{"id":"W4415870502","doi":"10.1007/s11036-025-02479-0","title":"Seeds Image – Introduction and Baseline Experiments with the New Labeled Benchmark for Machine Learning Tasks","year":2025,"lang":"en","type":"article","venue":"Mobile Networks and Applications","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Set (abstract data type); Data set; Baseline (sea); Image (mathematics); Artificial neural network; Object (grammar); Pattern recognition (psychology); Deep learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001076052,0.00008544546,0.00008457855,0.000004541937,0.0004710053,0.00007392553,0.00006280057,0.0000396433,0.00003479789],"category_scores_gemma":[0.000003804179,0.00002606877,0.0000190886,0.0002374882,0.00004274115,0.00004305481,0.00003337214,0.00008602721,5.686762e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004599937,"about_ca_system_score_gemma":0.000002972491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005609219,"about_ca_topic_score_gemma":0.0001606667,"domain_scores_codex":[0.9995351,0.00001996244,0.00008197282,0.0002060915,0.00003903454,0.0001178819],"domain_scores_gemma":[0.9997153,0.0001300272,0.0000370946,0.00004005205,0.0000368532,0.00004073264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001370953,0.0002328879,0.007087212,0.00002203938,0.0001095327,2.756092e-7,0.0001230615,0.003877384,0.1345979,0.005356246,0.2113544,0.637102],"study_design_scores_gemma":[0.0001972445,0.0001180212,0.004726574,0.000006813686,0.00003433414,0.000001948274,0.0002835488,0.003304311,0.0006018198,0.0001159584,0.9905186,0.0000907698],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8161863,0.01984747,0.0809344,0.07363311,0.0002314731,0.007136612,0.00007945597,0.0003317571,0.001619409],"genre_scores_gemma":[0.9912092,0.0004404639,0.0002729142,0.0005714086,0.001812448,0.001340641,0.0004364457,0.00000133464,0.003915142],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7791643,"threshold_uncertainty_score":0.3622639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004022319303019252,"score_gpt":0.2121795176663746,"score_spread":0.2081571983633553,"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."}}