{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FCLK7U2DILP44R2BCRKKTS7Z62","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b18c0dd22162c538854b092c9f3db5609a44e5dde60fcaae19d306944fe9efd9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:30:45Z","title_canon_sha256":"5121cd88f29dea2aa388555d6e6a937fd1a121872ef98f3b616afa775076055f"},"schema_version":"1.0","source":{"id":"2507.06893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06893","created_at":"2026-07-05T11:34:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06893v1","created_at":"2026-07-05T11:34:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06893","created_at":"2026-07-05T11:34:24Z"},{"alias_kind":"pith_short_12","alias_value":"FCLK7U2DILP4","created_at":"2026-07-05T11:34:24Z"},{"alias_kind":"pith_short_16","alias_value":"FCLK7U2DILP44R2B","created_at":"2026-07-05T11:34:24Z"},{"alias_kind":"pith_short_8","alias_value":"FCLK7U2D","created_at":"2026-07-05T11:34:24Z"}],"graph_snapshots":[{"event_id":"sha256:9edd95fdeb0b8d8feb59b2c64ba57e007deb9ff80d1b81c05618fdbadc73c655","target":"graph","created_at":"2026-07-05T11:34:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.06893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI evaluations have become critical tools for assessing large language model capabilities and safety. This paper presents practical insights from eight months of maintaining $inspect\\_evals$, an open-source repository of 70+ community-contributed AI evaluations. We identify key challenges in implementing and maintaining AI evaluations and develop solutions including: (1) a structured cohort management framework for scaling community contributions, (2) statistical methodologies for optimal resampling and cross-model comparison with uncertainty quantification, and (3) systematic quality control ","authors_text":"Alexandra Abbas, Celia Waggoner, Justin Olive","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:30:45Z","title":"Developing and Maintaining an Open-Source Repository of AI Evaluations: Challenges and Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06893","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:666200659d2a6dd0bd8e1a7b68b5059bdaebe3630889fb414b305d5dedabed33","target":"record","created_at":"2026-07-05T11:34:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b18c0dd22162c538854b092c9f3db5609a44e5dde60fcaae19d306944fe9efd9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T14:30:45Z","title_canon_sha256":"5121cd88f29dea2aa388555d6e6a937fd1a121872ef98f3b616afa775076055f"},"schema_version":"1.0","source":{"id":"2507.06893","kind":"arxiv","version":1}},"canonical_sha256":"2896afd34342dfce47411454a9cbf9f686d5f283234dbdac36b7dd68d18fef0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2896afd34342dfce47411454a9cbf9f686d5f283234dbdac36b7dd68d18fef0d","first_computed_at":"2026-07-05T11:34:24.738811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:24.738811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FVIJ4uHe9mS12KSfrSFQKPAi3Z2eHSdKS3odyEm2HYwIjsDkpSBQhORNPSJnVd2WkqIbov4agqvuftK7/I7LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:24.739238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:666200659d2a6dd0bd8e1a7b68b5059bdaebe3630889fb414b305d5dedabed33","sha256:9edd95fdeb0b8d8feb59b2c64ba57e007deb9ff80d1b81c05618fdbadc73c655"],"state_sha256":"d30d332ab1c9f6642dba2150cdb22d07e360a927844753efd178d1e1884c989f"}