{"id":"W4386365732","doi":"10.18293/seke2023-176","title":"An Optimal Spacing Approach for Sampling Small-sized Datasets","year":2023,"lang":"en","type":"article","venue":"Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Ranking (information retrieval); Deep learning; Context (archaeology); Focus (optics); Sampling (signal processing); Data mining","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":[0.02567479,0.0009990537,0.002099865,0.003130507,0.001054082,0.001747257,0.003265017,0.002206774,0.00211873],"category_scores_gemma":[0.07209156,0.000727026,0.001696893,0.002958329,0.00184937,0.003130296,0.002873125,0.003320161,0.000456299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001565555,"about_ca_system_score_gemma":0.002156913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177418,"about_ca_topic_score_gemma":0.002201914,"domain_scores_codex":[0.9861173,0.008051855,0.0009261394,0.002576192,0.001901297,0.0004272219],"domain_scores_gemma":[0.9448414,0.04206231,0.003151284,0.005673201,0.003431104,0.0008407307],"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":[0.001281494,0.001008163,0.02721422,0.0006541341,0.0005266688,0.0004549967,0.0008616892,0.5734856,0.004268954,0.06218466,0.007037385,0.3210221],"study_design_scores_gemma":[0.0001044467,0.0002913795,0.002009116,0.00007148771,0.00003670594,0.0000809374,0.0001352377,0.9529084,0.001387421,0.04167972,0.001271284,0.00002377711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03198603,0.0003388562,0.9653214,0.000319616,0.00006105717,0.0003053887,0.000238159,0.0005484567,0.0008810061],"genre_scores_gemma":[0.4929792,0.000280149,0.5015936,0.0004257137,0.0001523486,0.001355094,0.001900087,0.0001492745,0.001164572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02567479,"threshold_uncertainty_score":0.1357829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05236607085311087,"score_gpt":0.2927527985220892,"score_spread":0.2403867276689784,"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."}}