{"id":"W4403318073","doi":"10.1145/3672539.3686763","title":"ChainBuddy: An AI-assisted Agent System for Helping Users Set up LLM Pipelines","year":2024,"lang":"en","type":"article","venue":"","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Set (abstract data type); Pipeline transport; Human–computer interaction; Engineering; Programming language","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":[0.0001733045,0.0001478273,0.0001444895,0.0001252202,0.00006482493,0.0001891685,0.0000964959,0.00008353157,0.00004242383],"category_scores_gemma":[0.00001608793,0.0001333698,0.00007346235,0.0002177955,0.000007748927,0.0001469753,0.00001092324,0.00008202084,0.00004818726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008748588,"about_ca_system_score_gemma":0.00002095536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001355461,"about_ca_topic_score_gemma":0.00001251023,"domain_scores_codex":[0.9992333,0.00001265018,0.000223895,0.0002051388,0.0001095319,0.0002154689],"domain_scores_gemma":[0.9996127,0.00004690584,0.00001051854,0.0001688607,0.00005984774,0.00010111],"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":[0.00001041576,0.00001500445,0.00002548019,0.001373096,0.0001758977,0.00001646231,0.001365126,0.9681413,0.0009111741,0.002722866,0.008740081,0.01650307],"study_design_scores_gemma":[0.0001924336,0.00002113129,0.00001032243,0.0001442281,0.00002940237,0.00001250717,0.001370507,0.9911469,0.002026129,0.000007638368,0.004853449,0.0001853957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01110065,0.0006316882,0.9787452,0.0002495513,0.004408608,0.0002683733,0.00004222288,0.003744683,0.0008090552],"genre_scores_gemma":[0.9253845,0.00003055032,0.07025665,0.0001729753,0.0006863298,0.00009785254,0.0001773648,0.0001121632,0.003081573],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9142839,"threshold_uncertainty_score":0.5438663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03231939994994936,"score_gpt":0.2772012039319405,"score_spread":0.2448818039819911,"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."}}