{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2MFEB3LPLWLA5X5DWCBPS267OO","short_pith_number":"pith:2MFEB3LP","schema_version":"1.0","canonical_sha256":"d30a40ed6f5d960edfa3b082f96bdf7394870638f601baffce5a79b0a1d6d8e5","source":{"kind":"arxiv","id":"1802.03699","version":1},"attestation_state":"computed","paper":{"title":"PCA-Based Missing Information Imputation for Real-Time Crash Likelihood Prediction Under Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hai Yang, Jintao Ke, Shuaichao Zhang, Xiqun Chen","submitted_at":"2018-02-11T06:21:47Z","abstract_excerpt":"The real-time crash likelihood prediction has been an important research topic. Various classifiers, such as support vector machine (SVM) and tree-based boosting algorithms, have been proposed in traffic safety studies. However, few research focuses on the missing data imputation in real-time crash likelihood prediction, although missing values are commonly observed due to breakdown of sensors or external interference. Besides, classifying imbalanced data is also a difficult problem in real-time crash likelihood prediction, since it is hard to distinguish crash-prone cases from non-crash cases"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.03699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-11T06:21:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7267a96eded81a563285f9ef7267ae522a4cecc44028542d215a15c85e260c20","abstract_canon_sha256":"b443b88eebf2184cd690e978901a80ce9a89acfea90b5e7dcfdc2517e84d5027"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:50.735768Z","signature_b64":"zUNSB4Buah/Zm664sytKYqVxt2HgsdxKUlqUKLxazX1lKfXluXvUsexY3QCLG0v4Z6wspVI8GJ9gNd1YM3LEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d30a40ed6f5d960edfa3b082f96bdf7394870638f601baffce5a79b0a1d6d8e5","last_reissued_at":"2026-05-18T00:23:50.735283Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:50.735283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PCA-Based Missing Information Imputation for Real-Time Crash Likelihood Prediction Under Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hai Yang, Jintao Ke, Shuaichao Zhang, Xiqun Chen","submitted_at":"2018-02-11T06:21:47Z","abstract_excerpt":"The real-time crash likelihood prediction has been an important research topic. Various classifiers, such as support vector machine (SVM) and tree-based boosting algorithms, have been proposed in traffic safety studies. However, few research focuses on the missing data imputation in real-time crash likelihood prediction, although missing values are commonly observed due to breakdown of sensors or external interference. Besides, classifying imbalanced data is also a difficult problem in real-time crash likelihood prediction, since it is hard to distinguish crash-prone cases from non-crash cases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03699","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.03699","created_at":"2026-05-18T00:23:50.735367+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03699v1","created_at":"2026-05-18T00:23:50.735367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03699","created_at":"2026-05-18T00:23:50.735367+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MFEB3LPLWLA","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MFEB3LPLWLA5X5D","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MFEB3LP","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO","json":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO.json","graph_json":"https://pith.science/api/pith-number/2MFEB3LPLWLA5X5DWCBPS267OO/graph.json","events_json":"https://pith.science/api/pith-number/2MFEB3LPLWLA5X5DWCBPS267OO/events.json","paper":"https://pith.science/paper/2MFEB3LP"},"agent_actions":{"view_html":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO","download_json":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO.json","view_paper":"https://pith.science/paper/2MFEB3LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03699&json=true","fetch_graph":"https://pith.science/api/pith-number/2MFEB3LPLWLA5X5DWCBPS267OO/graph.json","fetch_events":"https://pith.science/api/pith-number/2MFEB3LPLWLA5X5DWCBPS267OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO/action/storage_attestation","attest_author":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO/action/author_attestation","sign_citation":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO/action/citation_signature","submit_replication":"https://pith.science/pith/2MFEB3LPLWLA5X5DWCBPS267OO/action/replication_record"}},"created_at":"2026-05-18T00:23:50.735367+00:00","updated_at":"2026-05-18T00:23:50.735367+00:00"}