{"id":"W2898884573","doi":"10.1002/rob.21838","title":"Selective memory: Recalling relevant experience for long‐term visual localization","year":2018,"lang":"en","type":"article","venue":"Journal of Field Robotics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Landmark; Term (time); Artificial intelligence; Context (archaeology); Initialization; Field (mathematics); Key (lock); Human–computer interaction; Modalities; Computer vision; Real-time computing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005811251,0.000631718,0.0006770274,0.0007890211,0.0004603469,0.0009270501,0.001528664,0.0006810085,0.002628592],"category_scores_gemma":[0.002856535,0.000287761,0.0004467836,0.0006767836,0.0002986641,0.001489466,0.001208539,0.0006324117,0.001112511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000361834,"about_ca_system_score_gemma":0.0005210032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005032072,"about_ca_topic_score_gemma":0.007127253,"domain_scores_codex":[0.9996682,0.00004428265,0.00001991995,0.0001415537,0.00007483028,0.0000511849],"domain_scores_gemma":[0.9989249,0.0003372582,0.0001430678,0.0002673029,0.0002161803,0.0001113036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006878844,0.0004769837,0.008243901,0.0002396879,0.0001632084,0.0001847793,0.0006651346,0.02721887,0.04548378,0.002347109,0.005957636,0.908331],"study_design_scores_gemma":[0.00009133218,0.0008936537,0.01257535,0.00009291841,0.0002529272,0.0006116897,0.000519097,0.9097691,0.05522292,0.008766731,0.01108755,0.0001165618],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1463767,0.001056969,0.8430305,0.0002404545,0.0001262075,0.0001278203,0.0002835081,0.005547785,0.003210113],"genre_scores_gemma":[0.8286369,0.0002925779,0.1676218,0.0001160368,0.00005676738,0.00008782223,0.0003224134,0.0001342411,0.002731356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005032072,"threshold_uncertainty_score":0.01000553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01653788862499986,"score_gpt":0.2786194447107229,"score_spread":0.262081556085723,"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."}}