{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AQP56QZPY2AZQWPOLS53Q72FJW","short_pith_number":"pith:AQP56QZP","schema_version":"1.0","canonical_sha256":"041fdf432fc6819859ee5cbbb87f454da84448de01c371e6442e224554dde907","source":{"kind":"arxiv","id":"2311.11547","version":2},"attestation_state":"computed","paper":{"title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Abdelkarim El-Hajjami, Camille Salinesi, Nicolas Fafin","submitted_at":"2023-11-20T05:55:05Z","abstract_excerpt":"Recently, Large Language Models like ChatGPT have demonstrated remarkable proficiency in various Natural Language Processing tasks. Their application in Requirements Engineering, especially in requirements classification, has gained increasing interest. This paper reports an extensive empirical evaluation of two ChatGPT models, specifically gpt-3.5-turbo, and gpt-4 in both zero-shot and few-shot settings for requirements classification. The question arises as to how these models compare to traditional classification methods, specifically Support Vector Machine and Long Short-Term Memory. Based"},"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":"2311.11547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-20T05:55:05Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"2f25cc612616c662762790697170b93b8dc9626136c00d5ff65e3fea3b055301","abstract_canon_sha256":"e96d544fdb16df9aa1f1b043e038e8b6236b868c4093197401db7619f5a7a980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:19.259587Z","signature_b64":"O49TUKEm2wtlZmkcC3VnkUt+OyHCu5Nm3+dmHQ0OoMuUr0aJqwqTteh3K9eh/hrK4T9MNzozEN6gLgx5wKPrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"041fdf432fc6819859ee5cbbb87f454da84448de01c371e6442e224554dde907","last_reissued_at":"2026-07-05T08:08:19.259135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:19.259135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Abdelkarim El-Hajjami, Camille Salinesi, Nicolas Fafin","submitted_at":"2023-11-20T05:55:05Z","abstract_excerpt":"Recently, Large Language Models like ChatGPT have demonstrated remarkable proficiency in various Natural Language Processing tasks. Their application in Requirements Engineering, especially in requirements classification, has gained increasing interest. This paper reports an extensive empirical evaluation of two ChatGPT models, specifically gpt-3.5-turbo, and gpt-4 in both zero-shot and few-shot settings for requirements classification. The question arises as to how these models compare to traditional classification methods, specifically Support Vector Machine and Long Short-Term Memory. Based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11547","kind":"arxiv","version":2},"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/2311.11547/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":"2311.11547","created_at":"2026-07-05T08:08:19.259189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11547v2","created_at":"2026-07-05T08:08:19.259189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11547","created_at":"2026-07-05T08:08:19.259189+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQP56QZPY2AZ","created_at":"2026-07-05T08:08:19.259189+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQP56QZPY2AZQWPO","created_at":"2026-07-05T08:08:19.259189+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQP56QZP","created_at":"2026-07-05T08:08:19.259189+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03265","citing_title":"Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW","json":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW.json","graph_json":"https://pith.science/api/pith-number/AQP56QZPY2AZQWPOLS53Q72FJW/graph.json","events_json":"https://pith.science/api/pith-number/AQP56QZPY2AZQWPOLS53Q72FJW/events.json","paper":"https://pith.science/paper/AQP56QZP"},"agent_actions":{"view_html":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW","download_json":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW.json","view_paper":"https://pith.science/paper/AQP56QZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11547&json=true","fetch_graph":"https://pith.science/api/pith-number/AQP56QZPY2AZQWPOLS53Q72FJW/graph.json","fetch_events":"https://pith.science/api/pith-number/AQP56QZPY2AZQWPOLS53Q72FJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW/action/storage_attestation","attest_author":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW/action/author_attestation","sign_citation":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW/action/citation_signature","submit_replication":"https://pith.science/pith/AQP56QZPY2AZQWPOLS53Q72FJW/action/replication_record"}},"created_at":"2026-07-05T08:08:19.259189+00:00","updated_at":"2026-07-05T08:08:19.259189+00:00"}