{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3LM34CZPAE2UZC3C3GKO5LY34I","short_pith_number":"pith:3LM34CZP","schema_version":"1.0","canonical_sha256":"dad9be0b2f01354c8b62d994eeaf1be2252f38413ac2feab6442cabc4b4cb373","source":{"kind":"arxiv","id":"1802.03162","version":2},"attestation_state":"computed","paper":{"title":"URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Doyen Sahoo, Hung Le, Quang Pham, Steven C.H. Hoi","submitted_at":"2018-02-09T08:07:13Z","abstract_excerpt":"Malicious URLs host unsolicited content and are used to perpetrate cybercrimes. It is imperative to detect them in a timely manner. Traditionally, this is done through the usage of blacklists, which cannot be exhaustive, and cannot detect newly generated malicious URLs. To address this, recent years have witnessed several efforts to perform Malicious URL Detection using Machine Learning. The most popular and scalable approaches use lexical properties of the URL string by extracting Bag-of-words like features, followed by applying machine learning models such as SVMs. There are also other featu"},"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":"1802.03162","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-02-09T08:07:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5ad966920609feb09db7b949f6f5cace527690264eea21a68bf7624171b6f86c","abstract_canon_sha256":"d9f20523947e0e305991073d7703b6be49a027886687e7cb23c967bf4b390050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:08.579981Z","signature_b64":"Ye9K2sPSqdNbkTFclpEcbrpMchQ8fBeQ/F6afvwqZQQOLPgRuWNLfdTtuee/oAZBEcAK8/PnZMK2okFm50f+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad9be0b2f01354c8b62d994eeaf1be2252f38413ac2feab6442cabc4b4cb373","last_reissued_at":"2026-05-18T00:22:08.579543Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:08.579543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Doyen Sahoo, Hung Le, Quang Pham, Steven C.H. Hoi","submitted_at":"2018-02-09T08:07:13Z","abstract_excerpt":"Malicious URLs host unsolicited content and are used to perpetrate cybercrimes. It is imperative to detect them in a timely manner. Traditionally, this is done through the usage of blacklists, which cannot be exhaustive, and cannot detect newly generated malicious URLs. To address this, recent years have witnessed several efforts to perform Malicious URL Detection using Machine Learning. The most popular and scalable approaches use lexical properties of the URL string by extracting Bag-of-words like features, followed by applying machine learning models such as SVMs. There are also other featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03162","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":""},"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":"1802.03162","created_at":"2026-05-18T00:22:08.579611+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03162v2","created_at":"2026-05-18T00:22:08.579611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03162","created_at":"2026-05-18T00:22:08.579611+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LM34CZPAE2U","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LM34CZPAE2UZC3C","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LM34CZP","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.21353","citing_title":"Beyond Classification Accuracy: An Exploration-Range Evaluation of Adaptive Crawling for Fake Shopping Sites","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27335","citing_title":"Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I","json":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I.json","graph_json":"https://pith.science/api/pith-number/3LM34CZPAE2UZC3C3GKO5LY34I/graph.json","events_json":"https://pith.science/api/pith-number/3LM34CZPAE2UZC3C3GKO5LY34I/events.json","paper":"https://pith.science/paper/3LM34CZP"},"agent_actions":{"view_html":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I","download_json":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I.json","view_paper":"https://pith.science/paper/3LM34CZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03162&json=true","fetch_graph":"https://pith.science/api/pith-number/3LM34CZPAE2UZC3C3GKO5LY34I/graph.json","fetch_events":"https://pith.science/api/pith-number/3LM34CZPAE2UZC3C3GKO5LY34I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I/action/storage_attestation","attest_author":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I/action/author_attestation","sign_citation":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I/action/citation_signature","submit_replication":"https://pith.science/pith/3LM34CZPAE2UZC3C3GKO5LY34I/action/replication_record"}},"created_at":"2026-05-18T00:22:08.579611+00:00","updated_at":"2026-05-18T00:22:08.579611+00:00"}