{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DKHVD7QOLSOS2MXYMAYEDVYI5K","short_pith_number":"pith:DKHVD7QO","schema_version":"1.0","canonical_sha256":"1a8f51fe0e5c9d2d32f8603041d708eaac19bee5dc1758ed12b15c68d3c1724c","source":{"kind":"arxiv","id":"2408.02565","version":1},"attestation_state":"computed","paper":{"title":"Reasons to Doubt the Impact of AI Risk Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Gabriel Mukobi","submitted_at":"2024-08-05T15:42:51Z","abstract_excerpt":"AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they significantly improve our understanding of AI risks and, consequently, our ability to mitigate those risks. Evaluations may fail to improve understanding in six ways, such as risks manifesting beyond the AI system or insignificant returns from evaluations compared to real-world observations. Improved understanding may also not lead to better risk mitigation in fo"},"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":"2408.02565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-08-05T15:42:51Z","cross_cats_sorted":[],"title_canon_sha256":"0e06aa99373be5c12a5444dcf44e4aa88ee6b1b6a18d4afa02d5ecfda52faed5","abstract_canon_sha256":"06df7d538d094061f0b7e6ea39f9db79e50e399e9840a0c58b9c397ddc1efabe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:14.446623Z","signature_b64":"LP6kt11W2Zv3yhdyrqcJe1ABynyAkGw0iWfcRe2KohP0ENIes+mcir73RS3s3WtgHnwXCZPhsd/OnqXw8fL4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a8f51fe0e5c9d2d32f8603041d708eaac19bee5dc1758ed12b15c68d3c1724c","last_reissued_at":"2026-07-05T08:52:14.446095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:14.446095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasons to Doubt the Impact of AI Risk Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Gabriel Mukobi","submitted_at":"2024-08-05T15:42:51Z","abstract_excerpt":"AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they significantly improve our understanding of AI risks and, consequently, our ability to mitigate those risks. Evaluations may fail to improve understanding in six ways, such as risks manifesting beyond the AI system or insignificant returns from evaluations compared to real-world observations. Improved understanding may also not lead to better risk mitigation in fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02565","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/2408.02565/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":"2408.02565","created_at":"2026-07-05T08:52:14.446154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02565v1","created_at":"2026-07-05T08:52:14.446154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02565","created_at":"2026-07-05T08:52:14.446154+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKHVD7QOLSOS","created_at":"2026-07-05T08:52:14.446154+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKHVD7QOLSOS2MXY","created_at":"2026-07-05T08:52:14.446154+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKHVD7QO","created_at":"2026-07-05T08:52:14.446154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00836","citing_title":"Position Paper: Model Access should be a Key Concern in AI Governance","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K","json":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K.json","graph_json":"https://pith.science/api/pith-number/DKHVD7QOLSOS2MXYMAYEDVYI5K/graph.json","events_json":"https://pith.science/api/pith-number/DKHVD7QOLSOS2MXYMAYEDVYI5K/events.json","paper":"https://pith.science/paper/DKHVD7QO"},"agent_actions":{"view_html":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K","download_json":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K.json","view_paper":"https://pith.science/paper/DKHVD7QO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02565&json=true","fetch_graph":"https://pith.science/api/pith-number/DKHVD7QOLSOS2MXYMAYEDVYI5K/graph.json","fetch_events":"https://pith.science/api/pith-number/DKHVD7QOLSOS2MXYMAYEDVYI5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K/action/storage_attestation","attest_author":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K/action/author_attestation","sign_citation":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K/action/citation_signature","submit_replication":"https://pith.science/pith/DKHVD7QOLSOS2MXYMAYEDVYI5K/action/replication_record"}},"created_at":"2026-07-05T08:52:14.446154+00:00","updated_at":"2026-07-05T08:52:14.446154+00:00"}