{"id":"W4414015747","doi":"10.11159/mvml25.128","title":"Contrastive Self-Supervised Learning for Packaging Artwork Layer Classification with Text and Image Features","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Layer (electronics); Artificial intelligence; Contextual image classification; Image (mathematics); Natural language processing; Pattern recognition (psychology); Materials science; Nanotechnology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003240033,0.0001374175,0.0002132074,0.0002254803,0.0002242079,0.000274095,0.000103381,0.00004418978,6.718309e-8],"category_scores_gemma":[0.00003533917,0.00009212422,0.0000210231,0.0006705748,0.00006277717,0.0001414811,0.00003085774,0.0002052678,5.543273e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003445689,"about_ca_system_score_gemma":0.00001343384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005320699,"about_ca_topic_score_gemma":5.402208e-7,"domain_scores_codex":[0.9992309,0.000005009046,0.000169031,0.0002369752,0.0001518282,0.0002062569],"domain_scores_gemma":[0.999556,0.0001356736,0.00005324643,0.00005008401,0.0001477902,0.00005718869],"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":[0.0006831216,0.0001588343,0.02658534,0.005383424,0.0007304773,0.000003434571,0.002042031,0.09869438,0.3524203,0.2907646,0.006052713,0.2164814],"study_design_scores_gemma":[0.000435555,0.0001154338,0.006933766,0.0005551166,0.00001927114,0.00001349304,0.00004316948,0.9859856,0.004798366,0.00001202164,0.0009595754,0.0001286326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9643003,0.001172547,0.03033881,0.0001642773,0.001587332,0.001051038,0.000001856017,0.0003467419,0.001037036],"genre_scores_gemma":[0.9991558,0.00001784064,0.0005035652,0.000009674867,0.00009903705,0.0000361779,9.080753e-8,0.000009491916,0.0001683756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8872913,"threshold_uncertainty_score":0.3756717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00637281257876713,"score_gpt":0.2059374558583182,"score_spread":0.1995646432795511,"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."}}