{"id":"W2026316743","doi":"10.1145/1295074.1295082","title":"Toward a text classification system for the quality assessment of software requirements written in natural language","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software engineering; Documentation; Artifact (error); Natural language; Quality (philosophy); Process (computing); Software quality; Software requirements; Software requirements specification; Requirements engineering; Requirements elicitation; Software; Natural language processing; Artificial intelligence; Software development; Software design; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00280982,0.00007938452,0.0001286038,0.0001170433,0.00003791877,0.00004815748,0.0007749234,0.00004208259,0.000002601081],"category_scores_gemma":[0.0005738332,0.00005461576,0.00004994288,0.0003926888,0.00002313044,0.0001758406,0.0001421364,0.0001281465,0.000002534143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002652341,"about_ca_system_score_gemma":0.00006972011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000197241,"about_ca_topic_score_gemma":0.00005109374,"domain_scores_codex":[0.9986376,0.0000497154,0.0003427272,0.0002290489,0.0004793941,0.0002615722],"domain_scores_gemma":[0.9973134,0.001912688,0.00007708926,0.0005304642,0.0001294604,0.00003687452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007702532,0.0003776198,0.3529821,0.00193689,0.0001598061,0.00002360099,0.006539657,0.0005081979,0.03088912,0.2109848,0.000963985,0.3945572],"study_design_scores_gemma":[0.0004837522,0.00003525658,0.9424737,0.00005563733,0.000002636626,0.000002811074,0.001520681,0.05226202,0.002936917,0.00003161222,0.00008379436,0.0001111775],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06958312,0.0001329558,0.928937,0.0002950499,0.0002507223,0.0004637302,0.000002402209,0.0001646,0.0001703788],"genre_scores_gemma":[0.9203957,0.000001070741,0.07938263,0.00002495794,0.00002672265,0.00004832471,0.000003034864,0.000006144829,0.0001113707],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8508126,"threshold_uncertainty_score":0.2227166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09265065982244883,"score_gpt":0.3974940928867056,"score_spread":0.3048434330642568,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}