{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FOJY2S2VT5HZSVQLKXZH5DIKRY","short_pith_number":"pith:FOJY2S2V","schema_version":"1.0","canonical_sha256":"2b938d4b559f4f99560b55f27e8d0a8e3f44cc4ec2bb88374f0a843880631917","source":{"kind":"arxiv","id":"2310.13800","version":1},"attestation_state":"computed","paper":{"title":"Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Sottana, Bin Liang, Kai Zou, Zheng Yuan","submitted_at":"2023-10-20T20:17:09Z","abstract_excerpt":"Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providing a preliminary and hybrid evaluation on a range of open and closed-source generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction (GEC), using both automatic and human evaluation. We also explore the potential of the recently released GPT-4"},"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":"2310.13800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T20:17:09Z","cross_cats_sorted":[],"title_canon_sha256":"11277bda3796af28a2375d4d8d426bee3fd46c1b5305a895680c22ea37126037","abstract_canon_sha256":"aaa3a6997b89c665af4ba48d6b1bc4ec66c02ea8d1fcaae9bb974ae8aeb5acad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:34.989912Z","signature_b64":"rMwnH0r0PeCkKD/UrDCD5U8VTYMhsvhGxCarHTP/EPhECBMmfSrCarkIWYo3aKj2/obgeEdUA8zFDA+5+UMhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b938d4b559f4f99560b55f27e8d0a8e3f44cc4ec2bb88374f0a843880631917","last_reissued_at":"2026-07-05T07:03:34.989490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:34.989490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Sottana, Bin Liang, Kai Zou, Zheng Yuan","submitted_at":"2023-10-20T20:17:09Z","abstract_excerpt":"Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providing a preliminary and hybrid evaluation on a range of open and closed-source generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction (GEC), using both automatic and human evaluation. We also explore the potential of the recently released GPT-4"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13800","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/2310.13800/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":"2310.13800","created_at":"2026-07-05T07:03:34.989546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13800v1","created_at":"2026-07-05T07:03:34.989546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13800","created_at":"2026-07-05T07:03:34.989546+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOJY2S2VT5HZ","created_at":"2026-07-05T07:03:34.989546+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOJY2S2VT5HZSVQL","created_at":"2026-07-05T07:03:34.989546+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOJY2S2V","created_at":"2026-07-05T07:03:34.989546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05384","citing_title":"Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05432","citing_title":"AInstein: Can LLMs Solve Research Problems From Parametric Memory Alone?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":213,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY","json":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY.json","graph_json":"https://pith.science/api/pith-number/FOJY2S2VT5HZSVQLKXZH5DIKRY/graph.json","events_json":"https://pith.science/api/pith-number/FOJY2S2VT5HZSVQLKXZH5DIKRY/events.json","paper":"https://pith.science/paper/FOJY2S2V"},"agent_actions":{"view_html":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY","download_json":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY.json","view_paper":"https://pith.science/paper/FOJY2S2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13800&json=true","fetch_graph":"https://pith.science/api/pith-number/FOJY2S2VT5HZSVQLKXZH5DIKRY/graph.json","fetch_events":"https://pith.science/api/pith-number/FOJY2S2VT5HZSVQLKXZH5DIKRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY/action/storage_attestation","attest_author":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY/action/author_attestation","sign_citation":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY/action/citation_signature","submit_replication":"https://pith.science/pith/FOJY2S2VT5HZSVQLKXZH5DIKRY/action/replication_record"}},"created_at":"2026-07-05T07:03:34.989546+00:00","updated_at":"2026-07-05T07:03:34.989546+00:00"}