{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MLTIXGTUA263DOJ7T4WWRSVZ57","short_pith_number":"pith:MLTIXGTU","schema_version":"1.0","canonical_sha256":"62e68b9a7406bdb1b93f9f2d68cab9efc65de31c4e4e2f19770698f7d23dac91","source":{"kind":"arxiv","id":"2305.18486","version":4},"attestation_state":"computed","paper":{"title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jimmy Xiangji Huang, Md Amran Hossen Bhuiyan, Md Tahmid Rahman Laskar, Mizanur Rahman, M Saiful Bari, Shafiq Joty","submitted_at":"2023-05-29T12:37:21Z","abstract_excerpt":"The development of large language models (LLMs) such as ChatGPT has brought a lot of attention recently. However, their evaluation in the benchmark academic datasets remains under-explored due to the difficulty of evaluating the generative outputs produced by this model against the ground truth. In this paper, we aim to present a thorough evaluation of ChatGPT's performance on diverse academic datasets, covering tasks like question-answering, text summarization, code generation, commonsense reasoning, mathematical problem-solving, machine translation, bias detection, and ethical considerations"},"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":"2305.18486","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-29T12:37:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0ab98d48d5fa862a946d00bfd1f204e3a7ccaff8f73676194d2ea70e2fa450cd","abstract_canon_sha256":"ffbec594db9d5ff5b40a515a13ee59207520138ec69d008e5c461bfd754457c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:18.908216Z","signature_b64":"Ssj8chGEqIfM8uTDmqYkw1Z6hZGNnALNoX/cXqNiOMH78NZoiCmOXTKFsdbk3Pd031+OXKPWGFkCqqOVt/gtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62e68b9a7406bdb1b93f9f2d68cab9efc65de31c4e4e2f19770698f7d23dac91","last_reissued_at":"2026-07-05T06:28:18.907776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:18.907776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jimmy Xiangji Huang, Md Amran Hossen Bhuiyan, Md Tahmid Rahman Laskar, Mizanur Rahman, M Saiful Bari, Shafiq Joty","submitted_at":"2023-05-29T12:37:21Z","abstract_excerpt":"The development of large language models (LLMs) such as ChatGPT has brought a lot of attention recently. However, their evaluation in the benchmark academic datasets remains under-explored due to the difficulty of evaluating the generative outputs produced by this model against the ground truth. In this paper, we aim to present a thorough evaluation of ChatGPT's performance on diverse academic datasets, covering tasks like question-answering, text summarization, code generation, commonsense reasoning, mathematical problem-solving, machine translation, bias detection, and ethical considerations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18486","kind":"arxiv","version":4},"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/2305.18486/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":"2305.18486","created_at":"2026-07-05T06:28:18.907834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18486v4","created_at":"2026-07-05T06:28:18.907834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18486","created_at":"2026-07-05T06:28:18.907834+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLTIXGTUA263","created_at":"2026-07-05T06:28:18.907834+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLTIXGTUA263DOJ7","created_at":"2026-07-05T06:28:18.907834+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLTIXGTU","created_at":"2026-07-05T06:28:18.907834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57","json":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57.json","graph_json":"https://pith.science/api/pith-number/MLTIXGTUA263DOJ7T4WWRSVZ57/graph.json","events_json":"https://pith.science/api/pith-number/MLTIXGTUA263DOJ7T4WWRSVZ57/events.json","paper":"https://pith.science/paper/MLTIXGTU"},"agent_actions":{"view_html":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57","download_json":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57.json","view_paper":"https://pith.science/paper/MLTIXGTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18486&json=true","fetch_graph":"https://pith.science/api/pith-number/MLTIXGTUA263DOJ7T4WWRSVZ57/graph.json","fetch_events":"https://pith.science/api/pith-number/MLTIXGTUA263DOJ7T4WWRSVZ57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57/action/storage_attestation","attest_author":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57/action/author_attestation","sign_citation":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57/action/citation_signature","submit_replication":"https://pith.science/pith/MLTIXGTUA263DOJ7T4WWRSVZ57/action/replication_record"}},"created_at":"2026-07-05T06:28:18.907834+00:00","updated_at":"2026-07-05T06:28:18.907834+00:00"}