{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AHV4K5YERZ37ZRPPVVOMVXCSHJ","short_pith_number":"pith:AHV4K5YE","schema_version":"1.0","canonical_sha256":"01ebc577048e77fcc5efad5ccadc523a600e1b846449ba0409d2591560dee095","source":{"kind":"arxiv","id":"2305.11541","version":3},"attestation_state":"computed","paper":{"title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongmei Zhang, Fangkai Yang, Jue Zhang, Lu Wang, Mohit Garg, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Zezhong Wang","submitted_at":"2023-05-19T09:23:25Z","abstract_excerpt":"Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge. This issue has attracted widespread attention, but there are few relevant benchmarks available. In this paper, we provide a benchmark Question Answering (QA) dataset named MSQA, centered around Microsoft products and IT technical problems encountered by customers. This dataset contains industry cloud-specific QA knowledge, an area not extensively covered in general LLMs, m"},"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":"2305.11541","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T09:23:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97db0898f65f31ea8582064d8456dde8c53201199b2858957b0e9493bac1f27b","abstract_canon_sha256":"7aa69180898a37b6fe5a890c0f00db1518dfc1b4888dfc9c52295163ee8dcead"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:01.334698Z","signature_b64":"On2OooDX1SzzQTWSIZYMs7XRWKyyGQsxuibj9uTFb/R6CDN7ds4EWTgJsSO/CwhV7/xE1bGZvKVl3v5tXz1YAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01ebc577048e77fcc5efad5ccadc523a600e1b846449ba0409d2591560dee095","last_reissued_at":"2026-07-05T07:01:01.334205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:01.334205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongmei Zhang, Fangkai Yang, Jue Zhang, Lu Wang, Mohit Garg, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Zezhong Wang","submitted_at":"2023-05-19T09:23:25Z","abstract_excerpt":"Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge. This issue has attracted widespread attention, but there are few relevant benchmarks available. In this paper, we provide a benchmark Question Answering (QA) dataset named MSQA, centered around Microsoft products and IT technical problems encountered by customers. This dataset contains industry cloud-specific QA knowledge, an area not extensively covered in general LLMs, m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11541","kind":"arxiv","version":3},"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/2305.11541/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":"2305.11541","created_at":"2026-07-05T07:01:01.334267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11541v3","created_at":"2026-07-05T07:01:01.334267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11541","created_at":"2026-07-05T07:01:01.334267+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHV4K5YERZ37","created_at":"2026-07-05T07:01:01.334267+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHV4K5YERZ37ZRPP","created_at":"2026-07-05T07:01:01.334267+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHV4K5YE","created_at":"2026-07-05T07:01:01.334267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13580","citing_title":"A Collaborative Framework Integrating Large Language Model and Chemical Fragment Space: Mutual Inspiration for Lead Design","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ","json":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ.json","graph_json":"https://pith.science/api/pith-number/AHV4K5YERZ37ZRPPVVOMVXCSHJ/graph.json","events_json":"https://pith.science/api/pith-number/AHV4K5YERZ37ZRPPVVOMVXCSHJ/events.json","paper":"https://pith.science/paper/AHV4K5YE"},"agent_actions":{"view_html":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ","download_json":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ.json","view_paper":"https://pith.science/paper/AHV4K5YE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11541&json=true","fetch_graph":"https://pith.science/api/pith-number/AHV4K5YERZ37ZRPPVVOMVXCSHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AHV4K5YERZ37ZRPPVVOMVXCSHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ/action/storage_attestation","attest_author":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ/action/author_attestation","sign_citation":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ/action/citation_signature","submit_replication":"https://pith.science/pith/AHV4K5YERZ37ZRPPVVOMVXCSHJ/action/replication_record"}},"created_at":"2026-07-05T07:01:01.334267+00:00","updated_at":"2026-07-05T07:01:01.334267+00:00"}