{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IJCHRPBBGHJDTOZJS37ENKQ7QQ","short_pith_number":"pith:IJCHRPBB","schema_version":"1.0","canonical_sha256":"424478bc2131d239bb2996fe46aa1f84148e068eb255a96e5a454c293f1dc179","source":{"kind":"arxiv","id":"2212.08567","version":1},"attestation_state":"computed","paper":{"title":"Optimized Symbolic Interval Propagation for Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LO"],"primary_cat":"cs.LG","authors_text":"Carsten Sinz, Marko Kleine B\\\"uning, Philipp Kern","submitted_at":"2022-12-15T14:15:29Z","abstract_excerpt":"Neural networks are increasingly applied in safety critical domains, their verification thus is gaining importance. A large class of recent algorithms for proving input-output relations of feed-forward neural networks are based on linear relaxations and symbolic interval propagation. However, due to variable dependencies, the approximations deteriorate with increasing depth of the network. In this paper we present DPNeurifyFV, a novel branch-and-bound solver for ReLU networks with low dimensional input-space that is based on symbolic interval propagation with fresh variables and input-splittin"},"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":"2212.08567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-15T14:15:29Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LO"],"title_canon_sha256":"fc0bfb55fb28913e02ddbf962719ddabf05b570cdffa13f746b5034d5a134986","abstract_canon_sha256":"47023c0b6e804eb3b8a97fcabed2636f904938fffdc499ddbf00472d005a2762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:58.970353Z","signature_b64":"PzBLl7k8DaEXOtyUA1mCS8G/iVpiQKbajUF0oh0u8MmFeind+ge/Vv/nyBuLJFwHhtDz2V8iW8VuchJnPnGzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424478bc2131d239bb2996fe46aa1f84148e068eb255a96e5a454c293f1dc179","last_reissued_at":"2026-07-05T05:25:58.969880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:58.969880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimized Symbolic Interval Propagation for Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LO"],"primary_cat":"cs.LG","authors_text":"Carsten Sinz, Marko Kleine B\\\"uning, Philipp Kern","submitted_at":"2022-12-15T14:15:29Z","abstract_excerpt":"Neural networks are increasingly applied in safety critical domains, their verification thus is gaining importance. A large class of recent algorithms for proving input-output relations of feed-forward neural networks are based on linear relaxations and symbolic interval propagation. However, due to variable dependencies, the approximations deteriorate with increasing depth of the network. In this paper we present DPNeurifyFV, a novel branch-and-bound solver for ReLU networks with low dimensional input-space that is based on symbolic interval propagation with fresh variables and input-splittin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08567","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/2212.08567/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":"2212.08567","created_at":"2026-07-05T05:25:58.969939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08567v1","created_at":"2026-07-05T05:25:58.969939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08567","created_at":"2026-07-05T05:25:58.969939+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJCHRPBBGHJD","created_at":"2026-07-05T05:25:58.969939+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJCHRPBBGHJDTOZJ","created_at":"2026-07-05T05:25:58.969939+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJCHRPBB","created_at":"2026-07-05T05:25:58.969939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09377","citing_title":"Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ","json":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ.json","graph_json":"https://pith.science/api/pith-number/IJCHRPBBGHJDTOZJS37ENKQ7QQ/graph.json","events_json":"https://pith.science/api/pith-number/IJCHRPBBGHJDTOZJS37ENKQ7QQ/events.json","paper":"https://pith.science/paper/IJCHRPBB"},"agent_actions":{"view_html":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ","download_json":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ.json","view_paper":"https://pith.science/paper/IJCHRPBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08567&json=true","fetch_graph":"https://pith.science/api/pith-number/IJCHRPBBGHJDTOZJS37ENKQ7QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IJCHRPBBGHJDTOZJS37ENKQ7QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ/action/storage_attestation","attest_author":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ/action/author_attestation","sign_citation":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ/action/citation_signature","submit_replication":"https://pith.science/pith/IJCHRPBBGHJDTOZJS37ENKQ7QQ/action/replication_record"}},"created_at":"2026-07-05T05:25:58.969939+00:00","updated_at":"2026-07-05T05:25:58.969939+00:00"}