{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UNHISP5JGDU5MDKZTVAYKTMMPD","short_pith_number":"pith:UNHISP5J","schema_version":"1.0","canonical_sha256":"a34e893fa930e9d60d599d41854d8c78e0dfeb599aaf16704ff41534b2521592","source":{"kind":"arxiv","id":"2109.00498","version":1},"attestation_state":"computed","paper":{"title":"The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.LO","authors_text":"Changliu Liu, Stanley Bak, Taylor Johnson","submitted_at":"2021-08-31T01:29:56Z","abstract_excerpt":"This report summarizes the second International Verification of Neural Networks Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for ML-Enabled Autonomous Systems that was collocated with the 33rd International Conference on Computer-Aided Verification (CAV). Twelve teams participated in this competition. The goal of the competition is to provide an objective comparison of the state-of-the-art methods in neural network verification, in terms of scalability and speed. Along this line, we used standard formats (ONNX for neural networks and VNNLIB for specificatio"},"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":"2109.00498","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2021-08-31T01:29:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d879b05d8383cbe5369c55300e0db080282e18b924ad965f1a3f43011e112f9b","abstract_canon_sha256":"ba738c92ba94a4e319584e04cb3b0ca51c47493739148145c4a042db12247b7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:48.671701Z","signature_b64":"CWNATUf2feLTcH77ZWbn7z2Q5fQciOfrI4tLBhL0hgYI9zr/I6yXq2RyNjHRKOMqMasAEuvt5aGfd7Z/wm8VCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34e893fa930e9d60d599d41854d8c78e0dfeb599aaf16704ff41534b2521592","last_reissued_at":"2026-07-05T03:11:48.671226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:48.671226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.LO","authors_text":"Changliu Liu, Stanley Bak, Taylor Johnson","submitted_at":"2021-08-31T01:29:56Z","abstract_excerpt":"This report summarizes the second International Verification of Neural Networks Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for ML-Enabled Autonomous Systems that was collocated with the 33rd International Conference on Computer-Aided Verification (CAV). Twelve teams participated in this competition. The goal of the competition is to provide an objective comparison of the state-of-the-art methods in neural network verification, in terms of scalability and speed. Along this line, we used standard formats (ONNX for neural networks and VNNLIB for specificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00498","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/2109.00498/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":"2109.00498","created_at":"2026-07-05T03:11:48.671286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.00498v1","created_at":"2026-07-05T03:11:48.671286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00498","created_at":"2026-07-05T03:11:48.671286+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNHISP5JGDU5","created_at":"2026-07-05T03:11:48.671286+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNHISP5JGDU5MDKZ","created_at":"2026-07-05T03:11:48.671286+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNHISP5J","created_at":"2026-07-05T03:11:48.671286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20292","citing_title":"Shifting-based Optimizable Linear Relaxations for General Activation Functions","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23203","citing_title":"Lipschitz Optimization for Formal Verification of Homographies","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17153","citing_title":"Stress-Testing Neural Network Verifiers with Provably Robust Instances","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13845","citing_title":"Quantitative Linear Logic for Neuro-Symbolic Learning and Verification","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13845","citing_title":"Quantitative Linear Logic for Neuro-Symbolic Learning and Verification","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD","json":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD.json","graph_json":"https://pith.science/api/pith-number/UNHISP5JGDU5MDKZTVAYKTMMPD/graph.json","events_json":"https://pith.science/api/pith-number/UNHISP5JGDU5MDKZTVAYKTMMPD/events.json","paper":"https://pith.science/paper/UNHISP5J"},"agent_actions":{"view_html":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD","download_json":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD.json","view_paper":"https://pith.science/paper/UNHISP5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.00498&json=true","fetch_graph":"https://pith.science/api/pith-number/UNHISP5JGDU5MDKZTVAYKTMMPD/graph.json","fetch_events":"https://pith.science/api/pith-number/UNHISP5JGDU5MDKZTVAYKTMMPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD/action/storage_attestation","attest_author":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD/action/author_attestation","sign_citation":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD/action/citation_signature","submit_replication":"https://pith.science/pith/UNHISP5JGDU5MDKZTVAYKTMMPD/action/replication_record"}},"created_at":"2026-07-05T03:11:48.671286+00:00","updated_at":"2026-07-05T03:11:48.671286+00:00"}