{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I7HHKZLKHOSXUWS5I4JPQITVGE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ea074e42b2341f0861fc56a6780e46339674c619f75f4b7c95a7b8232c644b22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T19:05:04Z","title_canon_sha256":"07fdc213fafd41aae98ed91b52b2c9ed3691b78168d16e3e654083efb0a7975a"},"schema_version":"1.0","source":{"id":"2605.12657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12657","created_at":"2026-05-18T03:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12657v1","created_at":"2026-05-18T03:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12657","created_at":"2026-05-18T03:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"I7HHKZLKHOSX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"I7HHKZLKHOSXUWS5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"I7HHKZLK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5ad6774062dd24315179d8c65ff2bc8f24defaf29c935f4ee8aea9153142988f","target":"graph","created_at":"2026-05-18T03:09:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We determine that LLMs are generally able to recognize usability as a non-functional requirement in user reviews, in terms of their F-score, but the performance and reliability is strongly dependent on the prompt."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the human raters provide consistent ground truth labels and that the prompt developed on this dataset will produce reliable results on new reviews or different LLMs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large language models can identify usability requirements in user reviews with F-scores comparable to human raters when the prompt is well designed."}],"snapshot_sha256":"183e3b8cdaf39803031a19a27a7c6a14ca630a9b1eff187e2445504dd621fc21"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"It is known that user-centered approaches to requirements engineering in general lead to a better suited product for the end-users. LLM4RE provides promising approaches to support the requirements elicitation process (e.g. classification of requirements). Previous approaches focus on Machine-Learning (ML) or Deep-Learning (DL) aspects, which require intensive training with a large amount of manually labeled data. LLMs, on the other hand, are pre-trained on large amounts of user-generated text data, enabling a user-centric workflow to analyze requirements. In this paper, we explore the possibil","authors_text":"Cedric Wellhausen, Kurt Schneider, Laura Reinhardt","cross_cats":[],"headline":"Large language models can identify usability requirements in user reviews with F-scores comparable to human raters when the prompt is well designed.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T19:05:04Z","title":"User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models"},"references":{"count":26,"internal_anchors":3,"resolved_work":26,"sample":[{"cited_arxiv_id":"","doi":"10.1109/rew.2017.76","is_internal_anchor":false,"ref_index":1,"title":"E. Bakiu, E. Guzman, Which feature is unusable? detecting usability and user experience issues from user reviews, in: 2017 IEEE 25th International Requirements Engineering Conference Workshops (REW), ","work_id":"431bed5b-4d1b-430a-b24e-e07ef04bf16c","year":2017},{"cited_arxiv_id":"","doi":"10.33540/3091","is_internal_anchor":false,"ref_index":2,"title":"Groen, Crowd-Based Requirements Engineering, Doctoral thesis 2 (research not uu / graduation uu), Universiteit Utrecht, 2025","work_id":"733c5b63-f823-4e46-9598-154e238bfaa1","year":2025},{"cited_arxiv_id":"","doi":"10.1145/3444689","is_internal_anchor":false,"ref_index":3,"title":"L. Zhao, W. Alhoshan, A. Ferrari, K. J. Letsholo, M. A. Ajagbe, E.-V. Chioasca, R. T. Batista-Navarro, Natural language processing for requirements engineering: A systematic mapping study, ACM Comput.","work_id":"a106466d-85ec-4c4f-b8c6-618579be471b","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Large language models (llms) for requirements engineering (re): A systematic literature review","work_id":"2eb74df0-3d00-48e2-8142-5f447e9d5188","year":2025},{"cited_arxiv_id":"","doi":"10.1109/rew57809.2023.00024","is_internal_anchor":false,"ref_index":5,"title":"Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)","work_id":"7e50a9a4-df1e-4f4a-afd3-fd45d6f41c29","year":2023}],"snapshot_sha256":"7f68631d2036a3ef6f41d005349b64236ff5b3a9cc9fc1625b47220b1cac640e"},"source":{"id":"2605.12657","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:20:58.447696Z","id":"3f555087-0e57-46da-a353-9e61c970e696","model_set":{"reader":"grok-4.3"},"one_line_summary":"LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large language models can identify usability requirements in user reviews with F-scores comparable to human raters when the prompt is well designed.","strongest_claim":"We determine that LLMs are generally able to recognize usability as a non-functional requirement in user reviews, in terms of their F-score, but the performance and reliability is strongly dependent on the prompt.","weakest_assumption":"That the human raters provide consistent ground truth labels and that the prompt developed on this dataset will produce reliable results on new reviews or different LLMs."}},"verdict_id":"3f555087-0e57-46da-a353-9e61c970e696"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a62247f770d0e3b2ac7d5fc38c9cd6d2ce848d2ae5f9cac8664d127a7f8b3ad4","target":"record","created_at":"2026-05-18T03:09:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ea074e42b2341f0861fc56a6780e46339674c619f75f4b7c95a7b8232c644b22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T19:05:04Z","title_canon_sha256":"07fdc213fafd41aae98ed91b52b2c9ed3691b78168d16e3e654083efb0a7975a"},"schema_version":"1.0","source":{"id":"2605.12657","kind":"arxiv","version":1}},"canonical_sha256":"47ce75656a3ba57a5a5d4712f8227531196c9d3d243737b9c3db92fde2bf330f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47ce75656a3ba57a5a5d4712f8227531196c9d3d243737b9c3db92fde2bf330f","first_computed_at":"2026-05-18T03:09:50.612393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:50.612393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mxqo3lZ69SKCWl4bLX/dEfNwBu7cppRQ70+rJrcafN9PJUyvgTsu3qYMvCZRF79Gde2A4CfIeV5nyb7O14cBBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:50.613256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a62247f770d0e3b2ac7d5fc38c9cd6d2ce848d2ae5f9cac8664d127a7f8b3ad4","sha256:5ad6774062dd24315179d8c65ff2bc8f24defaf29c935f4ee8aea9153142988f","sha256:120ddca9facc9aed56feb638f96e7e13f29fdb67086404f1f58afe94dd426ef0"],"state_sha256":"264df0d0ac0c2fb705d99e1a4f308d0c4f92a30f9e78476d9e2266495d369d93"}