{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MU43ZSKOZQWKDZEXK3F4H2UDA5","short_pith_number":"pith:MU43ZSKO","schema_version":"1.0","canonical_sha256":"6539bcc94ecc2ca1e49756cbc3ea8307411f27e7829119322da6c4df577f1601","source":{"kind":"arxiv","id":"2504.13839","version":2},"attestation_state":"computed","paper":{"title":"Audit Cards: Contextualizing AI Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Anka Reuel, Leon Staufer, Mick Yang, Stephen Casper","submitted_at":"2025-04-18T17:59:59Z","abstract_excerpt":"AI governance frameworks increasingly rely on audits, yet the results of their underlying evaluations require interpretation and context to be meaningfully informative. Even technically rigorous evaluations can offer little useful insight if reported selectively or obscurely. Current literature focuses primarily on technical best practices, but evaluations are an inherently sociotechnical process, and there is little guidance on reporting procedures and context. Through literature review, stakeholder interviews, and analysis of governance frameworks, we propose \"audit cards\" to make this conte"},"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":"2504.13839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-04-18T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"6e9258f709df65cd920cc453982acfbc4ccdcb9f1a245cea8751354a24f6ba08","abstract_canon_sha256":"7107c32b380f3a65e2310af633120df14e948169996a26b2ba8ff606e7c32f2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:11.626435Z","signature_b64":"8m98t3+QnlXW+VvkIs8js0Gky57rxGnH7T05wdHAns7KAWZqRaii2hExCMdVW9/krcWanFL+hwrx/cYRTFAWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6539bcc94ecc2ca1e49756cbc3ea8307411f27e7829119322da6c4df577f1601","last_reissued_at":"2026-07-05T11:54:11.625988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:11.625988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audit Cards: Contextualizing AI Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Anka Reuel, Leon Staufer, Mick Yang, Stephen Casper","submitted_at":"2025-04-18T17:59:59Z","abstract_excerpt":"AI governance frameworks increasingly rely on audits, yet the results of their underlying evaluations require interpretation and context to be meaningfully informative. Even technically rigorous evaluations can offer little useful insight if reported selectively or obscurely. Current literature focuses primarily on technical best practices, but evaluations are an inherently sociotechnical process, and there is little guidance on reporting procedures and context. Through literature review, stakeholder interviews, and analysis of governance frameworks, we propose \"audit cards\" to make this conte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13839","kind":"arxiv","version":2},"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/2504.13839/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":"2504.13839","created_at":"2026-07-05T11:54:11.626045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13839v2","created_at":"2026-07-05T11:54:11.626045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13839","created_at":"2026-07-05T11:54:11.626045+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU43ZSKOZQWK","created_at":"2026-07-05T11:54:11.626045+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU43ZSKOZQWKDZEX","created_at":"2026-07-05T11:54:11.626045+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU43ZSKO","created_at":"2026-07-05T11:54:11.626045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14516","citing_title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12207","citing_title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11462","citing_title":"Defeater Cards: Characterizing and Managing Safety Assurance Case Defeaters","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09809","citing_title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14528","citing_title":"Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17753","citing_title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16403","citing_title":"Computational Hermeneutics: Evaluating generative AI as a cultural technology","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5","json":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5.json","graph_json":"https://pith.science/api/pith-number/MU43ZSKOZQWKDZEXK3F4H2UDA5/graph.json","events_json":"https://pith.science/api/pith-number/MU43ZSKOZQWKDZEXK3F4H2UDA5/events.json","paper":"https://pith.science/paper/MU43ZSKO"},"agent_actions":{"view_html":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5","download_json":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5.json","view_paper":"https://pith.science/paper/MU43ZSKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13839&json=true","fetch_graph":"https://pith.science/api/pith-number/MU43ZSKOZQWKDZEXK3F4H2UDA5/graph.json","fetch_events":"https://pith.science/api/pith-number/MU43ZSKOZQWKDZEXK3F4H2UDA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5/action/storage_attestation","attest_author":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5/action/author_attestation","sign_citation":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5/action/citation_signature","submit_replication":"https://pith.science/pith/MU43ZSKOZQWKDZEXK3F4H2UDA5/action/replication_record"}},"created_at":"2026-07-05T11:54:11.626045+00:00","updated_at":"2026-07-05T11:54:11.626045+00:00"}