{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WBPAY4GEMR2IHSMI4EE4ONY37D","short_pith_number":"pith:WBPAY4GE","schema_version":"1.0","canonical_sha256":"b05e0c70c4647483c988e109c7371bf8cbe81867780da3f9daaa03f6b6ad2985","source":{"kind":"arxiv","id":"2410.12857","version":1},"attestation_state":"computed","paper":{"title":"Enterprise Benchmarks for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.CL","authors_text":"Bing Zhang, Guang-Jie Ren, Kate Soule, Md. Maruf Hossain, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Yada Zhu","submitted_at":"2024-10-11T18:19:05Z","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"},"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":"2410.12857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T18:19:05Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"9b2917a3286b353e78d4c78048e3285ba876b843cdae49977b208644c3763825","abstract_canon_sha256":"9ca2e21f733d9a90e59a176f381192736ad5140229fd39d930b94e109b8aef13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:51.978102Z","signature_b64":"F2UmaBMsrc35tAfK+NAL1d29Th/RX8y7qzbk9gcBG0E61Hm9voOJN4Jd/EJNW+Uor+qJsctVh/7/zWmNdXHICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05e0c70c4647483c988e109c7371bf8cbe81867780da3f9daaa03f6b6ad2985","last_reissued_at":"2026-07-05T09:21:51.977518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:51.977518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enterprise Benchmarks for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.CL","authors_text":"Bing Zhang, Guang-Jie Ren, Kate Soule, Md. Maruf Hossain, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Yada Zhu","submitted_at":"2024-10-11T18:19:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12857","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/2410.12857/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":"2410.12857","created_at":"2026-07-05T09:21:51.977587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12857v1","created_at":"2026-07-05T09:21:51.977587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12857","created_at":"2026-07-05T09:21:51.977587+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBPAY4GEMR2I","created_at":"2026-07-05T09:21:51.977587+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBPAY4GEMR2IHSMI","created_at":"2026-07-05T09:21:51.977587+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBPAY4GE","created_at":"2026-07-05T09:21:51.977587+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":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D","json":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D.json","graph_json":"https://pith.science/api/pith-number/WBPAY4GEMR2IHSMI4EE4ONY37D/graph.json","events_json":"https://pith.science/api/pith-number/WBPAY4GEMR2IHSMI4EE4ONY37D/events.json","paper":"https://pith.science/paper/WBPAY4GE"},"agent_actions":{"view_html":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D","download_json":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D.json","view_paper":"https://pith.science/paper/WBPAY4GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12857&json=true","fetch_graph":"https://pith.science/api/pith-number/WBPAY4GEMR2IHSMI4EE4ONY37D/graph.json","fetch_events":"https://pith.science/api/pith-number/WBPAY4GEMR2IHSMI4EE4ONY37D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D/action/storage_attestation","attest_author":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D/action/author_attestation","sign_citation":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D/action/citation_signature","submit_replication":"https://pith.science/pith/WBPAY4GEMR2IHSMI4EE4ONY37D/action/replication_record"}},"created_at":"2026-07-05T09:21:51.977587+00:00","updated_at":"2026-07-05T09:21:51.977587+00:00"}