{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BGS4UFYZ2SUDBNANVXQDZFJ7ZT","short_pith_number":"pith:BGS4UFYZ","schema_version":"1.0","canonical_sha256":"09a5ca1719d4a830b40dade03c953fcce4b4c58b2f1aab4254e6471a74f13df2","source":{"kind":"arxiv","id":"2406.05251","version":1},"attestation_state":"computed","paper":{"title":"Automated Trustworthiness Testing for Machine Learning Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Seaton Cousins-Baxter, Stefano Ruberto, Steven Cho, Valerio Terragni","submitted_at":"2024-06-07T20:25:05Z","abstract_excerpt":"Machine Learning (ML) has become an integral part of our society, commonly used in critical domains such as finance, healthcare, and transportation. Therefore, it is crucial to evaluate not only whether ML models make correct predictions but also whether they do so for the correct reasons, ensuring our trust that will perform well on unseen data. This concept is known as trustworthiness in ML. Recently, explainable techniques (e.g., LIME, SHAP) have been developed to interpret the decision-making processes of ML models, providing explanations for their predictions (e.g., words in the input tha"},"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":"2406.05251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T20:25:05Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"4ea66f967a00856daab078873d61c5c905ac9fe7b19998e15c6319af663efe78","abstract_canon_sha256":"f2b68f9823c9b1981401eb53d0fefb08e659c48fb03ea00f524322902148e50c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:03.099608Z","signature_b64":"kZxnLN6Xm1pDHQL9lgxP24Qi6WYxBl74gLPG/TjATe9cnR6L/zOn4ZYYQAeStixYV5IvbSMZv+OO703jfOX+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09a5ca1719d4a830b40dade03c953fcce4b4c58b2f1aab4254e6471a74f13df2","last_reissued_at":"2026-07-05T08:29:03.099172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:03.099172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Trustworthiness Testing for Machine Learning Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Seaton Cousins-Baxter, Stefano Ruberto, Steven Cho, Valerio Terragni","submitted_at":"2024-06-07T20:25:05Z","abstract_excerpt":"Machine Learning (ML) has become an integral part of our society, commonly used in critical domains such as finance, healthcare, and transportation. Therefore, it is crucial to evaluate not only whether ML models make correct predictions but also whether they do so for the correct reasons, ensuring our trust that will perform well on unseen data. This concept is known as trustworthiness in ML. Recently, explainable techniques (e.g., LIME, SHAP) have been developed to interpret the decision-making processes of ML models, providing explanations for their predictions (e.g., words in the input tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05251","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/2406.05251/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":"2406.05251","created_at":"2026-07-05T08:29:03.099241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05251v1","created_at":"2026-07-05T08:29:03.099241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05251","created_at":"2026-07-05T08:29:03.099241+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGS4UFYZ2SUD","created_at":"2026-07-05T08:29:03.099241+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGS4UFYZ2SUDBNAN","created_at":"2026-07-05T08:29:03.099241+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGS4UFYZ","created_at":"2026-07-05T08:29:03.099241+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/BGS4UFYZ2SUDBNANVXQDZFJ7ZT","json":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT.json","graph_json":"https://pith.science/api/pith-number/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/graph.json","events_json":"https://pith.science/api/pith-number/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/events.json","paper":"https://pith.science/paper/BGS4UFYZ"},"agent_actions":{"view_html":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT","download_json":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT.json","view_paper":"https://pith.science/paper/BGS4UFYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05251&json=true","fetch_graph":"https://pith.science/api/pith-number/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/graph.json","fetch_events":"https://pith.science/api/pith-number/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/action/storage_attestation","attest_author":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/action/author_attestation","sign_citation":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/action/citation_signature","submit_replication":"https://pith.science/pith/BGS4UFYZ2SUDBNANVXQDZFJ7ZT/action/replication_record"}},"created_at":"2026-07-05T08:29:03.099241+00:00","updated_at":"2026-07-05T08:29:03.099241+00:00"}