{"id":"W4407158731","doi":"10.1016/j.addma.2025.104692","title":"Audio-visual cross-modality knowledge transfer for machine learning-based in-situ monitoring in laser additive manufacturing","year":2025,"lang":"en","type":"article","venue":"Additive manufacturing","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"National Research Council Canada; Mitacs; Agency for Science, Technology and Research; McGill University","keywords":"Materials science; In situ; Audio visual; Modality (human–computer interaction); Transfer of learning; Knowledge transfer; Laser; Engineering drawing; Artificial intelligence; Optics; Computer science; Knowledge management; Multimedia; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004275148,0.0005510795,0.0005795413,0.0008073381,0.0001843311,0.00009573823,0.0003000991,0.0002981797,0.00009769538],"category_scores_gemma":[0.00005879954,0.0006086074,0.0002658337,0.0002782733,0.0001130697,0.0002905689,0.00005949622,0.0009690021,0.000004857352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004003213,"about_ca_system_score_gemma":0.00004586205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001298954,"about_ca_topic_score_gemma":0.0005100074,"domain_scores_codex":[0.9977227,0.0001169756,0.0005816429,0.0006072155,0.0001696085,0.0008018017],"domain_scores_gemma":[0.9986414,0.0009092781,0.00004432872,0.0002523488,0.00004838821,0.0001042363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003081132,0.001800169,0.03748107,0.005406195,0.00144821,0.0004756791,0.008260726,0.3700771,0.06206953,0.0005873393,0.0006091822,0.5087036],"study_design_scores_gemma":[0.001541591,0.00007040623,0.1228136,0.0005511426,0.00003179072,0.000001156004,0.0001221588,0.004034518,0.8667919,0.0007030933,0.002820558,0.0005181209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9500224,0.0002712329,0.04319698,0.00001823084,0.0005397343,0.0009834442,0.0008790366,0.0007940713,0.003294875],"genre_scores_gemma":[0.9983792,0.00006975114,0.0002597437,0.00002821888,0.0001591287,0.0006625488,0.0001857552,0.00009004186,0.0001655673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8047224,"threshold_uncertainty_score":0.9996365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009811584084861052,"score_gpt":0.2735026817450353,"score_spread":0.2636910976601743,"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."}}