{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:52YXVPDPLU6RQCJ5M6ZILJVSNN","short_pith_number":"pith:52YXVPDP","schema_version":"1.0","canonical_sha256":"eeb17abc6f5d3d18093d67b285a6b26b47d4a27e137f471bf120ea2082d833e8","source":{"kind":"arxiv","id":"2109.07989","version":1},"attestation_state":"computed","paper":{"title":"On Misbehaviour and Fault Tolerance in Machine Learning Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jukka K. Nurminen, Lalli Myllyaho, Mikko Raatikainen, Tomi M\\\"annist\\\"o, Tommi Mikkonen","submitted_at":"2021-09-16T13:58:18Z","abstract_excerpt":"Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability, such as reliability and security, of these systems. Systems can be tested and monitored, but this does not provide protection against faults and failures in adapted ML systems themselves. We studied software designs that aim at introducing fault tolerance in ML systems so that possible problems in ML components of the systems can be avoided. The research was "},"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":"2109.07989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2021-09-16T13:58:18Z","cross_cats_sorted":[],"title_canon_sha256":"8cc302086465a624447dce67a3975ff36cab41425310ffabc09a26c062b683af","abstract_canon_sha256":"8b887ec6c6abd47d96bd9dc3268c21dbb799a99414efd1ae2e39db2d4687b64d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:52.269805Z","signature_b64":"oYHTj0e7Fxc5avLpuzpDduf4wHuX5oHGMGK5avfA25lQi1NFGkSUCez3bcvvrlj/j+ju77Blov6HtubmRRpUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb17abc6f5d3d18093d67b285a6b26b47d4a27e137f471bf120ea2082d833e8","last_reissued_at":"2026-07-05T05:06:52.269433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:52.269433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Misbehaviour and Fault Tolerance in Machine Learning Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jukka K. Nurminen, Lalli Myllyaho, Mikko Raatikainen, Tomi M\\\"annist\\\"o, Tommi Mikkonen","submitted_at":"2021-09-16T13:58:18Z","abstract_excerpt":"Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability, such as reliability and security, of these systems. Systems can be tested and monitored, but this does not provide protection against faults and failures in adapted ML systems themselves. We studied software designs that aim at introducing fault tolerance in ML systems so that possible problems in ML components of the systems can be avoided. The research was "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07989","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/2109.07989/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":"2109.07989","created_at":"2026-07-05T05:06:52.269491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.07989v1","created_at":"2026-07-05T05:06:52.269491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07989","created_at":"2026-07-05T05:06:52.269491+00:00"},{"alias_kind":"pith_short_12","alias_value":"52YXVPDPLU6R","created_at":"2026-07-05T05:06:52.269491+00:00"},{"alias_kind":"pith_short_16","alias_value":"52YXVPDPLU6RQCJ5","created_at":"2026-07-05T05:06:52.269491+00:00"},{"alias_kind":"pith_short_8","alias_value":"52YXVPDP","created_at":"2026-07-05T05:06:52.269491+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/52YXVPDPLU6RQCJ5M6ZILJVSNN","json":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN.json","graph_json":"https://pith.science/api/pith-number/52YXVPDPLU6RQCJ5M6ZILJVSNN/graph.json","events_json":"https://pith.science/api/pith-number/52YXVPDPLU6RQCJ5M6ZILJVSNN/events.json","paper":"https://pith.science/paper/52YXVPDP"},"agent_actions":{"view_html":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN","download_json":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN.json","view_paper":"https://pith.science/paper/52YXVPDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.07989&json=true","fetch_graph":"https://pith.science/api/pith-number/52YXVPDPLU6RQCJ5M6ZILJVSNN/graph.json","fetch_events":"https://pith.science/api/pith-number/52YXVPDPLU6RQCJ5M6ZILJVSNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN/action/storage_attestation","attest_author":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN/action/author_attestation","sign_citation":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN/action/citation_signature","submit_replication":"https://pith.science/pith/52YXVPDPLU6RQCJ5M6ZILJVSNN/action/replication_record"}},"created_at":"2026-07-05T05:06:52.269491+00:00","updated_at":"2026-07-05T05:06:52.269491+00:00"}