{"id":"W4400434219","doi":"10.48550/arxiv.2407.03951","title":"Uncertainty-Guided Likelihood Tree Search","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; International Max Planck Research School for Advanced Methods in Process and Systems Engineering; Deutsche Forschungsgemeinschaft; International Max Planck Research School for Environmental, Cellular and Molecular Microbiology; Government of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Computer science; Language model; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002229891,0.001018197,0.001877323,0.001567819,0.0008895747,0.001432172,0.002163059,0.00214064,0.004784527],"category_scores_gemma":[0.01794821,0.0007507728,0.001123081,0.002372132,0.001191423,0.003161846,0.002283717,0.002481776,0.0013165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001281769,"about_ca_system_score_gemma":0.002749851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00561529,"about_ca_topic_score_gemma":0.007683051,"domain_scores_codex":[0.9985008,0.0006698814,0.00006202315,0.0003081217,0.0003209954,0.0001381096],"domain_scores_gemma":[0.9899776,0.008376352,0.0004435658,0.0004596917,0.0004965826,0.0002460826],"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":[0.0002225187,0.00008731111,0.002190593,0.0001947785,0.000082914,0.0001649613,0.0003135742,0.7883399,0.0011121,0.06638491,0.009192594,0.1317139],"study_design_scores_gemma":[0.00002402874,0.00001660124,0.00007848055,0.00001291922,0.000008101292,0.00002938141,0.0000161317,0.9640772,0.0002110815,0.03462287,0.0008955647,0.00000762496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01379039,0.000538467,0.9817499,0.0004555268,0.00003669188,0.0000690402,0.0002407553,0.000852734,0.002266585],"genre_scores_gemma":[0.4384409,0.0005038867,0.5552651,0.0004092085,0.00009895403,0.000393228,0.001194325,0.0005254835,0.00316887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00561529,"threshold_uncertainty_score":0.01600581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1085341178317484,"score_gpt":0.2191951407212647,"score_spread":0.1106610228895163,"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."}}