{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DKPQ3FQ32JO24A6EKMEY7LZ2FB","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":"cb69cd00f868f4f42ef93df0b59a97bc074427d095829fe291a56ad3b9139052","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T12:15:08Z","title_canon_sha256":"bdbc84183919e7ce0f88e4e608e48fdb246644dfd48a939c0a1887e2446ce6af"},"schema_version":"1.0","source":{"id":"2407.12872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12872","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12872v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12872","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"DKPQ3FQ32JO2","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"DKPQ3FQ32JO24A6E","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"DKPQ3FQ3","created_at":"2026-07-05T08:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:cb5d2b9bc70b091ce8de3b71780234376c166c263b67f52d621c70007f26df30","target":"graph","created_at":"2026-07-05T08:45:12Z","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/2407.12872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple responsible AI dimensions. This paper presents the library and exposes its underlying design principles: simplicity, coverage, extensibility and performance. We then present how these were implemented in the scientific and engineering choices taken when developing fmeval. A case study demonstrates a typical use case for the library: picking a suitable model for a question answering task. We close by discussing limitat","authors_text":"Aman Malhotra, Keerthan Vasist, Luca Franceschi, Michael Diamond, Michele Donini, Muhammad Bilal Zafar, Pinal Tailor, Pinar Yilmaz, Pola Schw\\\"obel, Tomer Shenhar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T12:15:08Z","title":"Evaluating Large Language Models with fmeval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12872","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":"sha256:3aacd3112fd634c6782c83e6570caf26c5ce13d3afb0affdb5e573758ec90eb1","target":"record","created_at":"2026-07-05T08:45:12Z","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":"cb69cd00f868f4f42ef93df0b59a97bc074427d095829fe291a56ad3b9139052","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T12:15:08Z","title_canon_sha256":"bdbc84183919e7ce0f88e4e608e48fdb246644dfd48a939c0a1887e2446ce6af"},"schema_version":"1.0","source":{"id":"2407.12872","kind":"arxiv","version":1}},"canonical_sha256":"1a9f0d961bd25dae03c453098faf3a285afd22307077f7faf5424a5afad16806","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a9f0d961bd25dae03c453098faf3a285afd22307077f7faf5424a5afad16806","first_computed_at":"2026-07-05T08:45:12.858071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:12.858071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3CIcubDsZyyvDjnMjo6syq08KNj4TBxv5xa7ioBa8ha+GZeZNGgPS2mlZwZQhB8HvzaIYF7mULrVulesSWUjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:12.858539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aacd3112fd634c6782c83e6570caf26c5ce13d3afb0affdb5e573758ec90eb1","sha256:cb5d2b9bc70b091ce8de3b71780234376c166c263b67f52d621c70007f26df30"],"state_sha256":"33755d541b4aacde055326d89b3bf9af8f976dc01c9dd1c09e9f76933e5e8e74"}