{"id":"W2786093037","doi":"10.1109/hpcc-smartcity-dss.2017.35","title":"An Efficient Type-Agnostic Approach for Finding Sub-sequences in Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Search engine indexing; Data mining; Data deduplication; Inverted index; Normalization (sociology); Semantics (computer science); Index (typography); Raw data; Data type; Data structure; Theoretical computer science; Information retrieval; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002284475,0.0008863042,0.001343421,0.006611621,0.0009866096,0.002774151,0.002231963,0.001023904,0.001697744],"category_scores_gemma":[0.01286577,0.0006089172,0.001244555,0.00670648,0.000989708,0.005484885,0.002689718,0.001593428,0.002064403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008893476,"about_ca_system_score_gemma":0.002700883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001722412,"about_ca_topic_score_gemma":0.002513969,"domain_scores_codex":[0.9960358,0.0003718473,0.0006113403,0.0007190179,0.002084227,0.0001778939],"domain_scores_gemma":[0.9876885,0.002525646,0.001388504,0.005430305,0.002711412,0.0002557191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004968721,0.0002747389,0.008996539,0.0006724451,0.000146857,0.0003947685,0.000645366,0.01125712,0.05940197,0.02142299,0.008886846,0.8874034],"study_design_scores_gemma":[0.0001608699,0.0006879678,0.008705699,0.0002903383,0.0002630366,0.00486872,0.001580812,0.5661399,0.2213813,0.1004709,0.09507859,0.0003718794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01424042,0.0006679238,0.9772667,0.0002077034,0.0001271989,0.0004033203,0.001740232,0.004113669,0.001232847],"genre_scores_gemma":[0.05617696,0.0003276127,0.9373132,0.0001214038,0.0000814243,0.00021688,0.003638954,0.0003115005,0.001812175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006611621,"threshold_uncertainty_score":0.01208162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5830582344166529,"score_gpt":0.5204564048528669,"score_spread":0.06260182956378602,"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."}}