{"id":"W2152061679","doi":"10.1145/1321211.1321246","title":"Removing manually generated boilerplate from electronic texts","year":2007,"lang":"en","type":"article","venue":"Proceedings of CASCON","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; University of New Brunswick","funders":"","keywords":"Computer science; Boilerplate text; Metadata; Parsing; Template; Information retrieval; ASCII; World Wide Web; Natural language processing; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0008219109,0.000148116,0.0001844041,0.0002263069,0.00005323651,0.0001322485,0.0007845321,0.00009280278,0.00001354121],"category_scores_gemma":[0.0004033892,0.0001531431,0.00004898156,0.0005847386,0.00003039876,0.0005651611,0.0002351825,0.0002792304,0.00002786047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000125476,"about_ca_system_score_gemma":0.00007616482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000741998,"about_ca_topic_score_gemma":0.00000463928,"domain_scores_codex":[0.9982264,0.000002596815,0.000282092,0.0003970045,0.0004643926,0.0006275207],"domain_scores_gemma":[0.999085,0.0002192797,0.0001032968,0.0001667122,0.0003281959,0.00009749398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006340549,0.00007291677,0.01909088,0.0001025184,0.00009706954,0.00003953837,0.001396775,0.00005190121,0.8514522,0.02085959,0.001390352,0.1053829],"study_design_scores_gemma":[0.0006752875,0.0002254282,0.07670267,0.0001254231,0.00001113745,0.00005082364,0.00004033074,0.01049323,0.9031549,0.004122436,0.003948381,0.0004500176],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9629576,0.0006824276,0.03430149,0.00008956974,0.0001312192,0.0001272961,9.93837e-7,0.0003340351,0.001375322],"genre_scores_gemma":[0.9832301,0.00002588995,0.01634981,0.00004151098,0.00009367809,0.000004250703,0.000001419078,0.00002027493,0.0002330212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1049329,"threshold_uncertainty_score":0.6244993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008669633716138785,"score_gpt":0.244718544950474,"score_spread":0.2360489112343352,"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."}}