{"id":"W1746353556","doi":"10.1007/978-1-84800-044-5_8","title":"Reporting Experiments in Software Engineering","year":2007,"lang":"en","type":"book-chapter","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":330,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Guideline; Computer science; Presentation (obstetrics); Unification; Set (abstract data type); Software; Empirical research; Data science; Management science; Software engineering; Engineering; Medicine; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0391929,0.001660524,0.002059753,0.004862311,0.001019897,0.006030326,0.003942413,0.00340172,0.02409067],"category_scores_gemma":[0.1733205,0.001053162,0.0007654287,0.004795691,0.003941712,0.01059646,0.003073802,0.003187699,0.01385964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001655233,"about_ca_system_score_gemma":0.002478447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008099793,"about_ca_topic_score_gemma":0.000902592,"domain_scores_codex":[0.926603,0.04721575,0.00504401,0.003324637,0.01709896,0.0007136324],"domain_scores_gemma":[0.7019569,0.2331637,0.009568486,0.03876458,0.01501767,0.00152868],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001726297,0.0001455088,0.001699872,0.001387659,0.00007811672,0.00008506615,0.000945505,0.001405214,0.002675802,0.09947188,0.1458734,0.7460594],"study_design_scores_gemma":[0.0001280572,0.0004605194,0.003915942,0.002721532,0.0001947133,0.00101375,0.001182843,0.02127011,0.02760213,0.53961,0.4016933,0.000207147],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005454993,0.016645,0.8355861,0.01275939,0.002912847,0.0005940109,0.002313529,0.01560326,0.1081308],"genre_scores_gemma":[0.1058136,0.01293623,0.7719833,0.00689076,0.004054505,0.001694252,0.005049093,0.003669718,0.08790852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9608071,"threshold_uncertainty_score":0.2072743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06714879045561481,"score_gpt":0.3130913835188216,"score_spread":0.2459425930632068,"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."}}