{"id":"W2162954778","doi":"10.1109/ssdbm.2007.32","title":"Effective Summarization of Multi-Dimensional Data Streams for Historical Stream Mining","year":2007,"lang":"en","type":"article","venue":"International Conference on Scientific and Statistical Database Management","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Automatic summarization; Computer science; Data stream; Data stream mining; Data mining; ENCODE; Data stream clustering; Cluster analysis; STREAMS; Task (project management); Space (punctuation); Simple (philosophy); Information retrieval; Artificial intelligence","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":[0.001447058,0.0001449507,0.0001557889,0.0002912052,0.000151427,0.0003157155,0.001187639,0.00002503727,0.00004839219],"category_scores_gemma":[0.0001917573,0.0001311836,0.00002137626,0.0002023314,0.0001415022,0.0006554403,0.001314137,0.00006393332,0.00001097066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008383086,"about_ca_system_score_gemma":0.00002450663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004305902,"about_ca_topic_score_gemma":0.00005167683,"domain_scores_codex":[0.9978578,0.00003468282,0.0003610622,0.0008394375,0.0006699068,0.0002371091],"domain_scores_gemma":[0.9984471,0.0003854968,0.0001341431,0.000710378,0.0002115201,0.0001114156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004842875,0.0002403991,0.0001343339,0.00003886996,0.00005515186,0.00002202424,0.00002810934,0.000009923288,0.00008527246,0.6916754,0.009811604,0.2978504],"study_design_scores_gemma":[0.001214839,0.0001488375,0.003195759,0.0001052041,0.00004331364,0.000001647464,0.000123677,0.9622474,0.0001619696,0.003953843,0.02855195,0.000251616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006807232,0.00001589948,0.9920346,0.0002970873,0.001247836,0.0004466039,0.002740535,0.00003226108,0.002504512],"genre_scores_gemma":[0.2654712,0.00002031276,0.7203074,0.000123192,0.0000736615,0.00003117929,0.01048929,0.00001126163,0.003472529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9622374,"threshold_uncertainty_score":0.5349511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09385673441405702,"score_gpt":0.3485527483789883,"score_spread":0.2546960139649312,"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."}}