{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WWAUV4JRYU4QEWDIIMDRL7BTMF","short_pith_number":"pith:WWAUV4JR","canonical_record":{"source":{"id":"1710.01011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-10-03T07:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"cb7389011e799b00ba096f54f4b9984df2b665daf479e39b29fbbc1e7e9323f0","abstract_canon_sha256":"511cf80f7ca8d78565272842637f5d191b70ed5b70e433708a87ed7146166598"},"schema_version":"1.0"},"canonical_sha256":"b5814af131c539025868430715fc33614e9e82970c6f58c7ec2eee76f1d7bb77","source":{"kind":"arxiv","id":"1710.01011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01011","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01011v1","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01011","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"pith_short_12","alias_value":"WWAUV4JRYU4Q","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WWAUV4JRYU4QEWDI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WWAUV4JR","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WWAUV4JRYU4QEWDIIMDRL7BTMF","target":"record","payload":{"canonical_record":{"source":{"id":"1710.01011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-10-03T07:18:42Z","cross_cats_sorted":[],"title_canon_sha256":"cb7389011e799b00ba096f54f4b9984df2b665daf479e39b29fbbc1e7e9323f0","abstract_canon_sha256":"511cf80f7ca8d78565272842637f5d191b70ed5b70e433708a87ed7146166598"},"schema_version":"1.0"},"canonical_sha256":"b5814af131c539025868430715fc33614e9e82970c6f58c7ec2eee76f1d7bb77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:45.518722Z","signature_b64":"UsdNLxpNMQ13lHfUlbXTgPr0tG0A/E90AFJZkBosNCfWu8QYx7U2Qri+718YiEm4+6wWCcOGKLvJfhDMfAsADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5814af131c539025868430715fc33614e9e82970c6f58c7ec2eee76f1d7bb77","last_reissued_at":"2026-05-18T00:33:45.518209Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:45.518209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.01011","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":"2026-05-18T00:33:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO601WijK6Pm4NDMdl7Xlo8Pydpa6OBlHUD8vpkjngplrSN3aksBgABP6dIbZ4kb4csvnQZpKsfTfg1cWo/ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:04:09.109760Z"},"content_sha256":"4580f765f70ac49b38d0273df0c8b00183127d9731f845ad9bcfa62092b00e13","schema_version":"1.0","event_id":"sha256:4580f765f70ac49b38d0273df0c8b00183127d9731f845ad9bcfa62092b00e13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WWAUV4JRYU4QEWDIIMDRL7BTMF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearest Neighbor Imputation for Categorical Data by Weighting of Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Gerhard Tutz, Shahla Faisal","submitted_at":"2017-10-03T07:18:42Z","abstract_excerpt":"Missing values are a common phenomenon in all areas of applied research. While various imputation methods are available for metrically scaled variables, methods for categorical data are scarce. An imputation method that has been shown to work well for high dimensional metrically scaled variables is the imputation by nearest neighbor methods. In this paper, we extend the weighted nearest neighbors approach to impute missing values in categorical variables. The proposed method, called $\\mathtt{wNNSel_{cat}}$, explicitly uses the information on association among attributes. The performance of dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01011","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":""},"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":"2026-05-18T00:33:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYqLWGoqpepl4yNFlLD8TB2Tp89CpPKT7Bxrbld8MigLb/0mNoqpF0HTyqOqS157zpCP8+72uw9Y3SujxtsNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:04:09.110492Z"},"content_sha256":"12669e7246b149f167209dd126e720e76121bbbda3c34432a1d572d3f6316eaf","schema_version":"1.0","event_id":"sha256:12669e7246b149f167209dd126e720e76121bbbda3c34432a1d572d3f6316eaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/bundle.json","state_url":"https://pith.science/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/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":"2026-06-05T19:04:09Z","links":{"resolver":"https://pith.science/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF","bundle":"https://pith.science/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/bundle.json","state":"https://pith.science/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWAUV4JRYU4QEWDIIMDRL7BTMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WWAUV4JRYU4QEWDIIMDRL7BTMF","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":"511cf80f7ca8d78565272842637f5d191b70ed5b70e433708a87ed7146166598","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-10-03T07:18:42Z","title_canon_sha256":"cb7389011e799b00ba096f54f4b9984df2b665daf479e39b29fbbc1e7e9323f0"},"schema_version":"1.0","source":{"id":"1710.01011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01011","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01011v1","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01011","created_at":"2026-05-18T00:33:45Z"},{"alias_kind":"pith_short_12","alias_value":"WWAUV4JRYU4Q","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WWAUV4JRYU4QEWDI","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WWAUV4JR","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:12669e7246b149f167209dd126e720e76121bbbda3c34432a1d572d3f6316eaf","target":"graph","created_at":"2026-05-18T00:33:45Z","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"},"paper":{"abstract_excerpt":"Missing values are a common phenomenon in all areas of applied research. While various imputation methods are available for metrically scaled variables, methods for categorical data are scarce. An imputation method that has been shown to work well for high dimensional metrically scaled variables is the imputation by nearest neighbor methods. In this paper, we extend the weighted nearest neighbors approach to impute missing values in categorical variables. The proposed method, called $\\mathtt{wNNSel_{cat}}$, explicitly uses the information on association among attributes. The performance of dif","authors_text":"Gerhard Tutz, Shahla Faisal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-10-03T07:18:42Z","title":"Nearest Neighbor Imputation for Categorical Data by Weighting of Attributes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01011","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":"sha256:4580f765f70ac49b38d0273df0c8b00183127d9731f845ad9bcfa62092b00e13","target":"record","created_at":"2026-05-18T00:33:45Z","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":"511cf80f7ca8d78565272842637f5d191b70ed5b70e433708a87ed7146166598","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-10-03T07:18:42Z","title_canon_sha256":"cb7389011e799b00ba096f54f4b9984df2b665daf479e39b29fbbc1e7e9323f0"},"schema_version":"1.0","source":{"id":"1710.01011","kind":"arxiv","version":1}},"canonical_sha256":"b5814af131c539025868430715fc33614e9e82970c6f58c7ec2eee76f1d7bb77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5814af131c539025868430715fc33614e9e82970c6f58c7ec2eee76f1d7bb77","first_computed_at":"2026-05-18T00:33:45.518209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:45.518209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UsdNLxpNMQ13lHfUlbXTgPr0tG0A/E90AFJZkBosNCfWu8QYx7U2Qri+718YiEm4+6wWCcOGKLvJfhDMfAsADQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:45.518722Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.01011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4580f765f70ac49b38d0273df0c8b00183127d9731f845ad9bcfa62092b00e13","sha256:12669e7246b149f167209dd126e720e76121bbbda3c34432a1d572d3f6316eaf"],"state_sha256":"b4063009822b0ddde694f51eee51706fba5670dd8ca02121cbced581c82cf9a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/BYGer86X6g0vs+iYgf+72QdTYFooGUz8z22V8Rc78pbVpAyp3zWV0XWJ28tIVSyVwiwk6rIbhQ1pEBdMpJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T19:04:09.113881Z","bundle_sha256":"2329cabaacccd72570cac7edd80807beda92819757522ee126dd6264ff9f7ec6"}}