{"id":"W6977394809","doi":"10.7939/dvn/10795","title":"Accurate Fact Harvesting from Natural Language Text in Wikipedia with Lector.","year":2016,"lang":"en","type":"dataset","venue":"Borealis","topic":"Military Technology and Strategies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Domain (mathematical analysis); Information extraction; Natural language; Relationship extraction; Open domain; Relation (database); Question answering; Volume (thermodynamics)","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":[0.001786248,0.001620684,0.0007164802,0.009951854,0.0008030568,0.001735973,0.001630918,0.001444818,0.002622803],"category_scores_gemma":[0.009263649,0.0004590363,0.0008781274,0.004840793,0.0005101891,0.003020822,0.001723657,0.001142652,0.005232986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091689,"about_ca_system_score_gemma":0.001478625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02016035,"about_ca_topic_score_gemma":0.04884275,"domain_scores_codex":[0.9980707,0.0003173656,0.0002776856,0.0005583879,0.0006537169,0.0001222613],"domain_scores_gemma":[0.9948966,0.001627904,0.0005850669,0.001466992,0.00116555,0.000257919],"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":[0.0006370739,0.0004901021,0.03450981,0.003993501,0.0005918563,0.001428889,0.0007075903,0.008966955,0.007574779,0.003816495,0.7734048,0.1638781],"study_design_scores_gemma":[0.0002319588,0.0001997835,0.04672009,0.0007138786,0.0003531082,0.002191667,0.0009221638,0.05643889,0.02132181,0.007140073,0.8636355,0.0001310045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04329146,0.003822118,0.0131939,0.0008607614,0.0004948125,0.0003306913,0.9178843,0.01155608,0.008565838],"genre_scores_gemma":[0.01791625,0.0003520099,0.01533851,0.00009032416,0.00003354073,0.0001143297,0.9650308,0.0000900985,0.001034118],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02016035,"threshold_uncertainty_score":0.04008603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007658465680868943,"score_gpt":0.2194942161478212,"score_spread":0.2118357504669522,"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."}}