{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z5QK7DQ3OJN3IOGZNFNYYAJ24Y","short_pith_number":"pith:Z5QK7DQ3","canonical_record":{"source":{"id":"2206.08478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T22:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"ff061624a05a038a11d2b18e48c5e9a1b0f630e8f46f23a3363b96840677fd37","abstract_canon_sha256":"942f253d94a95ff0661ebafae0d4a9e63a7c243e6fe7b3521802e45bd95f3a8b"},"schema_version":"1.0"},"canonical_sha256":"cf60af8e1b725bb438d9695b8c013ae617f96f55fd8c2a03691ae84c7800f967","source":{"kind":"arxiv","id":"2206.08478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08478","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08478v1","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08478","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"Z5QK7DQ3OJN3","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"Z5QK7DQ3OJN3IOGZ","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"Z5QK7DQ3","created_at":"2026-07-05T07:25:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z5QK7DQ3OJN3IOGZNFNYYAJ24Y","target":"record","payload":{"canonical_record":{"source":{"id":"2206.08478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T22:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"ff061624a05a038a11d2b18e48c5e9a1b0f630e8f46f23a3363b96840677fd37","abstract_canon_sha256":"942f253d94a95ff0661ebafae0d4a9e63a7c243e6fe7b3521802e45bd95f3a8b"},"schema_version":"1.0"},"canonical_sha256":"cf60af8e1b725bb438d9695b8c013ae617f96f55fd8c2a03691ae84c7800f967","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:37.437101Z","signature_b64":"Sws2T61DeeWflqdAjWf9NW1Iftb3BMGg75OgUR/Qu8adAsNh528AxBgBAysvqJg7hbmDkvZcrSb52nO6zr5eBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf60af8e1b725bb438d9695b8c013ae617f96f55fd8c2a03691ae84c7800f967","last_reissued_at":"2026-07-05T07:25:37.436644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:37.436644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.08478","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ljzdOH7Z32vpK6WemWfWowzCOQ5UGw4MxMDJjN0Jp2bVbuA3Ups8+D+FDfFg8MM33dY1bRRNWBGCojJbv0BCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:27:49.107777Z"},"content_sha256":"c7dd495b6cf11884232739a4f395d5d7efc22afbf75063176e01407f50a205ae","schema_version":"1.0","event_id":"sha256:c7dd495b6cf11884232739a4f395d5d7efc22afbf75063176e01407f50a205ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z5QK7DQ3OJN3IOGZNFNYYAJ24Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Classification of datasets with imputed missing values: does imputation quality matter?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"AIX-COVNET Collaboration, Antti Rannikko, Carola-Bibiane Sch\\\"onlieb, Evis Sala, James H.F. Rudd, Jan Stanczuk, Jing Tang, John A.D. Aston, Julian Gilbey, Matthew Thorpe, Michael Roberts, Mishal Patel, Philip Teare, Pietro Lio, Ramon Vinas Torne, S\\\"oren Dittmer, Tolou Shadbahr, Tuomas Mirtti","submitted_at":"2022-06-16T22:58:03Z","abstract_excerpt":"Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missing values are typically imputed using established methods, followed by classification of the now complete, imputed, samples. The focus of the machine learning researcher is then to optimise the downstream classification performance. In this study, we highlight that it is imperative to consider the quality of the imputation. We demonstrate how the commonly used measures for assessing quality are flawed and propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08478","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.08478/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":"2026-07-05T07:25:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5io3lLuuD7FKH6XfWaoWadZS6ZGuPEDbOmCnS1vnuNVh+AQn2iWXpL9JMTVRh83nXWSNSfM1kXO5rXrRwE7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:27:49.108385Z"},"content_sha256":"0c08c21fc0902a3c43180989715c9e92331463645a20ecbc429c654c331aae74","schema_version":"1.0","event_id":"sha256:0c08c21fc0902a3c43180989715c9e92331463645a20ecbc429c654c331aae74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/bundle.json","state_url":"https://pith.science/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/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