{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V52YZD3XQ3GHC7HDEJWD4SB6HR","short_pith_number":"pith:V52YZD3X","schema_version":"1.0","canonical_sha256":"af758c8f7786cc717ce3226c3e483e3c7a7858cf1fd48fae24d430e1eb0f1031","source":{"kind":"arxiv","id":"2405.17556","version":3},"attestation_state":"computed","paper":{"title":"Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Boetius, Stefan Leue, Tobias Sutter","submitted_at":"2024-05-27T18:00:03Z","abstract_excerpt":"Probabilistic verification problems of neural networks are concerned with formally analysing the output distribution of a neural network under a probability distribution of the inputs. Examples of probabilistic verification problems include verifying the demographic parity fairness notion or quantifying the safety of a neural network. We present a new algorithm for solving probabilistic verification problems of neural networks based on an algorithm for computing and iteratively refining lower and upper bounds on probabilities over the outputs of a neural network. By applying state-of-the-art b"},"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":"2405.17556","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T18:00:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2565813e396e2200e44fec9416c953c6e16907df12a20fccdb2057a33048f8ad","abstract_canon_sha256":"bf4783b4befda3ff0a5480afd02d35196a6c38046e00a9ab01f4f7a2f1397591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:42.000194Z","signature_b64":"UGK4qkTCJtJEbF4v0DzcIZTyF/DWlkD9SFgQe060pe+p97JTd/oCoyLbF6d0xkGmzV6BjZBPtPE3Gx5/Q6oEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af758c8f7786cc717ce3226c3e483e3c7a7858cf1fd48fae24d430e1eb0f1031","last_reissued_at":"2026-07-05T11:34:41.999741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:41.999741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Boetius, Stefan Leue, Tobias Sutter","submitted_at":"2024-05-27T18:00:03Z","abstract_excerpt":"Probabilistic verification problems of neural networks are concerned with formally analysing the output distribution of a neural network under a probability distribution of the inputs. Examples of probabilistic verification problems include verifying the demographic parity fairness notion or quantifying the safety of a neural network. We present a new algorithm for solving probabilistic verification problems of neural networks based on an algorithm for computing and iteratively refining lower and upper bounds on probabilities over the outputs of a neural network. By applying state-of-the-art b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17556","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/2405.17556/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":"2405.17556","created_at":"2026-07-05T11:34:41.999801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17556v3","created_at":"2026-07-05T11:34:41.999801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17556","created_at":"2026-07-05T11:34:41.999801+00:00"},{"alias_kind":"pith_short_12","alias_value":"V52YZD3XQ3GH","created_at":"2026-07-05T11:34:41.999801+00:00"},{"alias_kind":"pith_short_16","alias_value":"V52YZD3XQ3GHC7HD","created_at":"2026-07-05T11:34:41.999801+00:00"},{"alias_kind":"pith_short_8","alias_value":"V52YZD3X","created_at":"2026-07-05T11:34:41.999801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21556","citing_title":"Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18686","citing_title":"Neural Spectral Bias and Conformal Correlators I: Introduction and Applications","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR","json":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR.json","graph_json":"https://pith.science/api/pith-number/V52YZD3XQ3GHC7HDEJWD4SB6HR/graph.json","events_json":"https://pith.science/api/pith-number/V52YZD3XQ3GHC7HDEJWD4SB6HR/events.json","paper":"https://pith.science/paper/V52YZD3X"},"agent_actions":{"view_html":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR","download_json":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR.json","view_paper":"https://pith.science/paper/V52YZD3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17556&json=true","fetch_graph":"https://pith.science/api/pith-number/V52YZD3XQ3GHC7HDEJWD4SB6HR/graph.json","fetch_events":"https://pith.science/api/pith-number/V52YZD3XQ3GHC7HDEJWD4SB6HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR/action/storage_attestation","attest_author":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR/action/author_attestation","sign_citation":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR/action/citation_signature","submit_replication":"https://pith.science/pith/V52YZD3XQ3GHC7HDEJWD4SB6HR/action/replication_record"}},"created_at":"2026-07-05T11:34:41.999801+00:00","updated_at":"2026-07-05T11:34:41.999801+00:00"}