{"id":"W4393831576","doi":"10.5281/zenodo.6459608","title":"Artifact for \"Identifying Concepts in Software Projects\"","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Engineering Education and Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Artifact (error); Software; Computer science; Software engineering; Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.002124691,0.002118365,0.001163483,0.00474816,0.001079121,0.002861658,0.002528408,0.002422649,0.05589785],"category_scores_gemma":[0.01154766,0.0006589156,0.001439432,0.005879221,0.0005794783,0.001422186,0.00323309,0.002133206,0.07359712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001609912,"about_ca_system_score_gemma":0.003218445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01403239,"about_ca_topic_score_gemma":0.02582555,"domain_scores_codex":[0.9974802,0.0005960871,0.0003635855,0.0006255208,0.0005925763,0.000342101],"domain_scores_gemma":[0.9933797,0.002368372,0.0006844103,0.001833765,0.001199212,0.0005344108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007383049,0.00004326901,0.001124523,0.0007557272,0.00003018426,0.00002687659,0.00004244632,0.0002147233,0.0001436766,0.0006931775,0.9938923,0.002959314],"study_design_scores_gemma":[0.0003201335,0.00002634601,0.006823542,0.000333077,0.00003575026,0.00008658617,0.0001199668,0.0005534593,0.0004199989,0.001838564,0.9894113,0.0000313066],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002284537,0.00004521479,0.0002069925,0.00007514474,0.00004399927,0.0000234642,0.9982843,0.0003887185,0.0007037051],"genre_scores_gemma":[0.0004358098,0.0000272602,0.0004554965,0.0000436719,0.000008321163,0.0001173013,0.9984176,0.00005838693,0.0004361935],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05589785,"threshold_uncertainty_score":0.186997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05955262109185731,"score_gpt":0.3021419267577753,"score_spread":0.242589305665918,"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."}}