{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:33ZRTTSGM45LPUEOLLHVVXNIZD","short_pith_number":"pith:33ZRTTSG","schema_version":"1.0","canonical_sha256":"def319ce46673ab7d08e5acf5adda8c8dbab15df99ca716b2d88583e36fadd9e","source":{"kind":"arxiv","id":"1706.08605","version":1},"attestation_state":"computed","paper":{"title":"Developing Bug-Free Machine Learning Systems With Formal Mathematics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daniel Selsam, David L. Dill, Percy Liang","submitted_at":"2017-06-26T21:30:02Z","abstract_excerpt":"Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual implementation errors can be extremely difficult. We demonstrate a methodology in which developers use an interactive proof assistant to both implement their system and to state a formal theorem defining what it means for their system to be correct. The process of proving this theorem interactively in the proof assistant exposes all implementation errors since any error in the program would cause the proof to fail. As "},"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":"1706.08605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2017-06-26T21:30:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fb46af30b382038872650a6f8606bbc4bf343f0b764570c7f0bbd0e8311418c","abstract_canon_sha256":"924eef696a81c7455daf715a96db107d04f0c9b9ee5040cb7e59d3457f0128c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:31.593744Z","signature_b64":"LTbQwRqMI/0WcEh+hmNhqM/W8EJ68d3ySfYQDFPtn47qDKJRWkSq81ADYQmSmWIKf1StXcuGIH8B/MHs0u0uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def319ce46673ab7d08e5acf5adda8c8dbab15df99ca716b2d88583e36fadd9e","last_reissued_at":"2026-05-18T00:41:31.593171Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:31.593171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing Bug-Free Machine Learning Systems With Formal Mathematics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daniel Selsam, David L. Dill, Percy Liang","submitted_at":"2017-06-26T21:30:02Z","abstract_excerpt":"Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual implementation errors can be extremely difficult. We demonstrate a methodology in which developers use an interactive proof assistant to both implement their system and to state a formal theorem defining what it means for their system to be correct. The process of proving this theorem interactively in the proof assistant exposes all implementation errors since any error in the program would cause the proof to fail. As "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08605","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":""},"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":"1706.08605","created_at":"2026-05-18T00:41:31.593265+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.08605v1","created_at":"2026-05-18T00:41:31.593265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08605","created_at":"2026-05-18T00:41:31.593265+00:00"},{"alias_kind":"pith_short_12","alias_value":"33ZRTTSGM45L","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"33ZRTTSGM45LPUEO","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"33ZRTTSG","created_at":"2026-05-18T12:30:55.937587+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/33ZRTTSGM45LPUEOLLHVVXNIZD","json":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD.json","graph_json":"https://pith.science/api/pith-number/33ZRTTSGM45LPUEOLLHVVXNIZD/graph.json","events_json":"https://pith.science/api/pith-number/33ZRTTSGM45LPUEOLLHVVXNIZD/events.json","paper":"https://pith.science/paper/33ZRTTSG"},"agent_actions":{"view_html":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD","download_json":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD.json","view_paper":"https://pith.science/paper/33ZRTTSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.08605&json=true","fetch_graph":"https://pith.science/api/pith-number/33ZRTTSGM45LPUEOLLHVVXNIZD/graph.json","fetch_events":"https://pith.science/api/pith-number/33ZRTTSGM45LPUEOLLHVVXNIZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD/action/storage_attestation","attest_author":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD/action/author_attestation","sign_citation":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD/action/citation_signature","submit_replication":"https://pith.science/pith/33ZRTTSGM45LPUEOLLHVVXNIZD/action/replication_record"}},"created_at":"2026-05-18T00:41:31.593265+00:00","updated_at":"2026-05-18T00:41:31.593265+00:00"}