{"id":"W4414029501","doi":"10.1101/2025.08.31.672925","title":"What Large Language Models Know About Plant Molecular Biology","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Nautical Research Society","funders":"Agencia Nacional de Investigación y Desarrollo; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Computational biology; Biology; Computer science","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01115403,0.001717025,0.00123848,0.003874723,0.0008511324,0.005719197,0.001917364,0.002319354,0.004293998],"category_scores_gemma":[0.05267282,0.0008991067,0.002272551,0.002054695,0.001095275,0.01429762,0.001925538,0.003000404,0.004132482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001369125,"about_ca_system_score_gemma":0.002501098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006404461,"about_ca_topic_score_gemma":0.006517125,"domain_scores_codex":[0.9932932,0.004050031,0.0002731919,0.001388668,0.000799651,0.0001953152],"domain_scores_gemma":[0.945357,0.04524432,0.00147039,0.005022582,0.00213462,0.0007711764],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001123167,0.0007419834,0.1030829,0.006820089,0.002320215,0.000921347,0.008235279,0.1619786,0.01552744,0.04432332,0.09208877,0.5628369],"study_design_scores_gemma":[0.0001696854,0.0003000433,0.02639661,0.002342314,0.0008508555,0.0009653586,0.002861574,0.5768815,0.009458913,0.2189248,0.1605919,0.000256496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.280866,0.04006235,0.5259212,0.04097718,0.0008146281,0.0003803446,0.06439184,0.01284209,0.03374449],"genre_scores_gemma":[0.7521477,0.01219729,0.1461745,0.004028287,0.0008220412,0.000619246,0.07896833,0.001479674,0.003563063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9888459,"threshold_uncertainty_score":0.05898893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01264021789775562,"score_gpt":0.2425267328226745,"score_spread":0.2298865149249189,"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."}}