{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3MCUUTMRQ3B5EO7P7FWOQCJ7PY","short_pith_number":"pith:3MCUUTMR","schema_version":"1.0","canonical_sha256":"db054a4d9186c3d23beff96ce8093f7e31716ffb0dbf2a484b1a4ec22df9ff4b","source":{"kind":"arxiv","id":"2103.10529","version":1},"attestation_state":"computed","paper":{"title":"White Paper Machine Learning in Certified Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adrien Gauffriau, Alexandre Albore, Alexandre Hervieu, Baptiste Lefevre, Bernard Beaudouin, Brice Beltran, Camille Chapdelaine, Christophe Gabreau, Claire Pagetti, Cyril Cappi, Didier Duchel, Eric Jenn, Florence De Grancey, Franck Mamalet, Ghilaine Martinez, Gregory Flandin, Herv\\'e Delseny, Hugues Bonnin, Jean-Brice Ginestet, Jean-Marc Gabriel, Kevin Delmas, Laurent Gard\\`es, Lucian Alecu, Ludovic Ponsolle, Mathieu Damour, S\\'ebastien Gerchinovitz, Sylvaine Picard, Sylvain Pasquet","submitted_at":"2021-03-18T21:14:30Z","abstract_excerpt":"Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submi"},"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":"2103.10529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-18T21:14:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88926d8ef7b69581ee8920bc99b2f857f4a72bb160265571f30fdc463fc4b82a","abstract_canon_sha256":"d8299796714aff8edd96fb364caed083e9e454216774287da1f8fb7583299a01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:42.240791Z","signature_b64":"TMs4qr1WrwONm3zbGucjRTWrqvK6d4SelZ+ZabhOKJv8rd849rUdh0G8rLUMcjKocwnLuSOArwB7IG+UXYp1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db054a4d9186c3d23beff96ce8093f7e31716ffb0dbf2a484b1a4ec22df9ff4b","last_reissued_at":"2026-07-05T02:24:42.240429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:42.240429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"White Paper Machine Learning in Certified Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adrien Gauffriau, Alexandre Albore, Alexandre Hervieu, Baptiste Lefevre, Bernard Beaudouin, Brice Beltran, Camille Chapdelaine, Christophe Gabreau, Claire Pagetti, Cyril Cappi, Didier Duchel, Eric Jenn, Florence De Grancey, Franck Mamalet, Ghilaine Martinez, Gregory Flandin, Herv\\'e Delseny, Hugues Bonnin, Jean-Brice Ginestet, Jean-Marc Gabriel, Kevin Delmas, Laurent Gard\\`es, Lucian Alecu, Ludovic Ponsolle, Mathieu Damour, S\\'ebastien Gerchinovitz, Sylvaine Picard, Sylvain Pasquet","submitted_at":"2021-03-18T21:14:30Z","abstract_excerpt":"Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10529","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/2103.10529/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":"2103.10529","created_at":"2026-07-05T02:24:42.240491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10529v1","created_at":"2026-07-05T02:24:42.240491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10529","created_at":"2026-07-05T02:24:42.240491+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MCUUTMRQ3B5","created_at":"2026-07-05T02:24:42.240491+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MCUUTMRQ3B5EO7P","created_at":"2026-07-05T02:24:42.240491+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MCUUTMR","created_at":"2026-07-05T02:24:42.240491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.17028","citing_title":"Approach Towards Semi-Automated Certification for Low Criticality ML-Enabled Airborne Applications","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY","json":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY.json","graph_json":"https://pith.science/api/pith-number/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/graph.json","events_json":"https://pith.science/api/pith-number/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/events.json","paper":"https://pith.science/paper/3MCUUTMR"},"agent_actions":{"view_html":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY","download_json":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY.json","view_paper":"https://pith.science/paper/3MCUUTMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10529&json=true","fetch_graph":"https://pith.science/api/pith-number/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/graph.json","fetch_events":"https://pith.science/api/pith-number/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/action/storage_attestation","attest_author":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/action/author_attestation","sign_citation":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/action/citation_signature","submit_replication":"https://pith.science/pith/3MCUUTMRQ3B5EO7P7FWOQCJ7PY/action/replication_record"}},"created_at":"2026-07-05T02:24:42.240491+00:00","updated_at":"2026-07-05T02:24:42.240491+00:00"}