{"id":"W4385612782","doi":"10.1145/3539618.3591903","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Test (biology); Multimedia; Content (measure theory); Information retrieval; Image retrieval; Content-based image retrieval; Image (mathematics); Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004627554,0.0001338564,0.0001333127,0.0002854204,0.0002421301,0.0002209178,0.0005570513,0.00006275869,0.0001552895],"category_scores_gemma":[0.0006129761,0.0001291191,0.00004435096,0.001710985,0.00002862289,0.0004515435,0.0001944838,0.0001409976,0.004289996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001157328,"about_ca_system_score_gemma":0.00009167993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001026659,"about_ca_topic_score_gemma":0.00009436182,"domain_scores_codex":[0.9985625,0.00006191894,0.0002593348,0.0005223324,0.0003066237,0.0002872716],"domain_scores_gemma":[0.9985545,0.0002947147,0.00007163797,0.0006225774,0.0002187311,0.0002378853],"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":[0.0001154909,0.0009515777,0.1078821,0.00003553906,0.00005203334,0.0000349314,0.009466965,0.002104567,0.5978154,0.01770684,0.06714375,0.1966909],"study_design_scores_gemma":[0.00035415,0.0002609937,0.3222051,0.000003653846,0.000004093616,0.000008507342,0.00006439194,0.6666416,0.008177719,0.0002246447,0.001884841,0.000170351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5381185,0.000001252046,0.4445465,0.007941007,0.000297593,0.0008423575,0.000009726587,0.002204006,0.006039053],"genre_scores_gemma":[0.8733532,0.000002587855,0.11937,0.0004403006,0.0000875281,0.00007795948,0.00006239583,0.00001855408,0.006587486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.664537,"threshold_uncertainty_score":0.9964853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03756938073927824,"score_gpt":0.3233776406108255,"score_spread":0.2858082598715473,"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."}}