{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008132945,0.0006936711,0.0007593901,0.0004805513,0.0001662167,0.0008214488,0.002923307,0.0008178277,0.00001486193],"category_scores_gemma":[0.00009802398,0.0007492984,0.0002472848,0.0005411276,0.00006466625,0.0007086182,0.00321317,0.001046881,0.00004941555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002450729,"about_ca_system_score_gemma":0.0008544424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007839972,"about_ca_topic_score_gemma":0.000005174474,"domain_scores_codex":[0.995796,0.000264499,0.0006721034,0.001885462,0.0003887114,0.0009932645],"domain_scores_gemma":[0.9955018,0.00008636212,0.0003576487,0.003441246,0.0003318276,0.0002811357],"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":[0.00001833418,0.0003519072,0.0005517407,0.0009457083,0.0004783726,0.0006272517,0.0003175136,0.005982781,0.2313062,0.7588186,0.0004865941,0.0001150492],"study_design_scores_gemma":[0.001493713,0.00007503456,0.0006987569,0.003548968,0.0001663351,1.030616e-7,0.00002276126,0.7746813,0.1984769,0.0008630718,0.0169023,0.003070735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05956398,0.01666008,0.916643,0.000555799,0.004493606,0.0006658404,0.0003339519,0.001023585,0.00006010665],"genre_scores_gemma":[0.9152592,0.001576125,0.08109097,0.001384556,0.0003481667,0.00023154,0.000001377559,0.00007276402,0.00003527686],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8556952,"threshold_uncertainty_score":0.9994958,"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."}}