{"id":"W6893539337","doi":"10.5281/zenodo.16875904","title":"Agentic and Non-Agentic Multi-Hop Systems for Medical Question Answering","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Task (project management); Pipeline (software); Question answering; Questions and answers; Joint (building); Semantics (computer science); Interrogative word","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":[0.005027283,0.0008877372,0.0008799285,0.001436427,0.0009886628,0.002928473,0.0032548,0.002258306,0.008285554],"category_scores_gemma":[0.01157579,0.0006381192,0.001140057,0.0009216255,0.0009904999,0.003928831,0.005184701,0.001942763,0.003496507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001211471,"about_ca_system_score_gemma":0.002017825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006256642,"about_ca_topic_score_gemma":0.008570307,"domain_scores_codex":[0.9968206,0.00140885,0.0002565209,0.0007390459,0.0006047189,0.000170241],"domain_scores_gemma":[0.9935854,0.003522525,0.0002653829,0.001502982,0.0007443409,0.0003793221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002873237,0.001431047,0.006603895,0.001800051,0.0007601011,0.001086026,0.002618028,0.1217948,0.0506629,0.0662488,0.07640118,0.6677199],"study_design_scores_gemma":[0.0001900464,0.0001504781,0.000625647,0.00003327366,0.00006418984,0.0001165774,0.0002376036,0.9254453,0.01702507,0.0273258,0.02873083,0.00005516828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02659341,0.0007563605,0.9168474,0.001673834,0.000195821,0.0006886756,0.001251716,0.04601718,0.005975682],"genre_scores_gemma":[0.2687865,0.0002524912,0.7175834,0.0007509224,0.0001194198,0.0005756232,0.003687493,0.001275873,0.006968413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008285554,"threshold_uncertainty_score":0.02771795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03086425441502821,"score_gpt":0.2675632992729495,"score_spread":0.2366990448579213,"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."}}