{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5S5FLYIPCOHMIY5HA7UW2XEYPQ","short_pith_number":"pith:5S5FLYIP","schema_version":"1.0","canonical_sha256":"ecba55e10f138ec463a707e96d5c987c1f36e65e87c7fccb2240036b6cb5e437","source":{"kind":"arxiv","id":"2502.18535","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Bin Cao, Chonghe Zhao, Guofu Liao, Long Shi, Qing Yang, Shengli Zhang, Taotao Wang, Yifeng Liu, Zhizhi Peng, Zibin Lin","submitted_at":"2025-02-25T05:04:27Z","abstract_excerpt":"Machine learning is increasingly deployed through outsourced and cloud-based pipelines, which improve accessibility but also raise concerns about computational integrity, data privacy, and model confidentiality. Zero-knowledge proofs (ZKPs) provide a compelling foundation for verifiable machine learning because they allow one party to certify that a training, testing, or inference result was produced by the claimed computation without revealing sensitive data or proprietary model parameters. Despite rapid progress in zero-knowledge machine learning (ZKML), the literature remains fragmented acr"},"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":"2502.18535","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-02-25T05:04:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"21220574bd2c364702189ede587cc48f7d363da72c40944dcafb69fa3f30ee89","abstract_canon_sha256":"42dda99bd11b203c89e3519c2c38296b162596bfa3c7d2045565660763a843b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:22.261835Z","signature_b64":"wRZgIkOODbXvasTBollzziKmQdKbk+Esg5qBFXX4KnIx6NZaC0/kRDFY8z5vB7JXw0tME1KTsQ68TbS7f3miBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecba55e10f138ec463a707e96d5c987c1f36e65e87c7fccb2240036b6cb5e437","last_reissued_at":"2026-07-29T01:24:22.260896Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:22.260896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Bin Cao, Chonghe Zhao, Guofu Liao, Long Shi, Qing Yang, Shengli Zhang, Taotao Wang, Yifeng Liu, Zhizhi Peng, Zibin Lin","submitted_at":"2025-02-25T05:04:27Z","abstract_excerpt":"Machine learning is increasingly deployed through outsourced and cloud-based pipelines, which improve accessibility but also raise concerns about computational integrity, data privacy, and model confidentiality. Zero-knowledge proofs (ZKPs) provide a compelling foundation for verifiable machine learning because they allow one party to certify that a training, testing, or inference result was produced by the claimed computation without revealing sensitive data or proprietary model parameters. Despite rapid progress in zero-knowledge machine learning (ZKML), the literature remains fragmented acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18535","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/2502.18535/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":"2502.18535","created_at":"2026-07-29T01:24:22.261322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18535v2","created_at":"2026-07-29T01:24:22.261322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18535","created_at":"2026-07-29T01:24:22.261322+00:00"},{"alias_kind":"pith_short_12","alias_value":"5S5FLYIPCOHM","created_at":"2026-07-29T01:24:22.261322+00:00"},{"alias_kind":"pith_short_16","alias_value":"5S5FLYIPCOHMIY5H","created_at":"2026-07-29T01:24:22.261322+00:00"},{"alias_kind":"pith_short_8","alias_value":"5S5FLYIP","created_at":"2026-07-29T01:24:22.261322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2508.12035","citing_title":"ToxiEval-ZKP: A Structure-Private Verification Framework for Molecular Toxicity Repair Tasks","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20421","citing_title":"Hawkeye: Reproducing GPU-Level Non-Determinism","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08922","citing_title":"Toward Web 4.0: Bidirectional Trust between AI Agents and Blockchain","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25200","citing_title":"Making AI-Assisted Grant Evaluation Auditable without Exposing the Model","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07328","citing_title":"Unconsented Sensing: A Sociotechnical Governance Framework for 6G ISAC","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04738","citing_title":"Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ","json":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ.json","graph_json":"https://pith.science/api/pith-number/5S5FLYIPCOHMIY5HA7UW2XEYPQ/graph.json","events_json":"https://pith.science/api/pith-number/5S5FLYIPCOHMIY5HA7UW2XEYPQ/events.json","paper":"https://pith.science/paper/5S5FLYIP"},"agent_actions":{"view_html":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ","download_json":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ.json","view_paper":"https://pith.science/paper/5S5FLYIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18535&json=true","fetch_graph":"https://pith.science/api/pith-number/5S5FLYIPCOHMIY5HA7UW2XEYPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5S5FLYIPCOHMIY5HA7UW2XEYPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ/action/storage_attestation","attest_author":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ/action/author_attestation","sign_citation":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ/action/citation_signature","submit_replication":"https://pith.science/pith/5S5FLYIPCOHMIY5HA7UW2XEYPQ/action/replication_record"}},"created_at":"2026-07-29T01:24:22.261322+00:00","updated_at":"2026-07-29T01:24:22.261322+00:00"}