{"id":"W13883159","doi":"10.1142/9789812389701_0016","title":"HOW MANY TESTS ARE ENOUGH?","year":2002,"lang":"en","type":"book-chapter","venue":"World Scientific Publishing Company eBooks","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003220152,0.0009149954,0.0009445336,0.002331232,0.001264271,0.03955327,0.008068574,0.0004975409,0.0001437026],"category_scores_gemma":[0.0004980601,0.0009456638,0.0004395737,0.0005299185,0.0008374038,0.00527867,0.00191435,0.002038939,0.0004627309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005353147,"about_ca_system_score_gemma":0.0002582818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009246111,"about_ca_topic_score_gemma":0.0001400172,"domain_scores_codex":[0.9926491,0.0001862666,0.000928722,0.002528398,0.002536921,0.001170621],"domain_scores_gemma":[0.9919494,0.0002893767,0.001553717,0.004716543,0.0009377066,0.0005532582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002416281,0.00002625834,0.000009480501,0.00006540447,0.00003885105,0.00004816476,0.000427586,0.00000661445,0.00007657058,0.807387,0.1541292,0.03778243],"study_design_scores_gemma":[0.0002275883,0.00002242776,0.000131213,0.0004749436,0.0000318048,0.00004466351,0.00001380432,0.01111807,0.0002367135,0.04551715,0.9411874,0.0009942469],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001611918,0.0004898989,0.06570416,0.002565927,0.01120807,0.0007344064,0.00006359017,0.001288668,0.9179292],"genre_scores_gemma":[0.006902271,0.000002455004,0.1238883,0.0003510636,0.0006037232,0.00003929071,0.0000481227,0.0001037369,0.8680611],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7870582,"threshold_uncertainty_score":0.9992994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06748939186671869,"score_gpt":0.2548981382852846,"score_spread":0.1874087464185659,"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."}}