{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IVNSN6DBWGWI7JUGQ622VFEETA","short_pith_number":"pith:IVNSN6DB","schema_version":"1.0","canonical_sha256":"455b26f861b1ac8fa68687b5aa9484982de379688a65810818ed1a4b74260a74","source":{"kind":"arxiv","id":"2605.30155","version":1},"attestation_state":"computed","paper":{"title":"Neural Network Verification using Partial Multi-Neuron Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LO","authors_text":"Guy Katz, Ido Shmuel","submitted_at":"2026-05-28T16:15:13Z","abstract_excerpt":"The increasing integration of deep neural networks in critical systems has spawned a theoretical and practical interest in formally guaranteeing safety properties about their behavior. To achieve this, contemporary verification algorithms rely on computing linear relaxations for a network's non-linear activation functions. Existing approaches for linear relaxations typically fall into one of two categories: single-neuron relaxation, in which each activation neuron is bounded in terms of its sources; and multi-neuron relaxation, in which linear bounds involving multiple activation neurons and t"},"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":"2605.30155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2026-05-28T16:15:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f843b102020bb544fae52a2ba16907dd767d987b716df5a302934c16dafc7f3","abstract_canon_sha256":"ba07904eb90e041015ceedffd985d54daa865374d07d0c477345928fd1b7345a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:11.255292Z","signature_b64":"uqKSEmkdyIPZwES/bDeI7GZ9o7LXTBsio9utmhbKBmlz/WFoS3dICsjUGD9ixoh3m3I/nRPQkemHFFmrIiLCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"455b26f861b1ac8fa68687b5aa9484982de379688a65810818ed1a4b74260a74","last_reissued_at":"2026-05-29T02:06:11.254882Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:11.254882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Verification using Partial Multi-Neuron Relaxation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LO","authors_text":"Guy Katz, Ido Shmuel","submitted_at":"2026-05-28T16:15:13Z","abstract_excerpt":"The increasing integration of deep neural networks in critical systems has spawned a theoretical and practical interest in formally guaranteeing safety properties about their behavior. To achieve this, contemporary verification algorithms rely on computing linear relaxations for a network's non-linear activation functions. Existing approaches for linear relaxations typically fall into one of two categories: single-neuron relaxation, in which each activation neuron is bounded in terms of its sources; and multi-neuron relaxation, in which linear bounds involving multiple activation neurons and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30155","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/2605.30155/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":"2605.30155","created_at":"2026-05-29T02:06:11.254946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30155v1","created_at":"2026-05-29T02:06:11.254946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30155","created_at":"2026-05-29T02:06:11.254946+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVNSN6DBWGWI","created_at":"2026-05-29T02:06:11.254946+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVNSN6DBWGWI7JUG","created_at":"2026-05-29T02:06:11.254946+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVNSN6DB","created_at":"2026-05-29T02:06:11.254946+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/IVNSN6DBWGWI7JUGQ622VFEETA","json":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA.json","graph_json":"https://pith.science/api/pith-number/IVNSN6DBWGWI7JUGQ622VFEETA/graph.json","events_json":"https://pith.science/api/pith-number/IVNSN6DBWGWI7JUGQ622VFEETA/events.json","paper":"https://pith.science/paper/IVNSN6DB"},"agent_actions":{"view_html":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA","download_json":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA.json","view_paper":"https://pith.science/paper/IVNSN6DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30155&json=true","fetch_graph":"https://pith.science/api/pith-number/IVNSN6DBWGWI7JUGQ622VFEETA/graph.json","fetch_events":"https://pith.science/api/pith-number/IVNSN6DBWGWI7JUGQ622VFEETA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA/action/storage_attestation","attest_author":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA/action/author_attestation","sign_citation":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA/action/citation_signature","submit_replication":"https://pith.science/pith/IVNSN6DBWGWI7JUGQ622VFEETA/action/replication_record"}},"created_at":"2026-05-29T02:06:11.254946+00:00","updated_at":"2026-05-29T02:06:11.254946+00:00"}