{"id":"W4410768798","doi":"10.1016/j.foodchem.2025.144908","title":"Structure from motion-convolutional neural network model (SfM-CNN) achieved accurate portable Chinese dietary chemical composition estimation for dietary recall","year":2025,"lang":"en","type":"article","venue":"Food Chemistry","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Aurora College","funders":"National Key Research and Development Program of China","keywords":"Convolutional neural network; Composition (language); Recall; Computer science; Artificial intelligence; Pattern recognition (psychology); Cognitive psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001931128,0.0005338895,0.0003188617,0.0002607817,0.0001342796,0.0002066127,0.000389454,0.0004252979,0.001629366],"category_scores_gemma":[0.0004744021,0.0001941232,0.0002521745,0.0004107027,0.00009692741,0.0003701565,0.0003412399,0.0003735934,0.0006967185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003113535,"about_ca_system_score_gemma":0.0005499065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01279438,"about_ca_topic_score_gemma":0.02715636,"domain_scores_codex":[0.9998999,0.000007664848,0.000004057665,0.00004681066,0.00002846036,0.00001315913],"domain_scores_gemma":[0.9999208,0.00001616743,0.000008003718,0.00001117792,0.00003949333,0.000004389132],"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":[0.0006939045,0.0001455897,0.01507768,0.0003170487,0.0001293004,0.0002764649,0.00009288568,0.03972459,0.1877582,0.001676474,0.008016347,0.7460914],"study_design_scores_gemma":[0.00003485721,0.0001793759,0.01538572,0.00002633201,0.0001253411,0.000204925,0.0000406597,0.8884929,0.08511712,0.001253241,0.009083469,0.00005610455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3135966,0.003093338,0.6636273,0.0005147489,0.0006150453,0.0001035441,0.002646701,0.004525156,0.01127765],"genre_scores_gemma":[0.8509411,0.0008582855,0.1308444,0.0003682639,0.00007233298,0.00006356658,0.001825384,0.000126382,0.01490032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01279438,"threshold_uncertainty_score":0.0254398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01008698164404375,"score_gpt":0.2307860460686805,"score_spread":0.2206990644246368,"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."}}