{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CXCJCE43SBLTRT5GQ6ISWQBAQB","short_pith_number":"pith:CXCJCE43","schema_version":"1.0","canonical_sha256":"15c491139b905738cfa687912b40208045731dd74731bc051ebf795a69422349","source":{"kind":"arxiv","id":"2009.09663","version":2},"attestation_state":"computed","paper":{"title":"DeepDyve: Dynamic Verification for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Luo, Min Li, Qiang Xu, Ye Tian, Yu Li","submitted_at":"2020-09-21T07:58:18Z","abstract_excerpt":"Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as adversarial example attacks and fault injection attacks. While there are many defense methods proposed against maliciously crafted inputs, solutions against faults presented in the DNN system itself (e.g., parameters and calculations) are far less explored. In this paper, we develop a novel lightweight fault-tolerant solution for DNN-based systems, namely DeepDyve, "},"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":"2009.09663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-21T07:58:18Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"c3b45ea1d9c695c6b8361b9066e56e071eff9371ae2f9cdbafbec0ded3c4fac1","abstract_canon_sha256":"5619643c0c11b24b168ea8a64d78ec9ecf5da16475c056fbd516100255853b26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:28.403016Z","signature_b64":"GL42NAEQUxnQ6hNGW3EUq4MkYjBdIm/Vmu3Zdl68rtEbBskFI/o/ME7ILImyvLSxBs6BbFOFebmqjfMLoFaZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c491139b905738cfa687912b40208045731dd74731bc051ebf795a69422349","last_reissued_at":"2026-07-05T01:43:28.402591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:28.402591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepDyve: Dynamic Verification for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Luo, Min Li, Qiang Xu, Ye Tian, Yu Li","submitted_at":"2020-09-21T07:58:18Z","abstract_excerpt":"Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as adversarial example attacks and fault injection attacks. While there are many defense methods proposed against maliciously crafted inputs, solutions against faults presented in the DNN system itself (e.g., parameters and calculations) are far less explored. In this paper, we develop a novel lightweight fault-tolerant solution for DNN-based systems, namely DeepDyve, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09663","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/2009.09663/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":"2009.09663","created_at":"2026-07-05T01:43:28.402649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.09663v2","created_at":"2026-07-05T01:43:28.402649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09663","created_at":"2026-07-05T01:43:28.402649+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXCJCE43SBLT","created_at":"2026-07-05T01:43:28.402649+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXCJCE43SBLTRT5G","created_at":"2026-07-05T01:43:28.402649+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXCJCE43","created_at":"2026-07-05T01:43:28.402649+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/CXCJCE43SBLTRT5GQ6ISWQBAQB","json":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB.json","graph_json":"https://pith.science/api/pith-number/CXCJCE43SBLTRT5GQ6ISWQBAQB/graph.json","events_json":"https://pith.science/api/pith-number/CXCJCE43SBLTRT5GQ6ISWQBAQB/events.json","paper":"https://pith.science/paper/CXCJCE43"},"agent_actions":{"view_html":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB","download_json":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB.json","view_paper":"https://pith.science/paper/CXCJCE43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.09663&json=true","fetch_graph":"https://pith.science/api/pith-number/CXCJCE43SBLTRT5GQ6ISWQBAQB/graph.json","fetch_events":"https://pith.science/api/pith-number/CXCJCE43SBLTRT5GQ6ISWQBAQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB/action/storage_attestation","attest_author":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB/action/author_attestation","sign_citation":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB/action/citation_signature","submit_replication":"https://pith.science/pith/CXCJCE43SBLTRT5GQ6ISWQBAQB/action/replication_record"}},"created_at":"2026-07-05T01:43:28.402649+00:00","updated_at":"2026-07-05T01:43:28.402649+00:00"}