{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDZ3YSHTZXKRFAFKZEIEHUR25J","short_pith_number":"pith:NDZ3YSHT","schema_version":"1.0","canonical_sha256":"68f3bc48f3cdd51280aac91043d23aea42dfdadaa3c5e81e56f2b7eaeaafddc1","source":{"kind":"arxiv","id":"2506.20274","version":1},"attestation_state":"computed","paper":{"title":"Enterprise Large Language Model Evaluation Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Damien Jose, David Yi, James Gao, John Passarelli, Jordan Leventis, Kang Li, Liya Wang","submitted_at":"2025-06-25T09:34:25Z","abstract_excerpt":"Large Language Models (LLMs) ) have demonstrated promise in boosting productivity across AI-powered tools, yet existing benchmarks like Massive Multitask Language Understanding (MMLU) inadequately assess enterprise-specific task complexities. We propose a 14-task framework grounded in Bloom's Taxonomy to holistically evaluate LLM capabilities in enterprise contexts. To address challenges of noisy data and costly annotation, we develop a scalable pipeline combining LLM-as-a-Labeler, LLM-as-a-Judge, and corrective retrieval-augmented generation (CRAG), curating a robust 9,700-sample benchmark. E"},"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":"2506.20274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-25T09:34:25Z","cross_cats_sorted":[],"title_canon_sha256":"607d69c9e042881f19963ca4fbc9f22265b3f878192eb674cdb21d83b4ec66bb","abstract_canon_sha256":"592dd0acb5ccf597471b16cb6774518551b5657bdad9a4e02da5ea428211c812"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:03.053644Z","signature_b64":"qNfrxX+eohuESwMOXBTiepMGb5/N6APVkRI05Eo3gaodtdYA0qG8Ee2Q0lr34DWNlvMqzYDcW7XAL5zQOdiOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f3bc48f3cdd51280aac91043d23aea42dfdadaa3c5e81e56f2b7eaeaafddc1","last_reissued_at":"2026-07-05T11:27:03.053208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:03.053208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enterprise Large Language Model Evaluation Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Damien Jose, David Yi, James Gao, John Passarelli, Jordan Leventis, Kang Li, Liya Wang","submitted_at":"2025-06-25T09:34:25Z","abstract_excerpt":"Large Language Models (LLMs) ) have demonstrated promise in boosting productivity across AI-powered tools, yet existing benchmarks like Massive Multitask Language Understanding (MMLU) inadequately assess enterprise-specific task complexities. We propose a 14-task framework grounded in Bloom's Taxonomy to holistically evaluate LLM capabilities in enterprise contexts. To address challenges of noisy data and costly annotation, we develop a scalable pipeline combining LLM-as-a-Labeler, LLM-as-a-Judge, and corrective retrieval-augmented generation (CRAG), curating a robust 9,700-sample benchmark. E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20274","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/2506.20274/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":"2506.20274","created_at":"2026-07-05T11:27:03.053263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20274v1","created_at":"2026-07-05T11:27:03.053263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20274","created_at":"2026-07-05T11:27:03.053263+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDZ3YSHTZXKR","created_at":"2026-07-05T11:27:03.053263+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDZ3YSHTZXKRFAFK","created_at":"2026-07-05T11:27:03.053263+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDZ3YSHT","created_at":"2026-07-05T11:27:03.053263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05638","citing_title":"EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J","json":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J.json","graph_json":"https://pith.science/api/pith-number/NDZ3YSHTZXKRFAFKZEIEHUR25J/graph.json","events_json":"https://pith.science/api/pith-number/NDZ3YSHTZXKRFAFKZEIEHUR25J/events.json","paper":"https://pith.science/paper/NDZ3YSHT"},"agent_actions":{"view_html":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J","download_json":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J.json","view_paper":"https://pith.science/paper/NDZ3YSHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20274&json=true","fetch_graph":"https://pith.science/api/pith-number/NDZ3YSHTZXKRFAFKZEIEHUR25J/graph.json","fetch_events":"https://pith.science/api/pith-number/NDZ3YSHTZXKRFAFKZEIEHUR25J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J/action/storage_attestation","attest_author":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J/action/author_attestation","sign_citation":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J/action/citation_signature","submit_replication":"https://pith.science/pith/NDZ3YSHTZXKRFAFKZEIEHUR25J/action/replication_record"}},"created_at":"2026-07-05T11:27:03.053263+00:00","updated_at":"2026-07-05T11:27:03.053263+00:00"}