{"id":"W4415678236","doi":"10.1088/2632-2153/ae1927","title":"MatMMFuse: Multimodal fusion model for material property prediction","year":2025,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Embedding; Graph; Convolution (computer science); Encoder; Encoding (memory); Property (philosophy); ENCODE; Data modeling","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002254108,0.000241568,0.0002991847,0.0007368891,0.001360251,0.0003676598,0.0008919798,0.0001962516,0.0001192545],"category_scores_gemma":[0.002060004,0.0001702886,0.000026996,0.001202359,0.00124427,0.0004653879,0.0006484141,0.0002982325,0.00002770562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043113,"about_ca_system_score_gemma":0.0004908321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000234381,"about_ca_topic_score_gemma":0.00002273133,"domain_scores_codex":[0.9975158,0.00005754685,0.0003754437,0.0009465907,0.0004385721,0.0006660458],"domain_scores_gemma":[0.9989639,0.00005878482,0.0001642039,0.0003993032,0.000308579,0.0001052396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007131928,0.00002987034,0.004528524,0.00004463012,0.000001882113,0.000001008134,0.0001284882,0.006812014,0.9699817,0.006013269,0.0003323225,0.01205502],"study_design_scores_gemma":[0.0005585529,0.0001969319,0.000545208,0.0000455577,0.00001453232,0.00001783994,0.00003832769,0.8460717,0.1417869,0.005250948,0.005284266,0.0001892898],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9110839,0.00006762788,0.07945805,0.005733051,0.001111261,0.000695316,0.00003084004,0.001066818,0.0007531705],"genre_scores_gemma":[0.9482461,0.00001578961,0.04583799,0.0001869333,0.00006947519,0.00009270236,0.00000963292,0.00001862859,0.005522734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8392596,"threshold_uncertainty_score":0.9999399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007586592448563075,"score_gpt":0.2597565640646196,"score_spread":0.2521699716160565,"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."}}