{"id":"W4409767946","doi":"10.1145/3706598.3714085","title":"ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines","year":2025,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pipeline transport; Computer science; Petroleum engineering; Engineering; Mechanical engineering","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":[0.0002815936,0.0001102572,0.000172454,0.0000868432,0.000190446,0.0002363811,0.000589592,0.0000552442,0.000002397774],"category_scores_gemma":[0.00006385333,0.00008346463,0.0000616811,0.0002087392,0.00001551947,0.0002074622,0.0001369018,0.0000385585,0.000005945832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003633388,"about_ca_system_score_gemma":0.00007782394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008519913,"about_ca_topic_score_gemma":0.0001410785,"domain_scores_codex":[0.9990497,0.0000418864,0.0002378936,0.0003371961,0.0001038954,0.000229415],"domain_scores_gemma":[0.9992238,0.0001022949,0.000045726,0.0004616785,0.0001236193,0.00004285312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001004787,0.0001378224,0.0009779696,0.0002729405,0.00005852168,0.00001660523,0.0004219644,0.000552413,0.009467072,0.7640514,0.01435113,0.2096821],"study_design_scores_gemma":[0.0003993438,0.00008123446,0.001339767,0.00006063142,0.00001408803,0.000009761397,0.0005815434,0.9782079,0.01370457,0.0006692661,0.004757555,0.000174272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01595759,0.0001767702,0.9764453,0.002187417,0.001167138,0.0002237354,0.000001042145,0.0005940016,0.003247037],"genre_scores_gemma":[0.8017992,0.000001965485,0.1933708,0.001652537,0.0001360714,0.00005687423,0.000003346187,0.00000458048,0.002974599],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776555,"threshold_uncertainty_score":0.3403589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0344029826865024,"score_gpt":0.3051566207078752,"score_spread":0.2707536380213729,"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."}}