{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Z2E4BQMRONGGIYTKZH35H6AN5U","short_pith_number":"pith:Z2E4BQMR","canonical_record":{"source":{"id":"1702.01135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-03T19:26:01Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"7eb0a7ace4994afdbe54f0dcc06f755f2957d19b019ffaff07bb6099737aa063","abstract_canon_sha256":"2e0db536d2e838c66d439dac32004f20cb34e86b0e0f2141f251a41d928889a5"},"schema_version":"1.0"},"canonical_sha256":"ce89c0c191734c64626ac9f7d3f80ded3beb7e037ab7f94c9c7d9ab3a0e4fd57","source":{"kind":"arxiv","id":"1702.01135","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01135","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01135v2","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01135","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"Z2E4BQMRONGG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z2E4BQMRONGGIYTK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z2E4BQMR","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Z2E4BQMRONGGIYTKZH35H6AN5U","target":"record","payload":{"canonical_record":{"source":{"id":"1702.01135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-03T19:26:01Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"7eb0a7ace4994afdbe54f0dcc06f755f2957d19b019ffaff07bb6099737aa063","abstract_canon_sha256":"2e0db536d2e838c66d439dac32004f20cb34e86b0e0f2141f251a41d928889a5"},"schema_version":"1.0"},"canonical_sha256":"ce89c0c191734c64626ac9f7d3f80ded3beb7e037ab7f94c9c7d9ab3a0e4fd57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:13.403014Z","signature_b64":"lJkTsDyPBh/js9Jvvp757BpRA5ccD89skRDtWMRXJIbAtpQGQV+9a41w/ze/Aki8FlZS6YlruOtoC2RiaNz7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce89c0c191734c64626ac9f7d3f80ded3beb7e037ab7f94c9c7d9ab3a0e4fd57","last_reissued_at":"2026-05-18T00:44:13.402563Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:13.402563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.01135","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTiaubVJ5Q+CflP5mBBHZRwA2bBHuPah/XVARrFCJUVy8ZsXkMFTNmodBD7myBBGDrgCUrRryLctps7WsKHcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:31:21.393333Z"},"content_sha256":"cd3a09e5b068a9d942777878700c62c8df99d8aec01a4cd3e6d5bb0f7fcdec35","schema_version":"1.0","event_id":"sha256:cd3a09e5b068a9d942777878700c62c8df99d8aec01a4cd3e6d5bb0f7fcdec35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Z2E4BQMRONGGIYTKZH35H6AN5U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Clark Barrett, David Dill, Guy Katz, Kyle Julian, Mykel Kochenderfer","submitted_at":"2017-02-03T19:26:01Z","abstract_excerpt":"Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior. We present a novel, scalable, and efficient technique for verifying properties of deep neural networks (or providing counter-examples). The technique is based on the simplex method, extended to handle the non-convex Rectified Linear Unit (ReLU) activation function, which is a crucial ingredient in many modern neural networks. The verific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01135","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:44:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wb1x1RPwHWAwwkvBuW+2G9jgf586c1f1+mid/1W/vzAxY9XjWCIKhV9x70GCw9QaAfxgcMgp+HYzcljqwoYhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:31:21.394376Z"},"content_sha256":"3031432b6630a4991e12c2364756b1a6dc687d8e944d9378c2793095bc534801","schema_version":"1.0","event_id":"sha256:3031432b6630a4991e12c2364756b1a6dc687d8e944d9378c2793095bc534801"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/bundle.json","state_url":"https://pith.science/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T20:31:21Z","links":{"resolver":"https://pith.science/pith/Z2E4BQMRONGGIYTKZH35H6AN5U","bundle":"https://pith.science/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/bundle.json","state":"https://pith.science/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2E4BQMRONGGIYTKZH35H6AN5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Z2E4BQMRONGGIYTKZH35H6AN5U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e0db536d2e838c66d439dac32004f20cb34e86b0e0f2141f251a41d928889a5","cross_cats_sorted":["cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-03T19:26:01Z","title_canon_sha256":"7eb0a7ace4994afdbe54f0dcc06f755f2957d19b019ffaff07bb6099737aa063"},"schema_version":"1.0","source":{"id":"1702.01135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.01135","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"arxiv_version","alias_value":"1702.01135v2","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01135","created_at":"2026-05-18T00:44:13Z"},{"alias_kind":"pith_short_12","alias_value":"Z2E4BQMRONGG","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z2E4BQMRONGGIYTK","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z2E4BQMR","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:3031432b6630a4991e12c2364756b1a6dc687d8e944d9378c2793095bc534801","target":"graph","created_at":"2026-05-18T00:44:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems. However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior. We present a novel, scalable, and efficient technique for verifying properties of deep neural networks (or providing counter-examples). The technique is based on the simplex method, extended to handle the non-convex Rectified Linear Unit (ReLU) activation function, which is a crucial ingredient in many modern neural networks. The verific","authors_text":"Clark Barrett, David Dill, Guy Katz, Kyle Julian, Mykel Kochenderfer","cross_cats":["cs.LO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-03T19:26:01Z","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01135","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cd3a09e5b068a9d942777878700c62c8df99d8aec01a4cd3e6d5bb0f7fcdec35","target":"record","created_at":"2026-05-18T00:44:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2e0db536d2e838c66d439dac32004f20cb34e86b0e0f2141f251a41d928889a5","cross_cats_sorted":["cs.LO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-02-03T19:26:01Z","title_canon_sha256":"7eb0a7ace4994afdbe54f0dcc06f755f2957d19b019ffaff07bb6099737aa063"},"schema_version":"1.0","source":{"id":"1702.01135","kind":"arxiv","version":2}},"canonical_sha256":"ce89c0c191734c64626ac9f7d3f80ded3beb7e037ab7f94c9c7d9ab3a0e4fd57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce89c0c191734c64626ac9f7d3f80ded3beb7e037ab7f94c9c7d9ab3a0e4fd57","first_computed_at":"2026-05-18T00:44:13.402563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:13.402563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lJkTsDyPBh/js9Jvvp757BpRA5ccD89skRDtWMRXJIbAtpQGQV+9a41w/ze/Aki8FlZS6YlruOtoC2RiaNz7Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:13.403014Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.01135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd3a09e5b068a9d942777878700c62c8df99d8aec01a4cd3e6d5bb0f7fcdec35","sha256:3031432b6630a4991e12c2364756b1a6dc687d8e944d9378c2793095bc534801"],"state_sha256":"d1659092f8e39b4dfdddb364cdfda05f64ee3bcde3c45e3b98b1a834fe603371"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFvOh/+rx5dBd/SrN4IbZCPQcCGgtncZ+tHfF8TAQsK9jGPO5W+kSbs67f8ItMcTwzknOT15O4Vd5EHsrg/ECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:31:21.397657Z","bundle_sha256":"0940925840762d7aa2a20533b8e043f38fd5cfe81aba3dda020bf60d2b50935d"}}