{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65FU7LJIIV3QY3HFAIEX4FAY5Z","short_pith_number":"pith:65FU7LJI","schema_version":"1.0","canonical_sha256":"f74b4fad2845770c6ce502097e1418ee4798ad0385b74201838036d2f7967df2","source":{"kind":"arxiv","id":"2402.12572","version":2},"attestation_state":"computed","paper":{"title":"FairProof : Confidential and Certifiable Fairness for Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Amrita Roy Chowdhury, Chhavi Yadav, Dan Boneh, Kamalika Chaudhuri","submitted_at":"2024-02-19T21:53:43Z","abstract_excerpt":"Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose \\name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which i"},"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":"2402.12572","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T21:53:43Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"cfbe87ce9cece4d3c18abb6c7404efca7bc5a0b6e64eb6a2b179b93e90d028ba","abstract_canon_sha256":"4401396a166892d6006114439c214ea4bd33adb920733aee9ce6a17fc7afd88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:12.340711Z","signature_b64":"pDHoIRsPaFCdaPVAS9sD3lcMLMdtH7IyIApuQpEMXz5wy+O6es1P2cotWS7MVk743zt18q/+SLH1SNsynpezDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74b4fad2845770c6ce502097e1418ee4798ad0385b74201838036d2f7967df2","last_reissued_at":"2026-07-05T08:44:12.340211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:12.340211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairProof : Confidential and Certifiable Fairness for Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Amrita Roy Chowdhury, Chhavi Yadav, Dan Boneh, Kamalika Chaudhuri","submitted_at":"2024-02-19T21:53:43Z","abstract_excerpt":"Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose \\name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12572","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.12572/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":"2402.12572","created_at":"2026-07-05T08:44:12.340270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12572v2","created_at":"2026-07-05T08:44:12.340270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12572","created_at":"2026-07-05T08:44:12.340270+00:00"},{"alias_kind":"pith_short_12","alias_value":"65FU7LJIIV3Q","created_at":"2026-07-05T08:44:12.340270+00:00"},{"alias_kind":"pith_short_16","alias_value":"65FU7LJIIV3QY3HF","created_at":"2026-07-05T08:44:12.340270+00:00"},{"alias_kind":"pith_short_8","alias_value":"65FU7LJI","created_at":"2026-07-05T08:44:12.340270+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/65FU7LJIIV3QY3HFAIEX4FAY5Z","json":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z.json","graph_json":"https://pith.science/api/pith-number/65FU7LJIIV3QY3HFAIEX4FAY5Z/graph.json","events_json":"https://pith.science/api/pith-number/65FU7LJIIV3QY3HFAIEX4FAY5Z/events.json","paper":"https://pith.science/paper/65FU7LJI"},"agent_actions":{"view_html":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z","download_json":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z.json","view_paper":"https://pith.science/paper/65FU7LJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12572&json=true","fetch_graph":"https://pith.science/api/pith-number/65FU7LJIIV3QY3HFAIEX4FAY5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/65FU7LJIIV3QY3HFAIEX4FAY5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z/action/storage_attestation","attest_author":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z/action/author_attestation","sign_citation":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z/action/citation_signature","submit_replication":"https://pith.science/pith/65FU7LJIIV3QY3HFAIEX4FAY5Z/action/replication_record"}},"created_at":"2026-07-05T08:44:12.340270+00:00","updated_at":"2026-07-05T08:44:12.340270+00:00"}