c1e53e06d7bdb5c4532b1d5b26805229f350e9fde82db105ff9ef4","abstract_canon_sha256":"7be737dd937c89c4611a84601f86c08868b1b5a51c278a994c259c05de807e00"},"schema_version":"1.0"},"canonical_sha256":"777beb41d6587e608a8e4bc4441f84f5eb46684a7f6e6a33b646f2807b7ba6a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:02.912760Z","signature_b64":"Zu2L0Oc3D4HupLpmzT0eZN5aRySSun9KrsrSYdIr/uS5chcJOqW5JrM0ynDy6hkvDcTgmPbn1a7N7TRZ93iqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"777beb41d6587e608a8e4bc4441f84f5eb46684a7f6e6a33b646f2807b7ba6a5","last_reissued_at":"2026-07-05T11:03:02.912288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:02.912288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13786","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":"2026-07-05T11:03:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iYNDPrtG3H4LV7njOe7pL+CF1JVZfc/1g4oQ5T5rYAQCwcAtYDdNDOAUksYg5AbrWrx+sqYouSK4LPVtVj0cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:41.937510Z"},"content_sha256":"ee62ea48fdc56a14d48a66354473c21eb48b6bdb1a72bc86011a022faaccda80","schema_version":"1.0","event_id":"sha256:ee62ea48fdc56a14d48a66354473c21eb48b6bdb1a72bc86011a022faaccda80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O556WQOWLB7GBCUOJPCEIH4E6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Handling Missing Data in Downstream Tasks With Distribution-Preserving Guarantees","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cl\\'emence R\\'eda, Olaf Wolkenhauer, Rahul Bordoloi, Saptarshi Bej","submitted_at":"2025-01-23T16:04:18Z","abstract_excerpt":"Missing feature values are a significant hurdle for downstream machine-learning tasks such as classification. However, imputation methods for classification might be time-consuming for high-dimensional data, and offer few theoretical guarantees on the preservation of the data distribution and imputation quality, especially for not-missing-at-random mechanisms. First, we propose an imputation approach named F3I based on the iterative improvement of a K-nearest neighbor imputation, where neighbor-specific weights are learned through the optimization of a novel concave, differentiable objective f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13786","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/2501.13786/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":"2026-07-05T11:03:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIrv0+M8zjt2sc5sLPJ7EIItqrbR4DzalYdkGCBGLucCGVhQaa1IeMnD5ngLa8ypAEwf+iPPWNSYhG6/EQUxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:29:41.937836Z"},"content_sha256":"5bb9c8968ab39a08c836980e393c0122df7c0fc097c6c70707c665a925b7f8c0","schema_version":"1.0","event_id":"sha256:5bb9c8968ab39a08c836980e393c0122df7c0fc097c6c70707c665a925b7f8c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O556WQOWLB7GBCUOJPCEIH4E6X/bundle.json","state_url":"https://pith.science/pith/O556WQOWLB7GBCUOJPCEIH4E6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O556WQOWLB7GBCUOJPCEIH4E6X/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":"2026-08-14T10:29:41Z","links":{"resolver":"https://pith.science/pith/O556WQOWLB7GBCUOJPCEIH4E6X","bundle":"https://pith.science/pith/O556WQOWLB7GBCUOJPCEIH4E6X/bundle.json","state":"https://pith.science/pith/O556WQOWLB7GBCUOJPCEIH4E6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O556WQOWLB7GBCUOJPCEIH4E6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O556WQOWLB7GBCUOJPCEIH4E6X","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":"7be737dd937c89c4611a84601f86c08868b1b5a51c278a994c259c05de807e00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T16:04:18Z","title_canon_sha256":"9bfcba99b1c1e53e06d7bdb5c4532b1d5b26805229f350e9fde82db105ff9ef4"},"schema_version":"1.0","source":{"id":"2501.13786","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13786","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13786v2","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13786","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"O556WQOWLB7G","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"O556WQOWLB7GBCUO","created_at":"2026-07-05T11:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"O556WQOW","created_at":"2026-07-05T11:03:02Z"}],"graph_snapshots":[{"event_id":"sha256:5bb9c8968ab39a08c836980e393c0122df7c0fc097c6c70707c665a925b7f8c0","target":"graph","created_at":"2026-07-05T11:03:02Z","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/2501.13786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Missing feature values are a significant hurdle for downstream machine-learning tasks such as classification. However, imputation methods for classification might be time-consuming for high-dimensional data, and offer few theoretical guarantees on the preservation of the data distribution and imputation quality, especially for not-missing-at-random mechanisms. First, we propose an imputation approach named F3I based on the iterative improvement of a K-nearest neighbor imputation, where neighbor-specific weights are learned through the optimization of a novel concave, differentiable objective f","authors_text":"Cl\\'emence R\\'eda, Olaf Wolkenhauer, Rahul Bordoloi, Saptarshi Bej","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T16:04:18Z","title":"Handling Missing Data in Downstream Tasks With Distribution-Preserving Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13786","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:ee62ea48fdc56a14d48a66354473c21eb48b6bdb1a72bc86011a022faaccda80","target":"record","created_at":"2026-07-05T11:03:02Z","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":"7be737dd937c89c4611a84601f86c08868b1b5a51c278a994c259c05de807e00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T16:04:18Z","title_canon_sha256":"9bfcba99b1c1e53e06d7bdb5c4532b1d5b26805229f350e9fde82db105ff9ef4"},"schema_version":"1.0","source":{"id":"2501.13786","kind":"arxiv","version":2}},"canonical_sha256":"777beb41d6587e608a8e4bc4441f84f5eb46684a7f6e6a33b646f2807b7ba6a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"777beb41d6587e608a8e4bc4441f84f5eb46684a7f6e6a33b646f2807b7ba6a5","first_computed_at":"2026-07-05T11:03:02.912288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:02.912288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zu2L0Oc3D4HupLpmzT0eZN5aRySSun9KrsrSYdIr/uS5chcJOqW5JrM0ynDy6hkvDcTgmPbn1a7N7TRZ93iqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:02.912760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13786","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee62ea48fdc56a14d48a66354473c21eb48b6bdb1a72bc86011a022faaccda80","sha256:5bb9c8968ab39a08c836980e393c0122df7c0fc097c6c70707c665a925b7f8c0"],"state_sha256":"990d9b19045c26b3269a03bbb98205bbb0dbceb86f33253dee6a77779b028e20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MLMfCDg8acCdHZxBAsHYhAmTm0MWwWKo/kPApC14AYBR2PFZukhe5MkBYtjm9EE5fwVpChsc2NX3bhgsTETVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:29:41.941244Z","bundle_sha256":"9a97cf099ffa7065109ce74e24bb8bd29341e958a30f20b0eb91928b99628d20"}}