{"id":"W1933502375","doi":"","title":"MSR SPLAT, a language analysis toolkit","year":2012,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Parsing; Set (abstract data type); Dependency (UML); Programming language; Natural language processing; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0002693534,0.00009433589,0.00013251,0.0002153059,0.00004996363,0.000123689,0.0007036291,0.00005146241,0.0001553],"category_scores_gemma":[0.00003934434,0.00007046117,0.00009249018,0.001175432,0.00001507529,0.0008877487,0.0002433116,0.0001002936,0.00009673094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002631693,"about_ca_system_score_gemma":0.0000120929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001001509,"about_ca_topic_score_gemma":0.00001556839,"domain_scores_codex":[0.9991886,0.00002623955,0.0001158041,0.0001816487,0.0001932264,0.0002944668],"domain_scores_gemma":[0.9992779,0.00003932774,0.0000438655,0.0005113152,0.00003118264,0.00009635862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005842474,0.000223669,0.03110391,0.0000338162,0.0004490002,0.00005722947,0.007522886,0.000005224791,0.01258176,0.7360702,0.00962416,0.2023223],"study_design_scores_gemma":[0.001180561,0.0002543677,0.03615037,0.00008240274,0.001318041,0.0003034401,0.0008530708,0.08038632,0.788299,0.04786156,0.03898827,0.004322649],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01168485,0.002953169,0.9741582,0.0003151976,0.0000839357,0.00005372442,8.279632e-7,0.001137121,0.00961295],"genre_scores_gemma":[0.5649138,0.000001628595,0.4334174,0.0003984637,0.00004681934,0.000003569744,0.000001692871,0.000002953403,0.001213675],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7757172,"threshold_uncertainty_score":0.2873323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009082678841866323,"score_gpt":0.2786049867048803,"score_spread":0.269522307863014,"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."}}