{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26UMDBF2GKDCF5CQ3BOCRJ6DIF","short_pith_number":"pith:26UMDBF2","schema_version":"1.0","canonical_sha256":"d7a8c184ba328622f450d85c28a7c34141db53fbe54f4d3e2e3a5f36f3b96329","source":{"kind":"arxiv","id":"2401.14412","version":1},"attestation_state":"computed","paper":{"title":"Harnessing Neuron Stability to Improve DNN Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dong Xu, Hai Duong, Matthew B. Dwyer, ThanhVu Nguyen","submitted_at":"2024-01-19T23:48:04Z","abstract_excerpt":"Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing effective and scalable DNN verification techniques and tools. In this paper, we present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. VeriStable leverages the insight that while neuron behavior may be non-linear across the entire DNN input space, at intermediate states computed during verification many neurons m"},"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":"2401.14412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-19T23:48:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73d87bc229272d0a4ec1b6e23d508782829352bc783fbcdc29dedcbc0722a8f2","abstract_canon_sha256":"526f28d224d3d6542171fa691a152fab10f3a58b36ac454de922833d191a319b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:55.999109Z","signature_b64":"JBWmVfcF3nTR1VZY6DVveI6dXMT9DZgjPONAR3sKKXV5zcl6thstrS6Q5JP/xqY4xg61qOVw04reH3NfNdGmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a8c184ba328622f450d85c28a7c34141db53fbe54f4d3e2e3a5f36f3b96329","last_reissued_at":"2026-07-05T07:37:55.998743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:55.998743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Neuron Stability to Improve DNN Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dong Xu, Hai Duong, Matthew B. Dwyer, ThanhVu Nguyen","submitted_at":"2024-01-19T23:48:04Z","abstract_excerpt":"Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing effective and scalable DNN verification techniques and tools. In this paper, we present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. VeriStable leverages the insight that while neuron behavior may be non-linear across the entire DNN input space, at intermediate states computed during verification many neurons m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14412","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.14412/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":"2401.14412","created_at":"2026-07-05T07:37:55.998807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14412v1","created_at":"2026-07-05T07:37:55.998807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14412","created_at":"2026-07-05T07:37:55.998807+00:00"},{"alias_kind":"pith_short_12","alias_value":"26UMDBF2GKDC","created_at":"2026-07-05T07:37:55.998807+00:00"},{"alias_kind":"pith_short_16","alias_value":"26UMDBF2GKDCF5CQ","created_at":"2026-07-05T07:37:55.998807+00:00"},{"alias_kind":"pith_short_8","alias_value":"26UMDBF2","created_at":"2026-07-05T07:37:55.998807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02074","citing_title":"Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF","json":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF.json","graph_json":"https://pith.science/api/pith-number/26UMDBF2GKDCF5CQ3BOCRJ6DIF/graph.json","events_json":"https://pith.science/api/pith-number/26UMDBF2GKDCF5CQ3BOCRJ6DIF/events.json","paper":"https://pith.science/paper/26UMDBF2"},"agent_actions":{"view_html":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF","download_json":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF.json","view_paper":"https://pith.science/paper/26UMDBF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14412&json=true","fetch_graph":"https://pith.science/api/pith-number/26UMDBF2GKDCF5CQ3BOCRJ6DIF/graph.json","fetch_events":"https://pith.science/api/pith-number/26UMDBF2GKDCF5CQ3BOCRJ6DIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF/action/storage_attestation","attest_author":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF/action/author_attestation","sign_citation":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF/action/citation_signature","submit_replication":"https://pith.science/pith/26UMDBF2GKDCF5CQ3BOCRJ6DIF/action/replication_record"}},"created_at":"2026-07-05T07:37:55.998807+00:00","updated_at":"2026-07-05T07:37:55.998807+00:00"}