{"id":"W3138422238","doi":"10.5194/egusphere-egu21-2708","title":"WEIR-P: An Information Extraction Pipeline for the Wastewater Domain","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canarie","funders":"","keywords":"Wastewater; Pipeline (software); Sanitation; Domain (mathematical analysis); Engineering; Computer science; Environmental engineering; Mathematics; Operating system","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":[0.003275348,0.00285571,0.001337193,0.01026914,0.00140792,0.003762294,0.00189408,0.001277471,0.05230753],"category_scores_gemma":[0.01202705,0.001493413,0.00286526,0.008468639,0.0005758206,0.005600909,0.004867115,0.002273397,0.06190638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051681,"about_ca_system_score_gemma":0.004292661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005393956,"about_ca_topic_score_gemma":0.008434154,"domain_scores_codex":[0.998117,0.0003022802,0.0002855999,0.000540374,0.0005997628,0.0001550168],"domain_scores_gemma":[0.9966499,0.001345346,0.0002559895,0.0006708553,0.0009165173,0.0001613191],"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":[0.0005539545,0.000277212,0.005332546,0.003114136,0.0003435582,0.001014949,0.001418009,0.003101873,0.01162951,0.01032848,0.4256384,0.5372475],"study_design_scores_gemma":[0.0002370216,0.0003533323,0.009443736,0.0005382757,0.0001887752,0.0009059646,0.001388728,0.05394704,0.02654501,0.05168531,0.8545264,0.0002403894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00532112,0.001308623,0.4769467,0.001074874,0.0002615755,0.001601672,0.184355,0.3166728,0.01245761],"genre_scores_gemma":[0.02012012,0.001143747,0.7209197,0.0003947533,0.0001054061,0.001436722,0.2264739,0.01403744,0.01536819],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05230753,"threshold_uncertainty_score":0.1749861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0290160402497609,"score_gpt":0.2881792781220938,"score_spread":0.2591632378723329,"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."}}