":"2026-08-05T03:27:49Z","links":{"resolver":"https://pith.science/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y","bundle":"https://pith.science/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/bundle.json","state":"https://pith.science/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5QK7DQ3OJN3IOGZNFNYYAJ24Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z5QK7DQ3OJN3IOGZNFNYYAJ24Y","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":"942f253d94a95ff0661ebafae0d4a9e63a7c243e6fe7b3521802e45bd95f3a8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T22:58:03Z","title_canon_sha256":"ff061624a05a038a11d2b18e48c5e9a1b0f630e8f46f23a3363b96840677fd37"},"schema_version":"1.0","source":{"id":"2206.08478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08478","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08478v1","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08478","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_12","alias_value":"Z5QK7DQ3OJN3","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_16","alias_value":"Z5QK7DQ3OJN3IOGZ","created_at":"2026-07-05T07:25:37Z"},{"alias_kind":"pith_short_8","alias_value":"Z5QK7DQ3","created_at":"2026-07-05T07:25:37Z"}],"graph_snapshots":[{"event_id":"sha256:0c08c21fc0902a3c43180989715c9e92331463645a20ecbc429c654c331aae74","target":"graph","created_at":"2026-07-05T07:25:37Z","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/2206.08478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classifying samples in incomplete datasets is a common aim for machine learning practitioners, but is non-trivial. Missing data is found in most real-world datasets and these missing values are typically imputed using established methods, followed by classification of the now complete, imputed, samples. The focus of the machine learning researcher is then to optimise the downstream classification performance. In this study, we highlight that it is imperative to consider the quality of the imputation. We demonstrate how the commonly used measures for assessing quality are flawed and propose a n","authors_text":"AIX-COVNET Collaboration, Antti Rannikko, Carola-Bibiane Sch\\\"onlieb, Evis Sala, James H.F. Rudd, Jan Stanczuk, Jing Tang, John A.D. Aston, Julian Gilbey, Matthew Thorpe, Michael Roberts, Mishal Patel, Philip Teare, Pietro Lio, Ramon Vinas Torne, S\\\"oren Dittmer, Tolou Shadbahr, Tuomas Mirtti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T22:58:03Z","title":"Classification of datasets with imputed missing values: does imputation quality matter?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08478","kind":"arxiv","version":1},"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:c7dd495b6cf11884232739a4f395d5d7efc22afbf75063176e01407f50a205ae","target":"record","created_at":"2026-07-05T07:25:37Z","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":"942f253d94a95ff0661ebafae0d4a9e63a7c243e6fe7b3521802e45bd95f3a8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T22:58:03Z","title_canon_sha256":"ff061624a05a038a11d2b18e48c5e9a1b0f630e8f46f23a3363b96840677fd37"},"schema_version":"1.0","source":{"id":"2206.08478","kind":"arxiv","version":1}},"canonical_sha256":"cf60af8e1b725bb438d9695b8c013ae617f96f55fd8c2a03691ae84c7800f967","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf60af8e1b725bb438d9695b8c013ae617f96f55fd8c2a03691ae84c7800f967","first_computed_at":"2026-07-05T07:25:37.436644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:37.436644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sws2T61DeeWflqdAjWf9NW1Iftb3BMGg75OgUR/Qu8adAsNh528AxBgBAysvqJg7hbmDkvZcrSb52nO6zr5eBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:37.437101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7dd495b6cf11884232739a4f395d5d7efc22afbf75063176e01407f50a205ae","sha256:0c08c21fc0902a3c43180989715c9e92331463645a20ecbc429c654c331aae74"],"state_sha256":"6b8d16758c7d7c0394c23885ca53e09bc8a694df7d4a0802482653fcce379a7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5M+PPiHzokSa/llTFdNYh/BGpaEwXzXO6+Lvjj3mzPz0ppAxL5plzb6vClkEf+e70lNFPZcsHwGmOoWo4AqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:27:49.113370Z","bundle_sha256":"20e31cb42ffc352f4c57b38db60f0b7a49cd1fe4e11437861519dbc8197b589d"}}