{"id":"W2891582949","doi":"10.18653/v1/d18-1294","title":"Syntax Encoding with Application in Authorship Attribution","year":2018,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Computer science; Syntax; Natural language processing; Sentence; Encoding (memory); Artificial intelligence; Abstract syntax; Embedding; Parsing; ENCODE; Abstract syntax tree; Word (group theory); Representation (politics); Parse tree; Tree (set theory); Lossless compression; Linguistics; Data compression; Mathematics","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":[0.0008438492,0.00008919665,0.00008998968,0.0001144509,0.0001290234,0.00007677135,0.0003547639,0.00007734694,0.00002729806],"category_scores_gemma":[0.00003412848,0.00007262977,0.00001681179,0.0008092781,0.00004903388,0.0004040794,0.00007653777,0.0001354957,0.0002479499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008485674,"about_ca_system_score_gemma":0.00005006333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006443288,"about_ca_topic_score_gemma":0.0001516265,"domain_scores_codex":[0.9989942,0.00008379408,0.0001680303,0.0003172499,0.0001788508,0.0002578896],"domain_scores_gemma":[0.9993992,0.00004959178,0.00006148371,0.0003150095,0.00009743528,0.00007725124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001461148,0.00002589744,0.02973184,0.000006153302,0.000002822916,0.000002521807,0.0005877079,0.00001424139,0.002085232,0.9482435,0.00006548641,0.01921999],"study_design_scores_gemma":[0.001622688,0.0007124224,0.1660605,0.0001793436,0.00001345015,0.0001020565,0.0002472305,0.4954273,0.2473245,0.06177415,0.02526328,0.001273114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04913354,0.00001096477,0.9438195,0.001449983,0.00009453468,0.0001570983,5.813239e-7,0.0002140341,0.005119742],"genre_scores_gemma":[0.9686971,0.000001147637,0.03074434,0.0002175502,0.00007483821,0.00002343847,0.000005065869,0.000004031773,0.0002324864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9195636,"threshold_uncertainty_score":0.3186978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02970367137682244,"score_gpt":0.2849840804760073,"score_spread":0.2552804090991848,"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."}}