{"id":"W2894405212","doi":"10.1167/18.10.136","title":"Totally-Looks-Like: A Dataset and Benchmark of Semantic Image Similarity","year":2018,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Similarity (geometry); Artificial intelligence; Representation (politics); Perception; Sketch; Image (mathematics); Semantics (computer science); Pattern recognition (psychology); Information retrieval; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001502313,0.004029109,0.001811948,0.005861408,0.001717065,0.002516147,0.004517716,0.004591438,0.007400877],"category_scores_gemma":[0.007124228,0.0004217091,0.003924093,0.004599486,0.001510869,0.003081597,0.003544226,0.00301487,0.005832474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002248327,"about_ca_system_score_gemma":0.001311123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01504886,"about_ca_topic_score_gemma":0.02807868,"domain_scores_codex":[0.9967467,0.0005736684,0.0003668128,0.001033474,0.000994378,0.0002849245],"domain_scores_gemma":[0.996703,0.0007214677,0.0003738208,0.0009963278,0.0006212277,0.0005842833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004985911,0.004505516,0.03718218,0.009753759,0.003198962,0.00288802,0.0009436297,0.02533108,0.0206079,0.005457142,0.6184101,0.2667359],"study_design_scores_gemma":[0.002128765,0.006893943,0.1859333,0.002294894,0.00136256,0.01974582,0.004959965,0.2693005,0.03428917,0.02113285,0.4511601,0.000798149],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.4385563,0.02307443,0.02137389,0.00251096,0.003164896,0.002811182,0.4547777,0.01729636,0.03643443],"genre_scores_gemma":[0.1926846,0.001734795,0.03937323,0.0009281574,0.0003705368,0.0007065869,0.7581596,0.0006096422,0.0054329],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01504886,"threshold_uncertainty_score":0.02992254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009170502743326061,"score_gpt":0.3133320988807346,"score_spread":0.3041615961374086,"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."}}