{"id":"W4391506236","doi":"10.48550/arxiv.2402.00699","title":"PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Argonne National Laboratory; Purdue University; Cisco Systems; U.S. Department of Energy; Office of Science; National Science Foundation","keywords":"Open source; Open source software; Computer science; Software; Artificial intelligence; Statistics; Data mining; Machine learning; Mathematics; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.003520726,0.0002513738,0.000706271,0.001747554,0.00009621973,0.0008353344,0.003321351,0.0001452517,0.000148869],"category_scores_gemma":[0.0006205053,0.0002372419,0.0001922887,0.004467106,0.0002229554,0.0003895906,0.01751574,0.000368385,0.00002979531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000785172,"about_ca_system_score_gemma":0.0001565582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001898541,"about_ca_topic_score_gemma":0.001422474,"domain_scores_codex":[0.9963039,0.0002928204,0.0005922964,0.002165553,0.0003823414,0.0002631058],"domain_scores_gemma":[0.9962453,0.0007461202,0.0003547211,0.002365529,0.0001523464,0.0001360308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001076221,0.0001124576,0.0033049,0.00005258798,0.0004874549,0.000195823,0.000852103,0.9750289,9.55528e-7,0.005994327,0.009007243,0.004855596],"study_design_scores_gemma":[0.0003328551,0.00002242647,0.003512189,0.00009320052,0.0007326933,7.281007e-7,0.0007811001,0.9029481,0.000001814754,0.0897942,0.001533799,0.000246931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7871089,0.00009464155,0.2047785,0.00007364264,0.0004135282,0.0004376074,0.005722175,0.00006653027,0.00130447],"genre_scores_gemma":[0.9957182,0.00002351919,0.0007695333,0.00004598008,0.00001873081,9.075755e-7,0.001185996,0.00001079496,0.00222632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2086093,"threshold_uncertainty_score":0.9904304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2667119319386875,"score_gpt":0.3215716429832131,"score_spread":0.05485971104452553,"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."}}