{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETZ2F6OP5AIMEBRRTM473LGQ45","short_pith_number":"pith:ETZ2F6OP","schema_version":"1.0","canonical_sha256":"24f3a2f9cfe810c206319b39fdacd0e75c252b98a66169ca37d87abd979cc33a","source":{"kind":"arxiv","id":"2411.13808","version":1},"attestation_state":"computed","paper":{"title":"GPAI Evaluations Standards Taskforce: Towards Effective AI Governance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Everett Smith, Lisa Soder, Lukas Berglund, Patricia Paskov","submitted_at":"2024-11-21T03:14:31Z","abstract_excerpt":"General-purpose AI evaluations have been proposed as a promising way of identifying and mitigating systemic risks posed by AI development and deployment. While GPAI evaluations play an increasingly central role in institutional decision- and policy-making -- including by way of the European Union AI Act's mandate to conduct evaluations on GPAI models presenting systemic risk -- no standards exist to date to promote their quality or legitimacy. To strengthen GPAI evaluations in the EU, which currently constitutes the first and only jurisdiction that mandates GPAI evaluations, we outline four de"},"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":"2411.13808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-11-21T03:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"fc9ff1f3219e30c9172d7563cae12079e4c121facc294a604b3513aba651a0ee","abstract_canon_sha256":"040be8248d17a7ffeecc7b59d677bf237591aa6fbd2000f03331d6c45735aadd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:37.368714Z","signature_b64":"+uWw+wls7Od/VJEVuxJrfDsmISLiSZYcJb4CGywe8bX4zbf2++qysiLvkAOLzS+ei0hu0/sH8awlMmi7FfTrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f3a2f9cfe810c206319b39fdacd0e75c252b98a66169ca37d87abd979cc33a","last_reissued_at":"2026-07-05T09:38:37.368166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:37.368166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPAI Evaluations Standards Taskforce: Towards Effective AI Governance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Everett Smith, Lisa Soder, Lukas Berglund, Patricia Paskov","submitted_at":"2024-11-21T03:14:31Z","abstract_excerpt":"General-purpose AI evaluations have been proposed as a promising way of identifying and mitigating systemic risks posed by AI development and deployment. While GPAI evaluations play an increasingly central role in institutional decision- and policy-making -- including by way of the European Union AI Act's mandate to conduct evaluations on GPAI models presenting systemic risk -- no standards exist to date to promote their quality or legitimacy. To strengthen GPAI evaluations in the EU, which currently constitutes the first and only jurisdiction that mandates GPAI evaluations, we outline four de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13808","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/2411.13808/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":"2411.13808","created_at":"2026-07-05T09:38:37.368239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13808v1","created_at":"2026-07-05T09:38:37.368239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13808","created_at":"2026-07-05T09:38:37.368239+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETZ2F6OP5AIM","created_at":"2026-07-05T09:38:37.368239+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETZ2F6OP5AIMEBRR","created_at":"2026-07-05T09:38:37.368239+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETZ2F6OP","created_at":"2026-07-05T09:38:37.368239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12207","citing_title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45","json":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45.json","graph_json":"https://pith.science/api/pith-number/ETZ2F6OP5AIMEBRRTM473LGQ45/graph.json","events_json":"https://pith.science/api/pith-number/ETZ2F6OP5AIMEBRRTM473LGQ45/events.json","paper":"https://pith.science/paper/ETZ2F6OP"},"agent_actions":{"view_html":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45","download_json":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45.json","view_paper":"https://pith.science/paper/ETZ2F6OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13808&json=true","fetch_graph":"https://pith.science/api/pith-number/ETZ2F6OP5AIMEBRRTM473LGQ45/graph.json","fetch_events":"https://pith.science/api/pith-number/ETZ2F6OP5AIMEBRRTM473LGQ45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45/action/storage_attestation","attest_author":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45/action/author_attestation","sign_citation":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45/action/citation_signature","submit_replication":"https://pith.science/pith/ETZ2F6OP5AIMEBRRTM473LGQ45/action/replication_record"}},"created_at":"2026-07-05T09:38:37.368239+00:00","updated_at":"2026-07-05T09:38:37.368239+00:00"}