{"id":"W2947194824","doi":"10.4230/oasics.ldk.2019.13","title":"A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Computer science; Unstructured data; Data science; Database; Data mining; Big data","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":[0.0007851934,0.0003283709,0.0003700741,0.0003647797,0.0002271904,0.0009885686,0.002181997,0.0001023025,0.0000117064],"category_scores_gemma":[0.0001229367,0.0002803128,0.00006965824,0.0003597284,0.00005946994,0.003624919,0.001178969,0.0002905985,0.00002961292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006804948,"about_ca_system_score_gemma":0.0001082395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001782812,"about_ca_topic_score_gemma":0.00006831244,"domain_scores_codex":[0.9976595,0.00003375193,0.0008231117,0.000486257,0.0003881855,0.0006091757],"domain_scores_gemma":[0.9976442,0.0001524993,0.0003771578,0.001573288,0.0001226753,0.0001301633],"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":[0.0004344672,0.0006436133,0.01434156,0.003152006,0.0005685544,0.00001215083,0.0184606,0.002023461,0.0004317185,0.5775851,0.01869701,0.3636498],"study_design_scores_gemma":[0.007539582,0.0003685963,0.001939794,0.0002583233,0.00003674319,0.00003281202,0.001050204,0.9527543,0.0005722615,0.009323875,0.0254301,0.0006934021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1779382,0.00004622831,0.802901,0.002277319,0.002711478,0.007478424,0.00348885,0.0003435313,0.002814945],"genre_scores_gemma":[0.6320911,0.00001245647,0.3626729,0.001036038,0.0001988408,0.0001407913,0.003497468,0.0000485664,0.0003017806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9507309,"threshold_uncertainty_score":0.9999649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0271195313764799,"score_gpt":0.2921384102888953,"score_spread":0.2650188789124154,"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."}}