{"id":"W4409838812","doi":"10.1007/s10845-025-02614-4","title":"Gen-JEMA: enhanced explainability using generative joint embedding multimodal alignment for monitoring directed energy deposition","year":2025,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Embedding; Joint (building); Deposition (geology); Computer science; Energy (signal processing); Materials science; Artificial intelligence; Engineering; Geology; Structural engineering; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006132667,0.0002544544,0.0004120382,0.0003668236,0.0002873581,0.0002143536,0.0005199549,0.00009759189,0.0000043273],"category_scores_gemma":[0.0001183229,0.0002327085,0.000282948,0.0001297599,0.00002120948,0.0006068773,0.0002334522,0.000221658,4.48024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009857311,"about_ca_system_score_gemma":0.0001291965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005919893,"about_ca_topic_score_gemma":0.000004163744,"domain_scores_codex":[0.9976944,0.0001217428,0.00101622,0.0003976601,0.0003778854,0.0003920743],"domain_scores_gemma":[0.9984595,0.0001897154,0.0005485279,0.0003520281,0.0003318037,0.0001184798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009767917,0.0001594737,0.0001144155,0.0001566133,0.0003047574,0.00003295077,0.003421875,0.5430433,0.3239043,0.001433223,0.00002159436,0.1273098],"study_design_scores_gemma":[0.0002330609,0.00004537816,0.00008832328,0.0002501065,0.00002440959,0.00001772164,0.0002311597,0.3141116,0.6832851,0.00151695,0.00005953409,0.0001365975],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4079445,0.0002058525,0.5903298,0.00009115956,0.001227718,0.0001345616,5.317162e-7,0.00003835913,0.0000275303],"genre_scores_gemma":[0.7191401,0.00004561022,0.2804047,0.00004503672,0.0003039889,0.00001322831,4.942061e-7,0.00001011152,0.00003673397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3593808,"threshold_uncertainty_score":0.9489576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03275531907417412,"score_gpt":0.3040574270648438,"score_spread":0.2713021079906697,"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."}}