{"id":"W2259525462","doi":"","title":"Distance intertextuelle et classement des textes d'après leur structure : méthodes de découpage et analyses arborées","year":2006,"lang":"fr","type":"preprint","venue":"Open Repository and Bibliography (University of Liège)","topic":"Linguistics and Discourse Analysis","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Linguistic Association","funders":"","keywords":"Natural language processing; Computer science; Artificial intelligence; Linguistics; Tree (set theory); Humanities; Mathematics; Combinatorics; Philosophy","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":[0.006567581,0.001024247,0.001220338,0.007401361,0.002240783,0.01162689,0.001478155,0.001725759,0.008089792],"category_scores_gemma":[0.04597851,0.0009096425,0.001578325,0.006209755,0.002754336,0.006610716,0.002612295,0.003358916,0.004059045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002315853,"about_ca_system_score_gemma":0.00269732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008428343,"about_ca_topic_score_gemma":0.01142371,"domain_scores_codex":[0.9891019,0.003589669,0.0007929747,0.003031321,0.003082098,0.0004021199],"domain_scores_gemma":[0.9533078,0.03427328,0.00201967,0.003162581,0.006525871,0.0007108647],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002313143,0.0004938806,0.04571123,0.002102447,0.0006701477,0.0004442741,0.03852058,0.006619993,0.05908398,0.09203809,0.007752139,0.7442502],"study_design_scores_gemma":[0.0004712534,0.000923525,0.168012,0.001070713,0.001245117,0.001905532,0.03719331,0.1870392,0.1675174,0.1333027,0.3008141,0.0005051126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2854654,0.002431957,0.6900163,0.0009381781,0.0002169042,0.0003132001,0.002899738,0.002712902,0.01500533],"genre_scores_gemma":[0.5630373,0.0007911386,0.4091959,0.00009297976,0.0001524286,0.0006609035,0.003532256,0.001852046,0.02068496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01162689,"threshold_uncertainty_score":0.03473312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09109063205159147,"score_gpt":0.3248004868262289,"score_spread":0.2337098547746374,"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."}}