{"id":"W1997648388","doi":"10.1109/asonam.2012.239","title":"Lessons from a Jihadi Corpus","year":2012,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Deception; Rank (graph theory); Ranking (information retrieval); Computer science; Process (computing); Natural language processing; Artificial intelligence; Factor (programming language); Psychology; Social psychology; Mathematics; Programming language","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002186244,0.0000533451,0.00005938513,0.00002223025,0.00007243975,0.00005086652,0.0003112937,0.00003963909,0.0002299819],"category_scores_gemma":[0.00002582047,0.00004418457,0.00002918305,0.0001411986,0.00001163186,0.0003676665,0.0001194132,0.00007392319,0.0009208479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001474021,"about_ca_system_score_gemma":0.00001809632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007016934,"about_ca_topic_score_gemma":0.000004485984,"domain_scores_codex":[0.9994325,0.00004089489,0.00007898011,0.000118022,0.0001034574,0.0002261669],"domain_scores_gemma":[0.9994989,0.00007084989,0.00002472017,0.0002560456,0.00001821319,0.0001312848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[9.341841e-7,0.0000247565,0.01138449,6.955353e-7,0.00000523148,9.963644e-7,0.0005964261,9.877352e-7,0.0007673456,0.9589059,0.00193014,0.02638205],"study_design_scores_gemma":[0.0008841015,0.00005977095,0.1894913,0.00002716678,0.00001994957,0.00003324959,0.0002030205,0.04025321,0.1172293,0.06864469,0.5821565,0.0009976339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01394276,0.000287655,0.9668997,0.003467578,0.0007109974,0.00003595486,0.00000284457,0.000237266,0.01441523],"genre_scores_gemma":[0.9504383,0.00000361723,0.04718128,0.0009384152,0.000113554,0.000002878184,0.0000034928,0.000002461833,0.001316056],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9364955,"threshold_uncertainty_score":0.9998571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07617170086621515,"score_gpt":0.3223950401989654,"score_spread":0.2462233393327502,"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."}}