{"id":"W7138443373","doi":"10.18653/v1/2025.wasp-main.17","title":"“Clutch or Cry” Team at TRACS @ WASP2025: A Hybrid Stacking Ensemble for Astrophysical Document Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Astronomy and Astrophysical Research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Stacking; Identification (biology); Field (mathematics); Work (physics)","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":[0.002823591,0.002071619,0.001449349,0.003966173,0.001201,0.001804087,0.002193805,0.001398104,0.00384715],"category_scores_gemma":[0.004571173,0.0004964037,0.001581668,0.002404095,0.0003058658,0.003297515,0.002857162,0.001902248,0.007324002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008473041,"about_ca_system_score_gemma":0.001833795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008715173,"about_ca_topic_score_gemma":0.01517882,"domain_scores_codex":[0.9980982,0.0002535152,0.0001349826,0.0007286068,0.0005912489,0.0001935101],"domain_scores_gemma":[0.9976909,0.0004302525,0.0001143596,0.000686252,0.0008048097,0.0002733924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005178729,0.0005527125,0.008076333,0.0002642136,0.0003878045,0.0001895564,0.0002825315,0.00808064,0.02624876,0.001057349,0.09179166,0.8625505],"study_design_scores_gemma":[0.0001846946,0.0010084,0.01392685,0.0001221572,0.000565782,0.0006061078,0.0005629571,0.7782955,0.07933695,0.01052412,0.1146722,0.000194381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1106534,0.003215402,0.6683393,0.001065476,0.001328954,0.001095128,0.02208438,0.1836107,0.008607357],"genre_scores_gemma":[0.2174066,0.0007446231,0.6768976,0.0007278077,0.0004754121,0.00072668,0.08297642,0.002943303,0.01710146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008715173,"threshold_uncertainty_score":0.01732892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02695021573628087,"score_gpt":0.3339908340063135,"score_spread":0.3070406182700327,"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."}}