{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WBPAY4GEMR2IHSMI4EE4ONY37D","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":"9ca2e21f733d9a90e59a176f381192736ad5140229fd39d930b94e109b8aef13","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T18:19:05Z","title_canon_sha256":"9b2917a3286b353e78d4c78048e3285ba876b843cdae49977b208644c3763825"},"schema_version":"1.0","source":{"id":"2410.12857","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12857","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12857v1","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12857","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"WBPAY4GEMR2I","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"WBPAY4GEMR2IHSMI","created_at":"2026-07-05T09:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"WBPAY4GE","created_at":"2026-07-05T09:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:4dcae2a1a0a081ea625e10713c329cc42d951f3841eea4261212e0471ce52371","target":"graph","created_at":"2026-07-05T09:21:51Z","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/2410.12857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise applications. Therefore, LLMs need to be able to benchmark enterprise datasets for various tasks. This work presents a systematic exploration of benchmarking strategies tailored to LLM evaluation, focusing on the utilization of domain-specific datasets and consisting of a variety of NLP tasks. The proposed evaluation framework encompasses 25 publicly available datasets from diverse enterprise domains like financial se","authors_text":"Bing Zhang, Guang-Jie Ren, Kate Soule, Md. Maruf Hossain, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Yada Zhu","cross_cats":["cs.AI","cs.CE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T18:19:05Z","title":"Enterprise Benchmarks for Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12857","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:afcfa7e2bdd29fe921fb113608676b8ab454517c6b9a6554e8a13aa9114430f5","target":"record","created_at":"2026-07-05T09:21:51Z","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":"9ca2e21f733d9a90e59a176f381192736ad5140229fd39d930b94e109b8aef13","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T18:19:05Z","title_canon_sha256":"9b2917a3286b353e78d4c78048e3285ba876b843cdae49977b208644c3763825"},"schema_version":"1.0","source":{"id":"2410.12857","kind":"arxiv","version":1}},"canonical_sha256":"b05e0c70c4647483c988e109c7371bf8cbe81867780da3f9daaa03f6b6ad2985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b05e0c70c4647483c988e109c7371bf8cbe81867780da3f9daaa03f6b6ad2985","first_computed_at":"2026-07-05T09:21:51.977518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:51.977518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F2UmaBMsrc35tAfK+NAL1d29Th/RX8y7qzbk9gcBG0E61Hm9voOJN4Jd/EJNW+Uor+qJsctVh/7/zWmNdXHICw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:51.978102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12857","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afcfa7e2bdd29fe921fb113608676b8ab454517c6b9a6554e8a13aa9114430f5","sha256:4dcae2a1a0a081ea625e10713c329cc42d951f3841eea4261212e0471ce52371"],"state_sha256":"83078a3e11ebff5566718fac228d8fbdcc64a96f96fa440f7074fad35c80bc72"}