{"id":"W6947768563","doi":"10.48448/fe2c-3r68","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Interpretability; Decomposition; Distillation; Artificial neural network; Analytics; Empirical modelling","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006191123,0.0002998743,0.00026594,0.0001818684,0.0001781109,0.0001227051,0.0004025562,0.0001984222,0.01186611],"category_scores_gemma":[0.0001336606,0.0002711249,0.00007524349,0.001273576,0.001484425,0.0002583293,0.0001933955,0.000230672,0.001940717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008977554,"about_ca_system_score_gemma":0.0001308349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003481181,"about_ca_topic_score_gemma":0.0007764886,"domain_scores_codex":[0.9977021,0.00006635191,0.0004114631,0.0007394438,0.0006895732,0.0003910603],"domain_scores_gemma":[0.9990692,0.00003562903,0.0003749136,0.0003461173,0.00004241896,0.0001316997],"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":[0.00004043732,0.001701123,0.008528472,0.002637794,0.00008346295,0.00002368315,0.002894383,0.001069195,0.1293063,0.09673578,0.7092194,0.04776],"study_design_scores_gemma":[0.001051756,0.0004639936,0.007532168,0.002999827,0.0002497449,0.00002920049,0.001088509,0.07226034,0.02507851,0.00560775,0.881745,0.001893239],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01004701,0.0008448507,0.007120276,0.0006954529,0.001097889,0.001043113,0.0002165708,0.0006510695,0.9782838],"genre_scores_gemma":[0.7873642,0.000105702,0.04613179,0.0002722251,0.0007864151,0.0002089024,0.001338909,0.0007121485,0.1630797],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8152041,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04094282590825347,"score_gpt":0.3452855641476843,"score_spread":0.3043427382394308,"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."}}