{"id":"W169063832","doi":"10.63317/2ghqfd9j9xh9","title":"A French Human Reference Corpus for Multi-Document Summarization and Sentence Compression","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Automatic summarization; Computer science; Natural language processing; Multi-document summarization; Artificial intelligence; Sentence; Information retrieval; Compression (physics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003061343,0.0003087422,0.0002966335,0.0001552429,0.0002367744,0.0005996815,0.001403862,0.0004501416,0.000008971195],"category_scores_gemma":[0.00009154484,0.0002526726,0.00005163963,0.00009994365,0.00008097843,0.0003358617,0.002769497,0.0007841321,0.000001628489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005038795,"about_ca_system_score_gemma":0.00008522249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008705101,"about_ca_topic_score_gemma":0.0002923803,"domain_scores_codex":[0.9982747,0.00005009626,0.0003427421,0.0007820436,0.0002814154,0.0002690353],"domain_scores_gemma":[0.9983086,0.00007183202,0.0003262004,0.0008509523,0.0003377255,0.0001046632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002262539,0.0004016915,0.002861696,0.002063958,0.00007226624,0.00002400483,0.002870879,0.00003012898,0.2533446,0.4641246,0.004266204,0.2699174],"study_design_scores_gemma":[0.001284674,0.000264588,0.002330524,0.001680426,0.00005726392,0.00003943225,0.0000255318,0.3454119,0.1611063,0.4833712,0.002525333,0.001902842],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00610656,0.0009218956,0.990397,0.0002997908,0.0003937035,0.0008664621,0.0000139723,0.0008709101,0.0001297257],"genre_scores_gemma":[0.2610875,0.00004247179,0.7377894,0.0001365229,0.00004123788,0.00009209992,0.00009208651,0.0000136133,0.0007050147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3453818,"threshold_uncertainty_score":0.9999925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04659203308536194,"score_gpt":0.3394436589713973,"score_spread":0.2928516258860354,"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."}}