{"id":"W6962820809","doi":"10.17632/tyrwtcycgk","title":"Transferring visual knowledge in large-scale CNNs facilitates interpretable and cost-effective wetland cover mapping under dynamic environments","year":2025,"lang":"en","type":"dataset","venue":"Mendeley Data","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Cover (algebra); Convolutional neural network; Code (set theory); Feature (linguistics); Land cover; Pattern recognition (psychology)","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":[0.001531557,0.001081607,0.001329914,0.0009542058,0.0002238815,0.0002215044,0.001857671,0.000601372,0.0003580363],"category_scores_gemma":[0.0001185166,0.001152803,0.00009756039,0.0005850337,0.0002404376,0.001009306,0.003411074,0.001473445,0.0007747878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001138632,"about_ca_system_score_gemma":0.0001757976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004823192,"about_ca_topic_score_gemma":0.008613942,"domain_scores_codex":[0.994168,0.0007376805,0.0009019511,0.002423679,0.0005134555,0.001255164],"domain_scores_gemma":[0.9963949,0.0006366411,0.000182499,0.002530702,0.0000241981,0.0002310478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002777944,0.00100961,0.0004549456,0.001084452,0.0007071045,0.00005061996,0.0007668922,0.0001698024,0.001245457,0.000001653782,0.992309,0.001922705],"study_design_scores_gemma":[0.003324,0.000096297,0.001206866,0.001447211,0.0003310176,0.00001370451,0.001124611,0.02483431,0.00004800341,0.00002395772,0.9665156,0.001034433],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002465074,0.002529525,0.003704405,0.00002164458,0.0003602911,0.003583918,0.9870673,0.00007406428,0.0001937657],"genre_scores_gemma":[0.006928088,0.001374741,0.0000818371,0.00007565023,0.00004018543,0.0006369051,0.9899974,0.00009399791,0.0007711911],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02579337,"threshold_uncertainty_score":0.9990922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02251189093538717,"score_gpt":0.3175538184389053,"score_spread":0.2950419275035181,"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."}}