{"id":"W4242845477","doi":"10.1145/2088883.2088889","title":"Report from the 2nd international workshop on replication in empirical software engineering research (RESER 2011)","year":2012,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Replication (statistics); Session (web analytics); Computer science; Empirical research; Joint (building); Software; Software engineering; Engineering; World Wide Web; Civil engineering; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00366399,0.0004947847,0.0003939345,0.0007560006,0.0001872286,0.000360427,0.004274116,0.0003508907,0.0001101983],"category_scores_gemma":[0.5348583,0.0004404036,0.0001618598,0.001483185,0.00007007291,0.001078123,0.001871145,0.001961102,0.0003338459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006101881,"about_ca_system_score_gemma":0.000139469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001828487,"about_ca_topic_score_gemma":0.000009503401,"domain_scores_codex":[0.9945462,0.0001403602,0.0007330946,0.001240892,0.001848555,0.001490854],"domain_scores_gemma":[0.744252,0.2484881,0.0001522711,0.006082787,0.0004909359,0.000533887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001755271,0.0001398524,0.9764401,0.00002733948,0.00005813495,0.0001122429,0.0008529937,0.009253729,0.0004313933,0.0002082064,0.006606255,0.005852241],"study_design_scores_gemma":[0.0003441304,0.00003422081,0.9720321,0.000271731,0.000006074904,0.00007438198,0.00001562265,0.002708777,0.002162196,0.00004590112,0.02176098,0.000543902],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7461711,0.002004772,0.2403214,0.004855268,0.003243658,0.0008359937,0.00003528378,0.002525113,0.000007481651],"genre_scores_gemma":[0.907001,0.00004610805,0.09099078,0.0001593572,0.001129195,0.0003303138,0.00009543506,0.0001237612,0.0001240114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5311943,"threshold_uncertainty_score":0.9998048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08854124489477622,"score_gpt":0.3640275285554867,"score_spread":0.2754862836607105,"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."}}