{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006328996,0.00007502815,0.0001640494,0.0001137145,0.00008546358,0.0000686785,0.0005010592,0.00003618197,0.00002838147],"category_scores_gemma":[0.0001340268,0.00005939898,0.00003907454,0.0001725491,0.00009366158,0.0004368981,0.000278226,0.0001912758,0.00001115821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001337155,"about_ca_system_score_gemma":0.00004312175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006473507,"about_ca_topic_score_gemma":0.000005387748,"domain_scores_codex":[0.9990672,0.0000697447,0.0003311387,0.000143026,0.0002833839,0.0001054724],"domain_scores_gemma":[0.9988427,0.0001151124,0.0003718329,0.00037259,0.0002075975,0.00009017581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002395567,0.001534748,0.02260282,0.0003161639,0.0001819484,0.0001290027,0.003600065,0.0002344289,0.6322266,0.01233176,0.1242666,0.2023363],"study_design_scores_gemma":[0.001286029,0.001685713,0.7794735,0.0002552512,0.00004946647,0.000439133,0.0000285523,0.193358,0.004114676,0.005921526,0.01312569,0.0002625494],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8035139,0.0001309738,0.1925287,0.002890479,0.0002141287,0.000114149,0.00003852725,0.00001732482,0.0005517946],"genre_scores_gemma":[0.8893421,0.0000178141,0.1104179,0.0001256109,0.00007923516,3.441706e-7,0.000005737691,0.000003876537,0.000007359143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7568706,"threshold_uncertainty_score":0.242222,"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."}}