{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LYO2NW744OXCI2P2XJFUNF56OR","short_pith_number":"pith:LYO2NW74","schema_version":"1.0","canonical_sha256":"5e1da6dbfce3ae2469faba4b4697be74664b132dc2d27445d638b899aa434fd6","source":{"kind":"arxiv","id":"2304.02554","version":1},"attestation_state":"computed","paper":{"title":"Human-like Summarization Evaluation with ChatGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Ruan, Mingqi Gao, Renliang Sun, Shiping Yang, Xiaojun Wan, Xunjian Yin","submitted_at":"2023-04-05T16:17:32Z","abstract_excerpt":"Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory. In this study, we explored ChatGPT's ability to perform human-like summarization evaluation using four human evaluation methods on five datasets. We found that ChatGPT was able to complete annotations relatively smoothly using Likert scale scoring, pairwise comparison, Pyramid, and binary factuality evaluation. Additionally, it outperformed commonly used automatic evaluation metrics on some datasets. Furthermore, we discussed the impact of different prompts, compared its performan"},"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":"2304.02554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-05T16:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"a59cddd9d8cd4d4b273a3e60b46b9a4dfed44a729bc62f6d4374dc958c8c330e","abstract_canon_sha256":"a24e132d2b29492700827c16f972a1949a950700b02d227ec90ba96e0f88def5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:26.707151Z","signature_b64":"x88EuP+81bJSDh9R7Ddb7J4Q2bzox/fcgMN+FDDS/036u/pTZXSpfmS1TB4vtsdBIfKBngAJui6/lf0reY87BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e1da6dbfce3ae2469faba4b4697be74664b132dc2d27445d638b899aa434fd6","last_reissued_at":"2026-07-05T05:58:26.706788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:26.706788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-like Summarization Evaluation with ChatGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Ruan, Mingqi Gao, Renliang Sun, Shiping Yang, Xiaojun Wan, Xunjian Yin","submitted_at":"2023-04-05T16:17:32Z","abstract_excerpt":"Evaluating text summarization is a challenging problem, and existing evaluation metrics are far from satisfactory. In this study, we explored ChatGPT's ability to perform human-like summarization evaluation using four human evaluation methods on five datasets. We found that ChatGPT was able to complete annotations relatively smoothly using Likert scale scoring, pairwise comparison, Pyramid, and binary factuality evaluation. Additionally, it outperformed commonly used automatic evaluation metrics on some datasets. Furthermore, we discussed the impact of different prompts, compared its performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02554","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/2304.02554/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":"2304.02554","created_at":"2026-07-05T05:58:26.706849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02554v1","created_at":"2026-07-05T05:58:26.706849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02554","created_at":"2026-07-05T05:58:26.706849+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYO2NW744OXC","created_at":"2026-07-05T05:58:26.706849+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYO2NW744OXCI2P2","created_at":"2026-07-05T05:58:26.706849+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYO2NW74","created_at":"2026-07-05T05:58:26.706849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07936","citing_title":"Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00305","citing_title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2308.07201","citing_title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25665","citing_title":"LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR","json":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR.json","graph_json":"https://pith.science/api/pith-number/LYO2NW744OXCI2P2XJFUNF56OR/graph.json","events_json":"https://pith.science/api/pith-number/LYO2NW744OXCI2P2XJFUNF56OR/events.json","paper":"https://pith.science/paper/LYO2NW74"},"agent_actions":{"view_html":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR","download_json":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR.json","view_paper":"https://pith.science/paper/LYO2NW74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02554&json=true","fetch_graph":"https://pith.science/api/pith-number/LYO2NW744OXCI2P2XJFUNF56OR/graph.json","fetch_events":"https://pith.science/api/pith-number/LYO2NW744OXCI2P2XJFUNF56OR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR/action/storage_attestation","attest_author":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR/action/author_attestation","sign_citation":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR/action/citation_signature","submit_replication":"https://pith.science/pith/LYO2NW744OXCI2P2XJFUNF56OR/action/replication_record"}},"created_at":"2026-07-05T05:58:26.706849+00:00","updated_at":"2026-07-05T05:58:26.706849+00:00"}