{"id":"W4404780760","doi":"10.18653/v1/2024.wikinlp-1.9","title":"Retrieval Evaluation for Long-Form and Knowledge-Intensive Image–Text Article Composition","year":2024,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Composition (language); Image retrieval; Image (mathematics); Natural language processing; Artificial intelligence; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007373503,0.00162514,0.001594349,0.006863108,0.001552714,0.002567878,0.001768937,0.002201127,0.00272697],"category_scores_gemma":[0.02962542,0.0002823812,0.001401891,0.003855339,0.0009209101,0.003609841,0.002794086,0.001352247,0.002543889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001374812,"about_ca_system_score_gemma":0.001578317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005113693,"about_ca_topic_score_gemma":0.009908185,"domain_scores_codex":[0.9909429,0.003276104,0.001213352,0.001442518,0.002742532,0.0003826508],"domain_scores_gemma":[0.9805247,0.01013569,0.001612777,0.002940042,0.00367898,0.001107889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00665869,0.008878591,0.03719344,0.009025663,0.001496151,0.0006731179,0.001602209,0.02495663,0.1138112,0.002345316,0.06103637,0.7323226],"study_design_scores_gemma":[0.002061951,0.01487451,0.1683809,0.0008831422,0.001948992,0.00350832,0.004775351,0.4549243,0.2416642,0.00818982,0.09812643,0.0006620639],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8846787,0.0099648,0.0633577,0.0007592946,0.0006368622,0.003632694,0.01564955,0.008319889,0.01300057],"genre_scores_gemma":[0.7076644,0.001850138,0.2004198,0.0005470958,0.0004577661,0.001935802,0.07890102,0.0006306918,0.007593229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007373503,"threshold_uncertainty_score":0.03899527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02998989438937405,"score_gpt":0.3324935095904673,"score_spread":0.3025036152010933,"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."}}