{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NDZ3YSHTZXKRFAFKZEIEHUR25J","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":"592dd0acb5ccf597471b16cb6774518551b5657bdad9a4e02da5ea428211c812","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-25T09:34:25Z","title_canon_sha256":"607d69c9e042881f19963ca4fbc9f22265b3f878192eb674cdb21d83b4ec66bb"},"schema_version":"1.0","source":{"id":"2506.20274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20274","created_at":"2026-07-05T11:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20274v1","created_at":"2026-07-05T11:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20274","created_at":"2026-07-05T11:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"NDZ3YSHTZXKR","created_at":"2026-07-05T11:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"NDZ3YSHTZXKRFAFK","created_at":"2026-07-05T11:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"NDZ3YSHT","created_at":"2026-07-05T11:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:0762b61064b846d6192d83898415edb904382d63443628b3a93516c163ef6db4","target":"graph","created_at":"2026-07-05T11:27:03Z","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/2506.20274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Damien Jose, David Yi, James Gao, John Passarelli, Jordan Leventis, Kang Li, Liya Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-25T09:34:25Z","title":"Enterprise Large Language Model Evaluation Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20274","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":"sha256:591b8d518cc3e4cb1a673c7f234323b04cb85f493317e565c51d7d33ade1eeb9","target":"record","created_at":"2026-07-05T11:27:03Z","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":"592dd0acb5ccf597471b16cb6774518551b5657bdad9a4e02da5ea428211c812","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-25T09:34:25Z","title_canon_sha256":"607d69c9e042881f19963ca4fbc9f22265b3f878192eb674cdb21d83b4ec66bb"},"schema_version":"1.0","source":{"id":"2506.20274","kind":"arxiv","version":1}},"canonical_sha256":"68f3bc48f3cdd51280aac91043d23aea42dfdadaa3c5e81e56f2b7eaeaafddc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f3bc48f3cdd51280aac91043d23aea42dfdadaa3c5e81e56f2b7eaeaafddc1","first_computed_at":"2026-07-05T11:27:03.053208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:03.053208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNfrxX+eohuESwMOXBTiepMGb5/N6APVkRI05Eo3gaodtdYA0qG8Ee2Q0lr34DWNlvMqzYDcW7XAL5zQOdiOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:03.053644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591b8d518cc3e4cb1a673c7f234323b04cb85f493317e565c51d7d33ade1eeb9","sha256:0762b61064b846d6192d83898415edb904382d63443628b3a93516c163ef6db4"],"state_sha256":"e0f4febcea95a45ac3f010d4e74179eb6e4578152bc6fc8248049eb2bc8726bb"}