{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DHPH3K4YK3XUJG6RQF7HHEDWB6","short_pith_number":"pith:DHPH3K4Y","schema_version":"1.0","canonical_sha256":"19de7dab9856ef449bd1817e7390760fb33684387c54155513aaf4bf5d91a334","source":{"kind":"arxiv","id":"2404.05964","version":2},"attestation_state":"computed","paper":{"title":"Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far Have We Gone?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Carsten Rudolph, Marthie Grobler, Surya Nepal, Tingmin Wu, Van Nguyen, Xingliang Yuan","submitted_at":"2024-04-09T02:52:55Z","abstract_excerpt":"Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In practice, although AI-based methods have been achieving promising performances in SVD and other domain applications (e.g., computer vision), they are well-known to fail in detecting the ground-truth label of input data (referred to as out-of-distribution, OOD, data) lying far away from the training data distribution (i.e., in-distribution, ID). This drawback leads t"},"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":"2404.05964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-04-09T02:52:55Z","cross_cats_sorted":[],"title_canon_sha256":"55dbabb825ae7e3be764b56129fcba2e138e395b3c93b8831ef949d5130f8a6a","abstract_canon_sha256":"076f3c5b2e10ff01ec295bca88b42fc286e4c2202b744b8fee29ca8a2f43c602"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:03.977515Z","signature_b64":"WHLhC8mx3xsGo7zQX+2sKM0d2mb2FTb3FaqUYu1tdqlLV1RIK+fwkdOERTQo12he23MG3bXHqyvcXx8w3XULAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19de7dab9856ef449bd1817e7390760fb33684387c54155513aaf4bf5d91a334","last_reissued_at":"2026-07-05T08:08:03.977091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:03.977091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far Have We Gone?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Carsten Rudolph, Marthie Grobler, Surya Nepal, Tingmin Wu, Van Nguyen, Xingliang Yuan","submitted_at":"2024-04-09T02:52:55Z","abstract_excerpt":"Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In practice, although AI-based methods have been achieving promising performances in SVD and other domain applications (e.g., computer vision), they are well-known to fail in detecting the ground-truth label of input data (referred to as out-of-distribution, OOD, data) lying far away from the training data distribution (i.e., in-distribution, ID). This drawback leads t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05964","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.05964/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.05964","created_at":"2026-07-05T08:08:03.977156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05964v2","created_at":"2026-07-05T08:08:03.977156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05964","created_at":"2026-07-05T08:08:03.977156+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHPH3K4YK3XU","created_at":"2026-07-05T08:08:03.977156+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHPH3K4YK3XUJG6R","created_at":"2026-07-05T08:08:03.977156+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHPH3K4Y","created_at":"2026-07-05T08:08:03.977156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04215","citing_title":"A Unified Model for Cross-Domain Clone Detection via Model Merging","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6","json":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6.json","graph_json":"https://pith.science/api/pith-number/DHPH3K4YK3XUJG6RQF7HHEDWB6/graph.json","events_json":"https://pith.science/api/pith-number/DHPH3K4YK3XUJG6RQF7HHEDWB6/events.json","paper":"https://pith.science/paper/DHPH3K4Y"},"agent_actions":{"view_html":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6","download_json":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6.json","view_paper":"https://pith.science/paper/DHPH3K4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05964&json=true","fetch_graph":"https://pith.science/api/pith-number/DHPH3K4YK3XUJG6RQF7HHEDWB6/graph.json","fetch_events":"https://pith.science/api/pith-number/DHPH3K4YK3XUJG6RQF7HHEDWB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6/action/storage_attestation","attest_author":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6/action/author_attestation","sign_citation":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6/action/citation_signature","submit_replication":"https://pith.science/pith/DHPH3K4YK3XUJG6RQF7HHEDWB6/action/replication_record"}},"created_at":"2026-07-05T08:08:03.977156+00:00","updated_at":"2026-07-05T08:08:03.977156+00:00"}