{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PRM5UAJSC7RPQTAFIYTI3TARBA","short_pith_number":"pith:PRM5UAJS","schema_version":"1.0","canonical_sha256":"7c59da013217e2f84c0546268dcc11080087cfb42a25289607c902d2d3655d23","source":{"kind":"arxiv","id":"2501.06491","version":3},"attestation_state":"computed","paper":{"title":"Improving Requirements Classification with SMOTE-Tomek Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.SE","authors_text":"Barak Or","submitted_at":"2025-01-11T09:36:14Z","abstract_excerpt":"This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold cross-validation, to address class imbalance in the PROMISE dataset. This dataset comprises 969 categorized requirements, classified into functional and non-functional types. The proposed approach enhances the representation of minority classes while maintaining the integrity of validation folds, leading to a notable improvement in classification accuracy. Logistic regression achieved 76.16\\%, significantly surpassing the baseline of 58.31\\%. These r"},"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":"2501.06491","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-11T09:36:14Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"051a62c1cd71a415b146765af061076f6494d6884bf151b4cea0af30389caf42","abstract_canon_sha256":"4e03d0c411b98ca6fb878ecb384f38f59289f1cbd9ac435306797b92d0c2b2f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:26.163509Z","signature_b64":"A3cioUhNqDDlnVUZGn83RWh2dO2y908bAqjPZfGfPKVbdKlTVKCvd6cgixFH00Rar0G8f1T4l3Z3zqTYE8F2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c59da013217e2f84c0546268dcc11080087cfb42a25289607c902d2d3655d23","last_reissued_at":"2026-05-28T01:04:26.162924Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:26.162924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Requirements Classification with SMOTE-Tomek Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.SE","authors_text":"Barak Or","submitted_at":"2025-01-11T09:36:14Z","abstract_excerpt":"This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold cross-validation, to address class imbalance in the PROMISE dataset. This dataset comprises 969 categorized requirements, classified into functional and non-functional types. The proposed approach enhances the representation of minority classes while maintaining the integrity of validation folds, leading to a notable improvement in classification accuracy. Logistic regression achieved 76.16\\%, significantly surpassing the baseline of 58.31\\%. These r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06491","kind":"arxiv","version":3},"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/2501.06491/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":"2501.06491","created_at":"2026-05-28T01:04:26.163000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06491v3","created_at":"2026-05-28T01:04:26.163000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06491","created_at":"2026-05-28T01:04:26.163000+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRM5UAJSC7RP","created_at":"2026-05-28T01:04:26.163000+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRM5UAJSC7RPQTAF","created_at":"2026-05-28T01:04:26.163000+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRM5UAJS","created_at":"2026-05-28T01:04:26.163000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA","json":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA.json","graph_json":"https://pith.science/api/pith-number/PRM5UAJSC7RPQTAFIYTI3TARBA/graph.json","events_json":"https://pith.science/api/pith-number/PRM5UAJSC7RPQTAFIYTI3TARBA/events.json","paper":"https://pith.science/paper/PRM5UAJS"},"agent_actions":{"view_html":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA","download_json":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA.json","view_paper":"https://pith.science/paper/PRM5UAJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06491&json=true","fetch_graph":"https://pith.science/api/pith-number/PRM5UAJSC7RPQTAFIYTI3TARBA/graph.json","fetch_events":"https://pith.science/api/pith-number/PRM5UAJSC7RPQTAFIYTI3TARBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA/action/storage_attestation","attest_author":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA/action/author_attestation","sign_citation":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA/action/citation_signature","submit_replication":"https://pith.science/pith/PRM5UAJSC7RPQTAFIYTI3TARBA/action/replication_record"}},"created_at":"2026-05-28T01:04:26.163000+00:00","updated_at":"2026-05-28T01:04:26.163000+00:00"}