{"id":"W2333815456","doi":"10.1115/detc2015-47541","title":"Automatic Extraction of Function Knowledge From Text","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Autodesk (Canada)","funders":"","keywords":"WordNet; Computer science; Word2vec; Natural language processing; Knowledge base; Artificial intelligence; Leverage (statistics); Parsing; Information retrieval; Function (biology); Knowledge extraction","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":[0.00102606,0.001890432,0.0009797683,0.01583174,0.001006014,0.001711062,0.001269443,0.001037932,0.003906096],"category_scores_gemma":[0.007888319,0.0006854067,0.001324665,0.006688525,0.000672226,0.004215848,0.0013551,0.001212982,0.003699178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053418,"about_ca_system_score_gemma":0.002605136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003580105,"about_ca_topic_score_gemma":0.005272841,"domain_scores_codex":[0.9983511,0.0002734291,0.0002573422,0.0004632769,0.0005628971,0.00009192732],"domain_scores_gemma":[0.992991,0.003969032,0.0007477339,0.0006129268,0.001568852,0.0001105533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001616171,0.0002437779,0.007037128,0.003332166,0.0001563658,0.002189728,0.001513721,0.004218236,0.0431486,0.01105168,0.04170612,0.8852409],"study_design_scores_gemma":[0.0001522754,0.0003024654,0.03705567,0.002624057,0.0007324262,0.005136305,0.003229869,0.2194601,0.1845873,0.08679996,0.4595406,0.0003789991],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06724193,0.003986154,0.8334436,0.001196569,0.0003093823,0.001139631,0.0497408,0.02474355,0.01819845],"genre_scores_gemma":[0.1451065,0.002279239,0.7609467,0.0003277419,0.0002105253,0.0009632214,0.08433298,0.00119967,0.004633434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01583174,"threshold_uncertainty_score":0.01306719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04113296902143269,"score_gpt":0.3013955782573264,"score_spread":0.2602626092358937,"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."}}