{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HANDZI3AXYWTQV2H2BZT6NLGWL","short_pith_number":"pith:HANDZI3A","schema_version":"1.0","canonical_sha256":"381a3ca360be2d385747d0733f3566b2e7eeac1ca6475e80c93289ce666b6b4f","source":{"kind":"arxiv","id":"2204.04211","version":1},"attestation_state":"computed","paper":{"title":"Measuring AI Systems Beyond Accuracy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Anusha Sinha, Eric Heim, Jay Palat, Nathan VanHoudnos, Rachel Dzombak, Violet Turri","submitted_at":"2022-04-07T17:09:07Z","abstract_excerpt":"Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics. Testing is additionally often siloed from the other phases of the ML system lifecycle. Research investigating cross-domain approaches to ML T&E is needed to drive the state of the art forward and to build an Artificial Intelligence (AI) engineering discipline. This paper advocates for a robust, integrated approach to testing by outlining six key questions for guiding a holistic T&E strategy."},"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":"2204.04211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-07T17:09:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bf517a568a9bf63b30e2164b6a8bdb7c08fe1a1bbaed43077fc3f5fe2c3b9213","abstract_canon_sha256":"3d6fc033a2b4f0c19fdb18a4e433c1779eb7f4b5a2274324d9bed3b86a1eae59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:46.284394Z","signature_b64":"NhVJxMDBddHIUJ/fB6/97/L3A5kMNEJK4O9nRTtU4e08o7o6VT0pjdx51flRR5/pQ7DdTYxd+xjygTIu6zffBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"381a3ca360be2d385747d0733f3566b2e7eeac1ca6475e80c93289ce666b6b4f","last_reissued_at":"2026-07-05T04:12:46.283927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:46.283927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring AI Systems Beyond Accuracy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Anusha Sinha, Eric Heim, Jay Palat, Nathan VanHoudnos, Rachel Dzombak, Violet Turri","submitted_at":"2022-04-07T17:09:07Z","abstract_excerpt":"Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics. Testing is additionally often siloed from the other phases of the ML system lifecycle. Research investigating cross-domain approaches to ML T&E is needed to drive the state of the art forward and to build an Artificial Intelligence (AI) engineering discipline. This paper advocates for a robust, integrated approach to testing by outlining six key questions for guiding a holistic T&E strategy."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04211","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/2204.04211/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":"2204.04211","created_at":"2026-07-05T04:12:46.283983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04211v1","created_at":"2026-07-05T04:12:46.283983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04211","created_at":"2026-07-05T04:12:46.283983+00:00"},{"alias_kind":"pith_short_12","alias_value":"HANDZI3AXYWT","created_at":"2026-07-05T04:12:46.283983+00:00"},{"alias_kind":"pith_short_16","alias_value":"HANDZI3AXYWTQV2H","created_at":"2026-07-05T04:12:46.283983+00:00"},{"alias_kind":"pith_short_8","alias_value":"HANDZI3A","created_at":"2026-07-05T04:12:46.283983+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/HANDZI3AXYWTQV2H2BZT6NLGWL","json":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL.json","graph_json":"https://pith.science/api/pith-number/HANDZI3AXYWTQV2H2BZT6NLGWL/graph.json","events_json":"https://pith.science/api/pith-number/HANDZI3AXYWTQV2H2BZT6NLGWL/events.json","paper":"https://pith.science/paper/HANDZI3A"},"agent_actions":{"view_html":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL","download_json":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL.json","view_paper":"https://pith.science/paper/HANDZI3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04211&json=true","fetch_graph":"https://pith.science/api/pith-number/HANDZI3AXYWTQV2H2BZT6NLGWL/graph.json","fetch_events":"https://pith.science/api/pith-number/HANDZI3AXYWTQV2H2BZT6NLGWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL/action/storage_attestation","attest_author":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL/action/author_attestation","sign_citation":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL/action/citation_signature","submit_replication":"https://pith.science/pith/HANDZI3AXYWTQV2H2BZT6NLGWL/action/replication_record"}},"created_at":"2026-07-05T04:12:46.283983+00:00","updated_at":"2026-07-05T04:12:46.283983+00:00"}