{"id":"W4394672802","doi":"10.1145/3613905.3650921","title":"Chart What I Say: Exploring Cross-Modality Prompt Alignment in AI-Assisted Chart Authoring","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Mitacs; University of Toronto","keywords":"Computer science; Chart; Modality (human–computer interaction); Variety (cybernetics); Focus (optics); Affordance; Natural language processing; Interface (matter); User interface; Spoken language; Artificial intelligence; Human–computer interaction; Programming language","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001938605,0.0006337572,0.0007991227,0.0004877515,0.0001265267,0.004386297,0.001851953,0.0004152763,0.00004654211],"category_scores_gemma":[0.00005654465,0.0005853793,0.0003279658,0.0005630451,0.00005887311,0.001480107,0.005709714,0.001174098,0.0006561739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007271264,"about_ca_system_score_gemma":0.0004611211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008601348,"about_ca_topic_score_gemma":0.000177807,"domain_scores_codex":[0.9947591,0.0002050169,0.001082218,0.002057755,0.000960308,0.0009355359],"domain_scores_gemma":[0.9972447,0.00007617676,0.0002114465,0.002009758,0.0001261901,0.0003317657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002251392,0.002249305,0.0330412,0.01535471,0.001361283,0.003930313,0.05330799,0.003889563,0.01359328,0.4114246,0.01435306,0.4472696],"study_design_scores_gemma":[0.005144966,0.0007588745,0.1675366,0.02945884,0.0001705657,0.000400969,0.004058822,0.1888999,0.1391755,0.4208049,0.03208046,0.01150965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6991717,0.007999403,0.1051994,0.04186147,0.09986015,0.007740493,0.00007740917,0.006650044,0.03143992],"genre_scores_gemma":[0.9896643,0.0001871065,0.004596039,0.0005485812,0.001012085,0.001561907,0.00004268476,0.00006325997,0.002324012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4357599,"threshold_uncertainty_score":0.9996598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09878289714193828,"score_gpt":0.3317976024484869,"score_spread":0.2330147053065487,"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."}}