{"id":"W4408664623","doi":"10.1117/12.3042442","title":"Machine-learning-driven optimization of vertical fiber-to-chip coupling system for co-packaged optics and in-package optical I/O applications","year":2025,"lang":"en","type":"article","venue":"","topic":"Semiconductor Lasers and Optical Devices","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ansys (Canada)","funders":"","keywords":"Optical fiber; Coupling (piping); Integrated optics; Computer science; Materials science; Optical coupling; Chip; Optoelectronics; Fiber; Electronic engineering; Engineering; Telecommunications; Composite material","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":[0.0001299928,0.0001403884,0.000269677,0.0001509608,0.00005376285,0.00003930863,0.0001096924,0.0001136864,0.00001886684],"category_scores_gemma":[0.00009443779,0.0001354612,0.00004187632,0.0002663985,0.00004181383,0.00006253238,0.00003271023,0.0001535048,0.000007824768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005895596,"about_ca_system_score_gemma":0.0000157552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005586516,"about_ca_topic_score_gemma":0.000006656802,"domain_scores_codex":[0.9991359,0.000009499773,0.0003415995,0.000203882,0.00009315432,0.0002159735],"domain_scores_gemma":[0.9992678,0.0003908121,0.00001457219,0.0001576803,0.00006226073,0.0001069336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003183405,0.00003139041,0.001397592,0.0006913044,0.00004037592,8.787403e-7,0.00004308665,0.964477,0.0120544,0.02099489,0.0000336891,0.0002035662],"study_design_scores_gemma":[0.0004862619,0.00003544913,0.0002890913,0.0001120119,0.00004334541,0.000001087389,0.0001567395,0.974111,0.024288,0.00003186573,0.00030629,0.0001388933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3230326,0.0002572214,0.6651416,0.0001102551,0.0001046855,0.001093647,0.00003205308,0.0002878616,0.009940054],"genre_scores_gemma":[0.9610664,0.00002848143,0.03858177,0.00002500071,0.00002411751,0.0001123399,0.00003517487,0.00002482613,0.0001019408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6380337,"threshold_uncertainty_score":0.5523949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00934871643180625,"score_gpt":0.2433474478388241,"score_spread":0.2339987314070179,"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."}}