{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G6AKPF5TXBEVVSE2PZZFSCEBQP","short_pith_number":"pith:G6AKPF5T","schema_version":"1.0","canonical_sha256":"3780a797b3b8495ac89a7e7259088183f2ccec446cbfde6ba93f61cf26fe9ec1","source":{"kind":"arxiv","id":"2405.21063","version":3},"attestation_state":"computed","paper":{"title":"Neural Network Verification with Branch-and-Bound for General Nonlinearities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Huan Zhang, Qirui Jin, Suman Jana, Zhouxing Shi, Zico Kolter","submitted_at":"2024-05-31T17:51:07Z","abstract_excerpt":"Branch-and-bound (BaB) is among the most effective techniques for neural network (NN) verification. However, existing works on BaB for NN verification have mostly focused on NNs with piecewise linear activations, especially ReLU networks. In this paper, we develop a general framework, named GenBaB, to conduct BaB on general nonlinearities to verify NNs with general architectures, based on linear bound propagation for NN verification. To decide which neuron to branch, we design a new branching heuristic which leverages linear bounds as shortcuts to efficiently estimate the potential improvement"},"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":"2405.21063","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T17:51:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d05a12964123dc9e81acbba48ef58e29b15fa166087ed7de1f9262ad92ec4092","abstract_canon_sha256":"48139b633db7d98a2e2162f05c48511a5f61c4860d7f6b8f7b460ed10ad76d90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:20.346309Z","signature_b64":"WTidTiWWfZlcJdJdXvQxaOm3zUbOHgMMrE9hZPy/HZFS5eSKNR6HaBMM5tjj/w4gavolSp9MgiW4vlORsS20Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3780a797b3b8495ac89a7e7259088183f2ccec446cbfde6ba93f61cf26fe9ec1","last_reissued_at":"2026-07-05T10:11:20.345794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:20.345794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Verification with Branch-and-Bound for General Nonlinearities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Huan Zhang, Qirui Jin, Suman Jana, Zhouxing Shi, Zico Kolter","submitted_at":"2024-05-31T17:51:07Z","abstract_excerpt":"Branch-and-bound (BaB) is among the most effective techniques for neural network (NN) verification. However, existing works on BaB for NN verification have mostly focused on NNs with piecewise linear activations, especially ReLU networks. In this paper, we develop a general framework, named GenBaB, to conduct BaB on general nonlinearities to verify NNs with general architectures, based on linear bound propagation for NN verification. To decide which neuron to branch, we design a new branching heuristic which leverages linear bounds as shortcuts to efficiently estimate the potential improvement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21063","kind":"arxiv","version":3},"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/2405.21063/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":"2405.21063","created_at":"2026-07-05T10:11:20.345855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.21063v3","created_at":"2026-07-05T10:11:20.345855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21063","created_at":"2026-07-05T10:11:20.345855+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6AKPF5TXBEV","created_at":"2026-07-05T10:11:20.345855+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6AKPF5TXBEVVSE2","created_at":"2026-07-05T10:11:20.345855+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6AKPF5T","created_at":"2026-07-05T10:11:20.345855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30155","citing_title":"Neural Network Verification using Partial Multi-Neuron Relaxation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18235","citing_title":"Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control","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":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13845","citing_title":"Quantitative Linear Logic for Neuro-Symbolic Learning and Verification","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP","json":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP.json","graph_json":"https://pith.science/api/pith-number/G6AKPF5TXBEVVSE2PZZFSCEBQP/graph.json","events_json":"https://pith.science/api/pith-number/G6AKPF5TXBEVVSE2PZZFSCEBQP/events.json","paper":"https://pith.science/paper/G6AKPF5T"},"agent_actions":{"view_html":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP","download_json":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP.json","view_paper":"https://pith.science/paper/G6AKPF5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.21063&json=true","fetch_graph":"https://pith.science/api/pith-number/G6AKPF5TXBEVVSE2PZZFSCEBQP/graph.json","fetch_events":"https://pith.science/api/pith-number/G6AKPF5TXBEVVSE2PZZFSCEBQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP/action/storage_attestation","attest_author":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP/action/author_attestation","sign_citation":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP/action/citation_signature","submit_replication":"https://pith.science/pith/G6AKPF5TXBEVVSE2PZZFSCEBQP/action/replication_record"}},"created_at":"2026-07-05T10:11:20.345855+00:00","updated_at":"2026-07-05T10:11:20.345855+00:00"}