{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DKPQ3FQ32JO24A6EKMEY7LZ2FB","short_pith_number":"pith:DKPQ3FQ3","schema_version":"1.0","canonical_sha256":"1a9f0d961bd25dae03c453098faf3a285afd22307077f7faf5424a5afad16806","source":{"kind":"arxiv","id":"2407.12872","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Large Language Models with fmeval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Malhotra, Keerthan Vasist, Luca Franceschi, Michael Diamond, Michele Donini, Muhammad Bilal Zafar, Pinal Tailor, Pinar Yilmaz, Pola Schw\\\"obel, Tomer Shenhar","submitted_at":"2024-07-15T12:15:08Z","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"},"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":"2407.12872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T12:15:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bdbc84183919e7ce0f88e4e608e48fdb246644dfd48a939c0a1887e2446ce6af","abstract_canon_sha256":"cb69cd00f868f4f42ef93df0b59a97bc074427d095829fe291a56ad3b9139052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.858539Z","signature_b64":"3CIcubDsZyyvDjnMjo6syq08KNj4TBxv5xa7ioBa8ha+GZeZNGgPS2mlZwZQhB8HvzaIYF7mULrVulesSWUjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9f0d961bd25dae03c453098faf3a285afd22307077f7faf5424a5afad16806","last_reissued_at":"2026-07-05T08:45:12.858071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.858071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models with fmeval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Malhotra, Keerthan Vasist, Luca Franceschi, Michael Diamond, Michele Donini, Muhammad Bilal Zafar, Pinal Tailor, Pinar Yilmaz, Pola Schw\\\"obel, Tomer Shenhar","submitted_at":"2024-07-15T12:15:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12872","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/2407.12872/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":"2407.12872","created_at":"2026-07-05T08:45:12.858127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12872v1","created_at":"2026-07-05T08:45:12.858127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12872","created_at":"2026-07-05T08:45:12.858127+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKPQ3FQ32JO2","created_at":"2026-07-05T08:45:12.858127+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKPQ3FQ32JO24A6E","created_at":"2026-07-05T08:45:12.858127+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKPQ3FQ3","created_at":"2026-07-05T08:45:12.858127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09670","citing_title":"The Science of Evaluating Foundation Models","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB","json":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB.json","graph_json":"https://pith.science/api/pith-number/DKPQ3FQ32JO24A6EKMEY7LZ2FB/graph.json","events_json":"https://pith.science/api/pith-number/DKPQ3FQ32JO24A6EKMEY7LZ2FB/events.json","paper":"https://pith.science/paper/DKPQ3FQ3"},"agent_actions":{"view_html":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB","download_json":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB.json","view_paper":"https://pith.science/paper/DKPQ3FQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12872&json=true","fetch_graph":"https://pith.science/api/pith-number/DKPQ3FQ32JO24A6EKMEY7LZ2FB/graph.json","fetch_events":"https://pith.science/api/pith-number/DKPQ3FQ32JO24A6EKMEY7LZ2FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB/action/storage_attestation","attest_author":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB/action/author_attestation","sign_citation":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB/action/citation_signature","submit_replication":"https://pith.science/pith/DKPQ3FQ32JO24A6EKMEY7LZ2FB/action/replication_record"}},"created_at":"2026-07-05T08:45:12.858127+00:00","updated_at":"2026-07-05T08:45:12.858127+00:00"}