{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003732774,0.001599015,0.0007383589,0.001054465,0.0009266275,0.001998428,0.002623127,0.001400402,0.03325048],"category_scores_gemma":[0.01208775,0.0009368262,0.0005963189,0.0004469531,0.0007749526,0.004625477,0.003293762,0.002358965,0.007515164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001152862,"about_ca_system_score_gemma":0.002417927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006508921,"about_ca_topic_score_gemma":0.01149259,"domain_scores_codex":[0.9986596,0.000591621,0.000101614,0.0002111546,0.0003444838,0.00009143454],"domain_scores_gemma":[0.9950295,0.003256528,0.0001807379,0.0005577562,0.0006777488,0.0002976765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003747887,0.001168707,0.004632782,0.001478689,0.0002682395,0.0006024441,0.002691718,0.07240403,0.03144506,0.04591242,0.3225444,0.5131036],"study_design_scores_gemma":[0.0005154973,0.0004136919,0.0006304402,0.0001355601,0.00007289799,0.0001625006,0.0003075076,0.7542049,0.02421844,0.02512565,0.1940888,0.0001241073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02181103,0.0004222222,0.6669679,0.001001713,0.0002739977,0.0007560925,0.002343055,0.2848031,0.02162091],"genre_scores_gemma":[0.1861992,0.000536661,0.7574489,0.0007614819,0.00007827712,0.001225214,0.006088835,0.02424967,0.02341188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03325048,"threshold_uncertainty_score":0.1112339,"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."}}