{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CTIBV2EHW3SSUNO244MRSGKT4N","short_pith_number":"pith:CTIBV2EH","schema_version":"1.0","canonical_sha256":"14d01ae887b6e52a35dae719191953e34a4f712ae7f318d63001a8e6d671b4c2","source":{"kind":"arxiv","id":"2310.15773","version":1},"attestation_state":"computed","paper":{"title":"BLESS: Benchmarking Large Language Models on Sentence Simplification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Chi, Dennis Aumiller, Fernando Alva-Manchego, Laura V\\'asquez-Rodr\\'iguez, Matthew Shardlow, Sweta Agrawal, Tannon Kew","submitted_at":"2023-10-24T12:18:17Z","abstract_excerpt":"We present BLESS, a comprehensive performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS). We examine how well off-the-shelf LLMs can solve this challenging task, assessing a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our analysis considers a suite of automatic metrics as well as a large-scale quantitative investigation into the types of common edit operations performed by the"},"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":"2310.15773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T12:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"9f9bdb185a93e6cfed5c45109c97e4588729082cb03c52a3ded3fb39501af472","abstract_canon_sha256":"13a840a74fba3e09b6dc09f13fead2e7c89856ef1bcf2467992625ce50e4ef28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:30.832965Z","signature_b64":"At5Hijrj9yGDseAfh6k0OtG4HoRLL0Z/RahbbWIr7J3tnyLkcB5oZWs0qxOanqPyhPyMVpM6uKcl58vJnB1EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14d01ae887b6e52a35dae719191953e34a4f712ae7f318d63001a8e6d671b4c2","last_reissued_at":"2026-07-05T07:04:30.832443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:30.832443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLESS: Benchmarking Large Language Models on Sentence Simplification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alison Chi, Dennis Aumiller, Fernando Alva-Manchego, Laura V\\'asquez-Rodr\\'iguez, Matthew Shardlow, Sweta Agrawal, Tannon Kew","submitted_at":"2023-10-24T12:18:17Z","abstract_excerpt":"We present BLESS, a comprehensive performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS). We examine how well off-the-shelf LLMs can solve this challenging task, assessing a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our analysis considers a suite of automatic metrics as well as a large-scale quantitative investigation into the types of common edit operations performed by the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15773","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/2310.15773/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":"2310.15773","created_at":"2026-07-05T07:04:30.832499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15773v1","created_at":"2026-07-05T07:04:30.832499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15773","created_at":"2026-07-05T07:04:30.832499+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTIBV2EHW3SS","created_at":"2026-07-05T07:04:30.832499+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTIBV2EHW3SSUNO2","created_at":"2026-07-05T07:04:30.832499+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTIBV2EH","created_at":"2026-07-05T07:04:30.832499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08281","citing_title":"Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N","json":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N.json","graph_json":"https://pith.science/api/pith-number/CTIBV2EHW3SSUNO244MRSGKT4N/graph.json","events_json":"https://pith.science/api/pith-number/CTIBV2EHW3SSUNO244MRSGKT4N/events.json","paper":"https://pith.science/paper/CTIBV2EH"},"agent_actions":{"view_html":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N","download_json":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N.json","view_paper":"https://pith.science/paper/CTIBV2EH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15773&json=true","fetch_graph":"https://pith.science/api/pith-number/CTIBV2EHW3SSUNO244MRSGKT4N/graph.json","fetch_events":"https://pith.science/api/pith-number/CTIBV2EHW3SSUNO244MRSGKT4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N/action/storage_attestation","attest_author":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N/action/author_attestation","sign_citation":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N/action/citation_signature","submit_replication":"https://pith.science/pith/CTIBV2EHW3SSUNO244MRSGKT4N/action/replication_record"}},"created_at":"2026-07-05T07:04:30.832499+00:00","updated_at":"2026-07-05T07:04:30.832499+00:00"}