{"id":"W3144575570","doi":"10.1109/asonam49781.2020.9381370","title":"Compression for Very Sparse Big Social Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia; University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Big data; Data compression; Compression (physics); Artificial intelligence; Data mining; Materials science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009877135,0.00008719508,0.0001193075,0.0000170188,0.0001924861,0.0001386541,0.001918322,0.00004161189,0.00002467542],"category_scores_gemma":[0.00003056075,0.00006712516,0.00003056032,0.0001290808,0.0000179289,0.0006226756,0.002224014,0.00006604579,0.00005052755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005315897,"about_ca_system_score_gemma":0.00004146119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001502254,"about_ca_topic_score_gemma":0.000001596378,"domain_scores_codex":[0.9990495,0.00002137237,0.0001342325,0.0004439985,0.0001789727,0.0001718958],"domain_scores_gemma":[0.9991531,0.00006029851,0.00004595664,0.0006091946,0.00003287669,0.00009855007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002486938,0.00005215026,0.00003488235,0.0000220956,0.000009644647,0.000005164623,0.0002564506,0.00001449769,0.001929165,0.01432336,0.613627,0.3697007],"study_design_scores_gemma":[0.0003784602,0.00004039286,0.0002295945,0.000006022184,0.000003219433,9.292442e-7,0.00001433257,0.6419703,0.0006923447,0.0006029467,0.3559479,0.0001136014],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003165173,0.00004810159,0.9928564,0.004997119,0.0004017169,0.0001349502,0.00008920518,0.0001906234,0.0009653519],"genre_scores_gemma":[0.2387818,0.00002614505,0.7472363,0.009681297,0.003036617,0.00002366673,0.0007476563,0.00002844772,0.0004380057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6419558,"threshold_uncertainty_score":0.3564751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2021195162059087,"score_gpt":0.3173468419974297,"score_spread":0.115227325791521,"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."}}