{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SW4HRIYDYLFGKNRZ4EEF5XH5AP","short_pith_number":"pith:SW4HRIYD","schema_version":"1.0","canonical_sha256":"95b878a303c2ca653639e1085edcfd03c27a6a9ada476277f870cc33b05b11fa","source":{"kind":"arxiv","id":"1909.06588","version":5},"attestation_state":"computed","paper":{"title":"Branch and Bound for Piecewise Linear Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilker Turkaslan, Jingyue Lu, M. Pawan Kumar, Philip H.S. Torr, Pushmeet Kohli, Rudy Bunel","submitted_at":"2019-09-14T12:44:35Z","abstract_excerpt":"The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. In this context, verification involves proving or disproving that an NN model satisfies certain input-output properties. Despite the reputation of learned NN models as black boxes, and the theoretical hardness of proving useful properties about them, researchers have been successful in verifying some classes of models by exploiting their piecewise linear structure and taking insights from formal methods such as Satisifiability Modu"},"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":"1909.06588","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-14T12:44:35Z","cross_cats_sorted":["cs.LO","stat.ML"],"title_canon_sha256":"61e2e3f5488d16ff9a686eba176a046dfe40b6e19705cef88e47b24bc78da839","abstract_canon_sha256":"984ad33f790befb43c4bfd11141bdf2c364e42074087a6c6046d8fed9e880935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:01.582140Z","signature_b64":"50tjh/fWxA7UujwgPgdqDKH65d/s55MZErmUFwKXCmeKw+tMWDl6aAYU5XboeGgZj4eRJOoKY4bUK3B41/uiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95b878a303c2ca653639e1085edcfd03c27a6a9ada476277f870cc33b05b11fa","last_reissued_at":"2026-07-05T11:59:01.581672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:01.581672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Branch and Bound for Piecewise Linear Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilker Turkaslan, Jingyue Lu, M. Pawan Kumar, Philip H.S. Torr, Pushmeet Kohli, Rudy Bunel","submitted_at":"2019-09-14T12:44:35Z","abstract_excerpt":"The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. In this context, verification involves proving or disproving that an NN model satisfies certain input-output properties. Despite the reputation of learned NN models as black boxes, and the theoretical hardness of proving useful properties about them, researchers have been successful in verifying some classes of models by exploiting their piecewise linear structure and taking insights from formal methods such as Satisifiability Modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06588","kind":"arxiv","version":5},"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/1909.06588/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":"1909.06588","created_at":"2026-07-05T11:59:01.581731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.06588v5","created_at":"2026-07-05T11:59:01.581731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06588","created_at":"2026-07-05T11:59:01.581731+00:00"},{"alias_kind":"pith_short_12","alias_value":"SW4HRIYDYLFG","created_at":"2026-07-05T11:59:01.581731+00:00"},{"alias_kind":"pith_short_16","alias_value":"SW4HRIYDYLFGKNRZ","created_at":"2026-07-05T11:59:01.581731+00:00"},{"alias_kind":"pith_short_8","alias_value":"SW4HRIYD","created_at":"2026-07-05T11:59:01.581731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30155","citing_title":"Neural Network Verification using Partial Multi-Neuron Relaxation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP","json":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP.json","graph_json":"https://pith.science/api/pith-number/SW4HRIYDYLFGKNRZ4EEF5XH5AP/graph.json","events_json":"https://pith.science/api/pith-number/SW4HRIYDYLFGKNRZ4EEF5XH5AP/events.json","paper":"https://pith.science/paper/SW4HRIYD"},"agent_actions":{"view_html":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP","download_json":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP.json","view_paper":"https://pith.science/paper/SW4HRIYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.06588&json=true","fetch_graph":"https://pith.science/api/pith-number/SW4HRIYDYLFGKNRZ4EEF5XH5AP/graph.json","fetch_events":"https://pith.science/api/pith-number/SW4HRIYDYLFGKNRZ4EEF5XH5AP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP/action/storage_attestation","attest_author":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP/action/author_attestation","sign_citation":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP/action/citation_signature","submit_replication":"https://pith.science/pith/SW4HRIYDYLFGKNRZ4EEF5XH5AP/action/replication_record"}},"created_at":"2026-07-05T11:59:01.581731+00:00","updated_at":"2026-07-05T11:59:01.581731+00:00"}