{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XLATSVGWGRIYBB4YPJBRQKU3VT","short_pith_number":"pith:XLATSVGW","schema_version":"1.0","canonical_sha256":"bac13954d634518087987a43182a9bace0f5798580dcd5fc94668bffec7976dc","source":{"kind":"arxiv","id":"2304.00813","version":1},"attestation_state":"computed","paper":{"title":"Model-Agnostic Reachability Analysis on Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Fu Wang, Geyong Min, Peipei Xu, Wenjie Ruan, Xiaowei Huang","submitted_at":"2023-04-03T09:01:59Z","abstract_excerpt":"Verification plays an essential role in the formal analysis of safety-critical systems. Most current verification methods have specific requirements when working on Deep Neural Networks (DNNs). They either target one particular network category, e.g., Feedforward Neural Networks (FNNs), or networks with specific activation functions, e.g., RdLU. In this paper, we develop a model-agnostic verification framework, called DeepAgn, and show that it can be applied to FNNs, Recurrent Neural Networks (RNNs), or a mixture of both. Under the assumption of Lipschitz continuity, DeepAgn analyses the reach"},"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":"2304.00813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-03T09:01:59Z","cross_cats_sorted":[],"title_canon_sha256":"14cdf68c905607bfdb33fbb140a2f4e2c36c305f487d72ec56dff9441438453c","abstract_canon_sha256":"56ecfeb739cdff269f7d2875ec8e6f6a89d0af7a58650e0cef883008912c8687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:22.963845Z","signature_b64":"gEHP5654/NOgQj72wrpPKjqtAcN+T648/TektXbpKy6Vn+svfK+OUxtPK5oBte48TDcyJMg8YwXTYnIsDqQTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bac13954d634518087987a43182a9bace0f5798580dcd5fc94668bffec7976dc","last_reissued_at":"2026-07-05T05:57:22.963403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:22.963403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Agnostic Reachability Analysis on Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Fu Wang, Geyong Min, Peipei Xu, Wenjie Ruan, Xiaowei Huang","submitted_at":"2023-04-03T09:01:59Z","abstract_excerpt":"Verification plays an essential role in the formal analysis of safety-critical systems. Most current verification methods have specific requirements when working on Deep Neural Networks (DNNs). They either target one particular network category, e.g., Feedforward Neural Networks (FNNs), or networks with specific activation functions, e.g., RdLU. In this paper, we develop a model-agnostic verification framework, called DeepAgn, and show that it can be applied to FNNs, Recurrent Neural Networks (RNNs), or a mixture of both. Under the assumption of Lipschitz continuity, DeepAgn analyses the reach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00813","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/2304.00813/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":"2304.00813","created_at":"2026-07-05T05:57:22.963465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00813v1","created_at":"2026-07-05T05:57:22.963465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00813","created_at":"2026-07-05T05:57:22.963465+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLATSVGWGRIY","created_at":"2026-07-05T05:57:22.963465+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLATSVGWGRIYBB4Y","created_at":"2026-07-05T05:57:22.963465+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLATSVGW","created_at":"2026-07-05T05:57:22.963465+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/XLATSVGWGRIYBB4YPJBRQKU3VT","json":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT.json","graph_json":"https://pith.science/api/pith-number/XLATSVGWGRIYBB4YPJBRQKU3VT/graph.json","events_json":"https://pith.science/api/pith-number/XLATSVGWGRIYBB4YPJBRQKU3VT/events.json","paper":"https://pith.science/paper/XLATSVGW"},"agent_actions":{"view_html":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT","download_json":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT.json","view_paper":"https://pith.science/paper/XLATSVGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00813&json=true","fetch_graph":"https://pith.science/api/pith-number/XLATSVGWGRIYBB4YPJBRQKU3VT/graph.json","fetch_events":"https://pith.science/api/pith-number/XLATSVGWGRIYBB4YPJBRQKU3VT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT/action/storage_attestation","attest_author":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT/action/author_attestation","sign_citation":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT/action/citation_signature","submit_replication":"https://pith.science/pith/XLATSVGWGRIYBB4YPJBRQKU3VT/action/replication_record"}},"created_at":"2026-07-05T05:57:22.963465+00:00","updated_at":"2026-07-05T05:57:22.963465+00:00"}