{"id":"W2593429156","doi":"10.1007/978-3-319-54181-5_22","title":"SSP: Supervised Sparse Projections for Large-Scale Retrieval in High Dimensions","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Encoding (memory); Convolutional neural network; Pattern recognition (psychology); Binary number; Projection (relational algebra); RGB color model; Neural coding; Binary code; Sparse matrix; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001198553,0.0005806891,0.0007256344,0.001101858,0.0006950381,0.0005837282,0.00355068,0.0004448632,0.00001049798],"category_scores_gemma":[0.0004288215,0.0005391857,0.0002077737,0.0005572462,0.0004948633,0.001347931,0.00158137,0.0009707814,0.00001627957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003740616,"about_ca_system_score_gemma":0.0006983619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003908815,"about_ca_topic_score_gemma":0.0003042071,"domain_scores_codex":[0.9957194,0.00003629179,0.0006283151,0.001878326,0.0007528854,0.0009847626],"domain_scores_gemma":[0.9962292,0.0005289303,0.0003481065,0.00228434,0.0004244122,0.0001850659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001894299,0.0005087429,0.0005181896,0.000267651,0.00004487707,0.0004244095,0.003347627,0.004987357,0.003049729,0.09299143,0.0004636341,0.8932069],"study_design_scores_gemma":[0.001539813,0.0008055193,0.0004168421,0.001095244,0.00002364087,0.00008837369,8.387162e-7,0.338651,0.02376379,0.6165884,0.01536331,0.001663265],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001372581,0.0003288182,0.9947532,0.000806822,0.001438824,0.001364516,0.00003934674,0.0003102597,0.0008209058],"genre_scores_gemma":[0.05611755,0.0002157185,0.9408318,0.0009675908,0.000496629,0.0000516436,0.00002036875,0.00006602581,0.001232625],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8915436,"threshold_uncertainty_score":0.999706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02869503918154223,"score_gpt":0.295643243122963,"score_spread":0.2669482039414207,"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."}}