{"id":"W2741988747","doi":"10.18653/v1/w17-2322","title":"Painless Relation Extraction with Kindred","year":2017,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Compute Canada","keywords":"Computer science; Relation (database); Relationship extraction; Python (programming language); Task (project management); Biomedical text mining; Data science; Data mining; Information retrieval; Text mining; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008949555,0.00005080855,0.00004558237,0.000008983048,0.000169437,0.00003428617,0.0001049802,0.0001061221,0.00001933207],"category_scores_gemma":[0.00009385368,0.00003561972,0.00001772235,0.000008132935,0.0001023286,0.000002325039,0.00002965214,0.00004261454,0.00001031769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002985497,"about_ca_system_score_gemma":0.00001682642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002536299,"about_ca_topic_score_gemma":0.00006696049,"domain_scores_codex":[0.9996468,0.000012514,0.00005320812,0.0001401072,0.00006069641,0.00008665725],"domain_scores_gemma":[0.9995865,0.000004800337,0.00005917211,0.0002941205,0.00002447594,0.00003098616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003796955,0.0001151146,0.1014748,0.00001964974,0.0001017083,0.00001980254,0.00007085117,0.00001551759,0.4329797,0.0009234897,0.01027925,0.4536203],"study_design_scores_gemma":[0.001093003,0.0005921736,0.656665,0.00002454973,0.00002043474,0.00004682758,0.0001728498,0.0001798696,0.1358754,0.0002189784,0.2048325,0.0002783692],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9461697,0.0000790282,0.02913499,0.0009264829,0.0001337562,0.00005907502,0.000001299615,0.00002833615,0.0234673],"genre_scores_gemma":[0.9921404,0.00001977499,0.004384629,0.00007312748,0.0001119068,0.000004930353,0.00001763454,0.000005184115,0.003242401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5551902,"threshold_uncertainty_score":0.145253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02022296523828725,"score_gpt":0.3020006754100079,"score_spread":0.2817777101717207,"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."}}