{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5XY6ASRS53JSNYALRCK4AOEO2","short_pith_number":"pith:U5XY6ASR","schema_version":"1.0","canonical_sha256":"a76f8f025197769937005c44ae01c476b3065e0838a82636448efda9d44f1e7d","source":{"kind":"arxiv","id":"2401.17555","version":2},"attestation_state":"computed","paper":{"title":"opML: Optimistic Machine Learning on Blockchain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Cathie So, Kartin Wong, KD Conway, Xiaohang Yu","submitted_at":"2024-01-31T02:43:38Z","abstract_excerpt":"The integration of machine learning with blockchain technology has witnessed increasing interest, driven by the vision of decentralized, secure, and transparent AI services. In this context, we introduce opML (Optimistic Machine Learning on chain), an innovative approach that empowers blockchain systems to conduct AI model inference. opML lies a interactive fraud proof protocol, reminiscent of the optimistic rollup systems. This mechanism ensures decentralized and verifiable consensus for ML services, enhancing trust and transparency. Unlike zkML (Zero-Knowledge Machine Learning), opML offers "},"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":"2401.17555","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-01-31T02:43:38Z","cross_cats_sorted":[],"title_canon_sha256":"6eeed37b47aae93c457bcdf5ea3f9fcba8c97c3482b1988f950ae04ace0ed73c","abstract_canon_sha256":"e332a68300480b0ac5ca9863f980f0a67cfba725c4d17345938178b7178cb73e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:03.583607Z","signature_b64":"GuNqrRwUX5iRlPjU9fXM1eJnTFmne3K/gCcWQkVrt7DXypApsRK5fVqYA+5ER7ivVqIoQZzEbdPd1I9TK1nCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a76f8f025197769937005c44ae01c476b3065e0838a82636448efda9d44f1e7d","last_reissued_at":"2026-07-05T07:41:03.582406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:03.582406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"opML: Optimistic Machine Learning on Blockchain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Cathie So, Kartin Wong, KD Conway, Xiaohang Yu","submitted_at":"2024-01-31T02:43:38Z","abstract_excerpt":"The integration of machine learning with blockchain technology has witnessed increasing interest, driven by the vision of decentralized, secure, and transparent AI services. In this context, we introduce opML (Optimistic Machine Learning on chain), an innovative approach that empowers blockchain systems to conduct AI model inference. opML lies a interactive fraud proof protocol, reminiscent of the optimistic rollup systems. This mechanism ensures decentralized and verifiable consensus for ML services, enhancing trust and transparency. Unlike zkML (Zero-Knowledge Machine Learning), opML offers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17555","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/2401.17555/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":"2401.17555","created_at":"2026-07-05T07:41:03.582474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17555v2","created_at":"2026-07-05T07:41:03.582474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17555","created_at":"2026-07-05T07:41:03.582474+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5XY6ASRS53J","created_at":"2026-07-05T07:41:03.582474+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5XY6ASRS53JSNYA","created_at":"2026-07-05T07:41:03.582474+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5XY6ASR","created_at":"2026-07-05T07:41:03.582474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24942","citing_title":"Quantum-Resilient Decentralized AI Economies: Proof-of-Useful-Work and Post-Quantum Security","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21045","citing_title":"OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2404.09005","citing_title":"Proof-of-Learning with Incentive Security","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04810","citing_title":"Game of Coding for Vector-Valued Computations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07841","citing_title":"\\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2","json":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2.json","graph_json":"https://pith.science/api/pith-number/U5XY6ASRS53JSNYALRCK4AOEO2/graph.json","events_json":"https://pith.science/api/pith-number/U5XY6ASRS53JSNYALRCK4AOEO2/events.json","paper":"https://pith.science/paper/U5XY6ASR"},"agent_actions":{"view_html":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2","download_json":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2.json","view_paper":"https://pith.science/paper/U5XY6ASR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17555&json=true","fetch_graph":"https://pith.science/api/pith-number/U5XY6ASRS53JSNYALRCK4AOEO2/graph.json","fetch_events":"https://pith.science/api/pith-number/U5XY6ASRS53JSNYALRCK4AOEO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2/action/storage_attestation","attest_author":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2/action/author_attestation","sign_citation":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2/action/citation_signature","submit_replication":"https://pith.science/pith/U5XY6ASRS53JSNYALRCK4AOEO2/action/replication_record"}},"created_at":"2026-07-05T07:41:03.582474+00:00","updated_at":"2026-07-05T07:41:03.582474+00:00"}