{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZGHVRE32A4MU52YELWFQPPAIMF","short_pith_number":"pith:ZGHVRE32","canonical_record":{"source":{"id":"2007.07052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2020-07-14T14:24:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"808eea30ba93a4a31aa618f4ad4dfae1b9010f2682dffde0f7b923684bf7bacc","abstract_canon_sha256":"44eadc5a5082c313b299e542a511613331995cb561dad43138d3e96560c700a4"},"schema_version":"1.0"},"canonical_sha256":"c98f58937a07194eeb045d8b07bc08616298541d055608f0522b1512e16a3ca6","source":{"kind":"arxiv","id":"2007.07052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07052","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07052v1","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07052","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZGHVRE32A4MU","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZGHVRE32A4MU52YE","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZGHVRE32","created_at":"2026-07-05T01:18:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZGHVRE32A4MU52YELWFQPPAIMF","target":"record","payload":{"canonical_record":{"source":{"id":"2007.07052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2020-07-14T14:24:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"808eea30ba93a4a31aa618f4ad4dfae1b9010f2682dffde0f7b923684bf7bacc","abstract_canon_sha256":"44eadc5a5082c313b299e542a511613331995cb561dad43138d3e96560c700a4"},"schema_version":"1.0"},"canonical_sha256":"c98f58937a07194eeb045d8b07bc08616298541d055608f0522b1512e16a3ca6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:26.374375Z","signature_b64":"EwBYtX/6PMHogRbiUVUZvEL5wHfChNOx/b4EUlzqjO0reN9GYN4glUQJ/OAiJusOS6Fo/NsfuJimNs1ZCTOEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98f58937a07194eeb045d8b07bc08616298541d055608f0522b1512e16a3ca6","last_reissued_at":"2026-07-05T01:18:26.373943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:26.373943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.07052","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":"2026-07-05T01:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CDJs79NpFygaKRfCG9A26Du6Wlzoe+5hBef+Wese+YjIWSpLTzEjqbk2pC1KRElLtWLHFgBdXC8EI0LZzBkXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:23:51.192217Z"},"content_sha256":"00dbdc464dce8d4c96fa39ede6f5e7208d112448da4453c57e92bdec7ea907bb","schema_version":"1.0","event_id":"sha256:00dbdc464dce8d4c96fa39ede6f5e7208d112448da4453c57e92bdec7ea907bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZGHVRE32A4MU52YELWFQPPAIMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predicting feature imputability in the absence of ground truth","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"David P. Finn, Girijesh Prasad, KongFatt Wong-Lin, Niamh McCombe, Paula L. McClean, Stephen Todd, Xuemei Ding","submitted_at":"2020-07-14T14:24:07Z","abstract_excerpt":"Data imputation is the most popular method of dealing with missing values, but in most real life applications, large missing data can occur and it is difficult or impossible to evaluate whether data has been imputed accurately (lack of ground truth). This paper addresses these issues by proposing an effective and simple principal component based method for determining whether individual data features can be accurately imputed - feature imputability. In particular, we establish a strong linear relationship between principal component loadings and feature imputability, even in the presence of ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07052","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/2007.07052/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":"2026-07-05T01:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"guEdOFx7jAPjVIuOkEfa2gXJLTudaEmMZ/nqGrrEJ9j4Nw0J1i+/8F8wfHORHzaLqHpDDaPj/m1RQA2Vh3OkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:23:51.192719Z"},"content_sha256":"732866542f5c52dec1105409b87c453f8dcbd5ce4391528949a347a496353929","schema_version":"1.0","event_id":"sha256:732866542f5c52dec1105409b87c453f8dcbd5ce4391528949a347a496353929"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGHVRE32A4MU52YELWFQPPAIMF/bundle.json","state_url":"https://pith.science/pith/ZGHVRE32A4MU52YELWFQPPAIMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGHVRE32A4MU52YELWFQPPAIMF/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":"2026-08-04T02:23:51Z","links":{"resolver":"https://pith.science/pith/ZGHVRE32A4MU52YELWFQPPAIMF","bundle":"https://pith.science/pith/ZGHVRE32A4MU52YELWFQPPAIMF/bundle.json","state":"https://pith.science/pith/ZGHVRE32A4MU52YELWFQPPAIMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGHVRE32A4MU52YELWFQPPAIMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZGHVRE32A4MU52YELWFQPPAIMF","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":"44eadc5a5082c313b299e542a511613331995cb561dad43138d3e96560c700a4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2020-07-14T14:24:07Z","title_canon_sha256":"808eea30ba93a4a31aa618f4ad4dfae1b9010f2682dffde0f7b923684bf7bacc"},"schema_version":"1.0","source":{"id":"2007.07052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07052","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07052v1","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07052","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZGHVRE32A4MU","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZGHVRE32A4MU52YE","created_at":"2026-07-05T01:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZGHVRE32","created_at":"2026-07-05T01:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:732866542f5c52dec1105409b87c453f8dcbd5ce4391528949a347a496353929","target":"graph","created_at":"2026-07-05T01:18:26Z","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/2007.07052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data imputation is the most popular method of dealing with missing values, but in most real life applications, large missing data can occur and it is difficult or impossible to evaluate whether data has been imputed accurately (lack of ground truth). This paper addresses these issues by proposing an effective and simple principal component based method for determining whether individual data features can be accurately imputed - feature imputability. In particular, we establish a strong linear relationship between principal component loadings and feature imputability, even in the presence of ex","authors_text":"David P. Finn, Girijesh Prasad, KongFatt Wong-Lin, Niamh McCombe, Paula L. McClean, Stephen Todd, Xuemei Ding","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2020-07-14T14:24:07Z","title":"Predicting feature imputability in the absence of ground truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07052","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":"sha256:00dbdc464dce8d4c96fa39ede6f5e7208d112448da4453c57e92bdec7ea907bb","target":"record","created_at":"2026-07-05T01:18:26Z","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":"44eadc5a5082c313b299e542a511613331995cb561dad43138d3e96560c700a4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2020-07-14T14:24:07Z","title_canon_sha256":"808eea30ba93a4a31aa618f4ad4dfae1b9010f2682dffde0f7b923684bf7bacc"},"schema_version":"1.0","source":{"id":"2007.07052","kind":"arxiv","version":1}},"canonical_sha256":"c98f58937a07194eeb045d8b07bc08616298541d055608f0522b1512e16a3ca6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c98f58937a07194eeb045d8b07bc08616298541d055608f0522b1512e16a3ca6","first_computed_at":"2026-07-05T01:18:26.373943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:26.373943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EwBYtX/6PMHogRbiUVUZvEL5wHfChNOx/b4EUlzqjO0reN9GYN4glUQJ/OAiJusOS6Fo/NsfuJimNs1ZCTOEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:26.374375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.07052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00dbdc464dce8d4c96fa39ede6f5e7208d112448da4453c57e92bdec7ea907bb","sha256:732866542f5c52dec1105409b87c453f8dcbd5ce4391528949a347a496353929"],"state_sha256":"9dd55caea10115b8eaf71f13e9fdd0db7e035ef5b17fc547c8ee0e911febb9d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dssZ0C2skxO/oxaFG7DWabasa1gpmmvRKkC6zXZiQA3jWXWU5kF1V85pZ6l1U38siAFMxtyV19sXTfwl1qHfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:23:51.196689Z","bundle_sha256":"a776eb7e74fe8edbb4dafeb1c6e016c86cd10f19acb9e6e1948f9e87d3cca2d5"}}