{"id":"W4401409197","doi":"10.1145/3674912.3674914","title":"HPC Jobs Classification and Resource Prediction to Minimize Job Failures","year":2024,"lang":"en","type":"article","venue":"","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Resource (disambiguation); Machine learning; Reliability engineering; Artificial intelligence; Engineering; Computer network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000285868,0.00009095843,0.00008715985,0.0001011621,0.00008550002,0.0007707146,0.0002925504,0.00005121935,0.000008385587],"category_scores_gemma":[0.00002526377,0.00007578563,0.00002837676,0.0003718263,0.00001444808,0.0002485407,0.0001169235,0.00007512527,0.0001186706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002468473,"about_ca_system_score_gemma":0.00002731154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003630721,"about_ca_topic_score_gemma":0.000004076114,"domain_scores_codex":[0.9990345,0.00005465278,0.0001809352,0.0003924411,0.0001813072,0.000156165],"domain_scores_gemma":[0.99946,0.0000960433,0.00001884239,0.0002920285,0.00003150325,0.0001015664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001131338,0.00003275073,0.005164663,0.0001419099,0.00005339956,0.00002081189,0.002969441,0.0009308349,0.002789321,0.54823,0.3815159,0.05813961],"study_design_scores_gemma":[0.00009600937,0.0000546992,0.03561025,0.00009154445,0.000005321708,0.00003721188,0.0001220573,0.3884271,0.00008814673,0.0005513229,0.5747786,0.000137749],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009953381,0.0002635644,0.963308,0.006156248,0.0005291956,0.0001468185,0.000007657683,0.0007488249,0.01888632],"genre_scores_gemma":[0.9841437,0.000003699867,0.01173286,0.0001725353,0.0001861668,0.00001318488,0.000008399041,0.000006195593,0.003733298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9741903,"threshold_uncertainty_score":0.7432019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02012244072311738,"score_gpt":0.2481325971765381,"score_spread":0.2280101564534207,"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."}}