{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MBWS6G2UXWT3XDN74VRVHAXKCC","short_pith_number":"pith:MBWS6G2U","schema_version":"1.0","canonical_sha256":"606d2f1b54bda7bb8dbfe5635382ea10bead5840409ddb463734419a65dd71ec","source":{"kind":"arxiv","id":"2103.03638","version":3},"attestation_state":"computed","paper":{"title":"PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Gagandeep Singh, Gleb Makarchuk, Mark Niklas M\\\"uller, Markus P\\\"uschel, Martin Vechev","submitted_at":"2021-03-05T12:53:24Z","abstract_excerpt":"Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant specifications remains an open and difficult challenge. In this paper, we take a major step forward in addressing this challenge and present a new verification framework, called PRIMA. PRIMA is both (i) general: it handles any non-linear activation function, and (ii) precise: it computes precise convex abstractions involving multiple neurons via nove"},"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":"2103.03638","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-03-05T12:53:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e444d5c17657ca0c1412f3963077347451f9e168712e6340fa6c2ac0988f0e16","abstract_canon_sha256":"179aabba907b5d66b5e6075b3425b33010c59784be5d7b97d60d393e6dcf3888"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:13.511733Z","signature_b64":"9+aHZBXnnYxMYvXJ4GNmi6wlRAitVTzp5kn+ytHTeoDZEP7+Ak2HyncvK4ds8WXpTq2Fcy9GsOdoFNLZ2iC6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606d2f1b54bda7bb8dbfe5635382ea10bead5840409ddb463734419a65dd71ec","last_reissued_at":"2026-07-05T04:00:13.511264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:13.511264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Gagandeep Singh, Gleb Makarchuk, Mark Niklas M\\\"uller, Markus P\\\"uschel, Martin Vechev","submitted_at":"2021-03-05T12:53:24Z","abstract_excerpt":"Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant specifications remains an open and difficult challenge. In this paper, we take a major step forward in addressing this challenge and present a new verification framework, called PRIMA. PRIMA is both (i) general: it handles any non-linear activation function, and (ii) precise: it computes precise convex abstractions involving multiple neurons via nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03638","kind":"arxiv","version":3},"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/2103.03638/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":"2103.03638","created_at":"2026-07-05T04:00:13.511323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03638v3","created_at":"2026-07-05T04:00:13.511323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03638","created_at":"2026-07-05T04:00:13.511323+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBWS6G2UXWT3","created_at":"2026-07-05T04:00:13.511323+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBWS6G2UXWT3XDN7","created_at":"2026-07-05T04:00:13.511323+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBWS6G2U","created_at":"2026-07-05T04:00:13.511323+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/MBWS6G2UXWT3XDN74VRVHAXKCC","json":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC.json","graph_json":"https://pith.science/api/pith-number/MBWS6G2UXWT3XDN74VRVHAXKCC/graph.json","events_json":"https://pith.science/api/pith-number/MBWS6G2UXWT3XDN74VRVHAXKCC/events.json","paper":"https://pith.science/paper/MBWS6G2U"},"agent_actions":{"view_html":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC","download_json":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC.json","view_paper":"https://pith.science/paper/MBWS6G2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03638&json=true","fetch_graph":"https://pith.science/api/pith-number/MBWS6G2UXWT3XDN74VRVHAXKCC/graph.json","fetch_events":"https://pith.science/api/pith-number/MBWS6G2UXWT3XDN74VRVHAXKCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC/action/storage_attestation","attest_author":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC/action/author_attestation","sign_citation":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC/action/citation_signature","submit_replication":"https://pith.science/pith/MBWS6G2UXWT3XDN74VRVHAXKCC/action/replication_record"}},"created_at":"2026-07-05T04:00:13.511323+00:00","updated_at":"2026-07-05T04:00:13.511323+00:00"}