{"id":"W4400687527","doi":"10.20944/preprints202407.0999.v1","title":"<em>QuickPic AAC</em>: An AI-Based Application to Enable Just-in-Time Generation of Topic-Specific Displays for Persons Who Are Minimally Speaking","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Assistive Technology in Communication and Mobility","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Vocabulary; Computer science; Usability; Multimedia; Artificial intelligence; Natural language processing; Speech recognition; Human–computer interaction; Linguistics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002792794,0.0005361209,0.0009874627,0.0004896222,0.0005523035,0.00003252294,0.001658017,0.001227231,0.0006985077],"category_scores_gemma":[0.000696624,0.0005777782,0.0002864201,0.0004503205,0.0001648013,0.0001140477,0.00254602,0.002082486,0.000873859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095169,"about_ca_system_score_gemma":0.000702042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001505196,"about_ca_topic_score_gemma":0.002940868,"domain_scores_codex":[0.9947674,0.0007762604,0.00155101,0.001749737,0.0004602616,0.0006953232],"domain_scores_gemma":[0.9937415,0.0004890395,0.0009473865,0.003847198,0.0007537995,0.0002211526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008256786,0.001877991,0.6065069,0.005422608,0.0002716457,0.000008584881,0.01687452,0.002919379,0.3362996,0.01490744,0.004795718,0.009289969],"study_design_scores_gemma":[0.00280269,0.0002581576,0.7741102,0.004119019,0.0003714513,0.000002376885,0.005201285,0.04871133,0.04570917,0.004885522,0.1119129,0.001915879],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9727922,0.0003598855,0.01159012,0.004432721,0.0006730378,0.00625364,0.0003636006,0.0004730643,0.003061691],"genre_scores_gemma":[0.98558,0.00009361732,0.003917577,0.0007103126,0.0004077632,0.00604212,0.0006103849,0.0001008071,0.002537416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2905904,"threshold_uncertainty_score":0.9999041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1886887886560189,"score_gpt":0.4326559531249511,"score_spread":0.2439671644689322,"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."}}