{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K5HRNSTFYYYYVRCWEWDHMFRDRV","short_pith_number":"pith:K5HRNSTF","schema_version":"1.0","canonical_sha256":"574f16ca65c6318ac45625867616238d4b9e89e34060a94214404d68bfab4ea2","source":{"kind":"arxiv","id":"2209.13331","version":1},"attestation_state":"computed","paper":{"title":"EditEval: An Instruction-Based Benchmark for Text Improvements","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edouard Grave, Fabio Petroni, Gautier Izacard, Jane Dwivedi-Yu, Maria Lomeli, Patrick Lewis, Sebastian Riedel, Timo Schick, Zhengbao Jiang","submitted_at":"2022-09-27T12:26:05Z","abstract_excerpt":"Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in different modular skills such as fixing outdated information or making the style more consistent. Even so, comprehensive evaluation of a model's capacity to perform these skills and the ability to edit remains sparse. This work presents EditEval: An instruction-based, benchmark and evaluation suite that leverages high-quality existing and new datasets for automatic"},"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":"2209.13331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T12:26:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"735dc59e20467cf0d40ac921af9b9f33e0621a0fd57f8d05ba07e357203a2e2e","abstract_canon_sha256":"f9e86df088ec26d50539a4dba2061adcd29bae9e5eb4e8942f7d5ea0af1a31ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:09.334821Z","signature_b64":"BTDBrRV+xTnsGYL8QPKGOsfC5jcoRM6UGha/+9/+XdySyKrWpegFfpt2N7zI4lK2wDBIyAm663A2BO46OcBeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"574f16ca65c6318ac45625867616238d4b9e89e34060a94214404d68bfab4ea2","last_reissued_at":"2026-07-05T05:01:09.334351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:09.334351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EditEval: An Instruction-Based Benchmark for Text Improvements","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Edouard Grave, Fabio Petroni, Gautier Izacard, Jane Dwivedi-Yu, Maria Lomeli, Patrick Lewis, Sebastian Riedel, Timo Schick, Zhengbao Jiang","submitted_at":"2022-09-27T12:26:05Z","abstract_excerpt":"Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in different modular skills such as fixing outdated information or making the style more consistent. Even so, comprehensive evaluation of a model's capacity to perform these skills and the ability to edit remains sparse. This work presents EditEval: An instruction-based, benchmark and evaluation suite that leverages high-quality existing and new datasets for automatic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13331","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/2209.13331/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":"2209.13331","created_at":"2026-07-05T05:01:09.334404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13331v1","created_at":"2026-07-05T05:01:09.334404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13331","created_at":"2026-07-05T05:01:09.334404+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5HRNSTFYYYY","created_at":"2026-07-05T05:01:09.334404+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5HRNSTFYYYYVRCW","created_at":"2026-07-05T05:01:09.334404+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5HRNSTF","created_at":"2026-07-05T05:01:09.334404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15597","citing_title":"LLMs Corrupt Your Documents When You Delegate","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV","json":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV.json","graph_json":"https://pith.science/api/pith-number/K5HRNSTFYYYYVRCWEWDHMFRDRV/graph.json","events_json":"https://pith.science/api/pith-number/K5HRNSTFYYYYVRCWEWDHMFRDRV/events.json","paper":"https://pith.science/paper/K5HRNSTF"},"agent_actions":{"view_html":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV","download_json":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV.json","view_paper":"https://pith.science/paper/K5HRNSTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13331&json=true","fetch_graph":"https://pith.science/api/pith-number/K5HRNSTFYYYYVRCWEWDHMFRDRV/graph.json","fetch_events":"https://pith.science/api/pith-number/K5HRNSTFYYYYVRCWEWDHMFRDRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV/action/storage_attestation","attest_author":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV/action/author_attestation","sign_citation":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV/action/citation_signature","submit_replication":"https://pith.science/pith/K5HRNSTFYYYYVRCWEWDHMFRDRV/action/replication_record"}},"created_at":"2026-07-05T05:01:09.334404+00:00","updated_at":"2026-07-05T05:01:09.334404+00:00"}