{"id":"W2056488032","doi":"10.1145/1391984.1391985","title":"Unit-level test adequacy criteria for visual dataflow languages and a testing methodology","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Dataflow; Context (archaeology); Unit testing; Visual programming language; Empirical research; Software engineering; Programming language; Software","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001389497,0.0002790582,0.00043149,0.0003456153,0.0003306694,0.00004497692,0.0004408362,0.0002002918,0.00000319793],"category_scores_gemma":[0.02163374,0.0002790802,0.00005670954,0.0003642591,0.0001129384,0.0002116091,0.00005969472,0.0003249873,0.000001302852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001775438,"about_ca_system_score_gemma":0.00005596422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001040593,"about_ca_topic_score_gemma":0.000003202286,"domain_scores_codex":[0.9983016,0.0002996254,0.0002859674,0.0005947637,0.0001002221,0.0004178481],"domain_scores_gemma":[0.9676278,0.03147611,0.00007014266,0.0005655641,0.0001147325,0.0001456635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006858348,0.0002459822,0.004847866,0.0003812986,0.0001450411,0.0001097678,0.002743813,0.001295612,0.01026787,0.0008979223,0.000571897,0.9784244],"study_design_scores_gemma":[0.01043469,0.01488964,0.1200833,0.001556643,0.000845295,0.02888515,0.0004930165,0.607833,0.1213767,0.07241214,0.01319636,0.007994033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01587246,0.0003192727,0.9784707,0.0001978415,0.0002826361,0.0001928241,0.0000373943,0.004624269,0.000002568135],"genre_scores_gemma":[0.07256598,0.00006208932,0.9268639,0.0002353064,0.0000650708,0.0001087564,0.000007245993,0.0000357654,0.00005589013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9704303,"threshold_uncertainty_score":0.9999661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3232977272659157,"score_gpt":0.4163952044641103,"score_spread":0.09309747719819456,"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."}}