{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GB6JYF4ZOBRDNV75X5NG2LLF6P","short_pith_number":"pith:GB6JYF4Z","schema_version":"1.0","canonical_sha256":"307c9c1799706236d7fdbf5a6d2d65f3e3a3c13f245af4c1518f745338857619","source":{"kind":"arxiv","id":"2505.20136","version":1},"attestation_state":"computed","paper":{"title":"Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Damian A. Tamburri, Filippo Scaramuzza, Giovanni Quattrocchi","submitted_at":"2025-05-26T15:39:11Z","abstract_excerpt":"As Artificial Intelligence (AI) systems, particularly those based on machine learning (ML), become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated sectors requiring tamper-proof, auditable evidence, as highlighted by apposite legal frameworks, e.g., the EU AI Act. Conversely, Zero-Knowledge Proofs (ZKPs) offer a cryptographic solution that enables provers to demonstrate, through verified computations, adherence to set requirements without re"},"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":"2505.20136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T15:39:11Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"0432cd683ee825cb70c03d1f7f673e9c06db3ccd488eb2d475a63d2ad08eb712","abstract_canon_sha256":"a7c63800356e8bbb352553d84a8069f481449bb2d3af62c6317ea742a57c5356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.070498Z","signature_b64":"7cnvjXshZLioTq5uMwbAfCPxy/B6CbFZghsq/HX3hMR98hIHG/o7TcM8IJ3euksRhSJxq6RkQvvtVSsYBrKdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"307c9c1799706236d7fdbf5a6d2d65f3e3a3c13f245af4c1518f745338857619","last_reissued_at":"2026-07-05T11:09:53.070025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.070025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Damian A. Tamburri, Filippo Scaramuzza, Giovanni Quattrocchi","submitted_at":"2025-05-26T15:39:11Z","abstract_excerpt":"As Artificial Intelligence (AI) systems, particularly those based on machine learning (ML), become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated sectors requiring tamper-proof, auditable evidence, as highlighted by apposite legal frameworks, e.g., the EU AI Act. Conversely, Zero-Knowledge Proofs (ZKPs) offer a cryptographic solution that enables provers to demonstrate, through verified computations, adherence to set requirements without re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20136","kind":"arxiv","version":1},"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/2505.20136/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":"2505.20136","created_at":"2026-07-05T11:09:53.070076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20136v1","created_at":"2026-07-05T11:09:53.070076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20136","created_at":"2026-07-05T11:09:53.070076+00:00"},{"alias_kind":"pith_short_12","alias_value":"GB6JYF4ZOBRD","created_at":"2026-07-05T11:09:53.070076+00:00"},{"alias_kind":"pith_short_16","alias_value":"GB6JYF4ZOBRDNV75","created_at":"2026-07-05T11:09:53.070076+00:00"},{"alias_kind":"pith_short_8","alias_value":"GB6JYF4Z","created_at":"2026-07-05T11:09:53.070076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.26576","citing_title":"\"Show Me You Comply... Without Showing Me Anything\": Zero-Knowledge Software Auditing for AI-Enabled Systems","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06323","citing_title":"Blockchain and AI: Securing Intelligent Networks for the Future","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P","json":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P.json","graph_json":"https://pith.science/api/pith-number/GB6JYF4ZOBRDNV75X5NG2LLF6P/graph.json","events_json":"https://pith.science/api/pith-number/GB6JYF4ZOBRDNV75X5NG2LLF6P/events.json","paper":"https://pith.science/paper/GB6JYF4Z"},"agent_actions":{"view_html":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P","download_json":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P.json","view_paper":"https://pith.science/paper/GB6JYF4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20136&json=true","fetch_graph":"https://pith.science/api/pith-number/GB6JYF4ZOBRDNV75X5NG2LLF6P/graph.json","fetch_events":"https://pith.science/api/pith-number/GB6JYF4ZOBRDNV75X5NG2LLF6P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P/action/storage_attestation","attest_author":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P/action/author_attestation","sign_citation":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P/action/citation_signature","submit_replication":"https://pith.science/pith/GB6JYF4ZOBRDNV75X5NG2LLF6P/action/replication_record"}},"created_at":"2026-07-05T11:09:53.070076+00:00","updated_at":"2026-07-05T11:09:53.070076+00:00"}