{"id":"W2186589424","doi":"10.5281/zenodo.2544203","title":"CGO/PPoPP'17 Artifact Evaluation Discussion (enabling open and reproducible research)","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Data science; Computer science; Psychology","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","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.05008049,0.0002618112,0.0004367462,0.001002994,0.001834519,0.005123936,0.006106867,0.0001895558,0.0005786573],"category_scores_gemma":[0.0103039,0.0001907032,0.0001290521,0.0009573839,0.0004216871,0.001185238,0.02417337,0.0007093716,0.0004906384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002410415,"about_ca_system_score_gemma":0.0003907736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000953587,"about_ca_topic_score_gemma":0.0003209351,"domain_scores_codex":[0.9920974,0.001322569,0.0004931975,0.004251538,0.001319362,0.0005159134],"domain_scores_gemma":[0.9896008,0.000601226,0.0006709029,0.007679947,0.00117157,0.0002755925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000453651,0.0004932897,0.02720768,0.0001108652,0.0002015109,0.0003460279,0.002077128,0.2095097,0.000114027,0.03010671,0.3928234,0.336556],"study_design_scores_gemma":[0.0006942091,0.00005809777,0.01377,0.0003052512,0.0000954045,0.000002475566,0.002105293,0.4664071,0.00006915994,0.455733,0.06029897,0.0004610731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8906447,0.0002342509,0.01785849,0.003127413,0.003500832,0.002775592,0.00008353826,0.0001452694,0.0816299],"genre_scores_gemma":[0.935385,0.00008037475,0.0002336412,0.00002617086,0.0001390446,0.000002418102,0.00006769204,0.00001488744,0.06405076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4256263,"threshold_uncertainty_score":0.9994649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7599273315730504,"score_gpt":0.4351556437469113,"score_spread":0.3247716878261391,"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."}}