{"id":"W2033016738","doi":"10.1145/1571941.1572087","title":"Incorporating prior knowledge into a transductive ranking algorithm for multi-document summarization","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Automatic summarization; Ranking (information retrieval); Computer science; Artificial intelligence; Function (biology); Learning to rank; Process (computing); Information retrieval; Machine learning; Natural language processing","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":[0.0008781663,0.0003927784,0.0004495234,0.000249341,0.0002493958,0.0004385452,0.001249536,0.0003038698,0.000004713087],"category_scores_gemma":[0.00005727374,0.0003919107,0.0002098735,0.0002205751,0.00002750641,0.0004632895,0.0007876058,0.0004263454,0.000006750591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003438773,"about_ca_system_score_gemma":0.0004419361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001455781,"about_ca_topic_score_gemma":0.000116218,"domain_scores_codex":[0.9973665,0.0001291055,0.0006718864,0.001189918,0.0002865187,0.0003560976],"domain_scores_gemma":[0.9982814,0.00009831203,0.0003319264,0.0008022023,0.0003822971,0.0001039122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002750411,0.00009328991,0.000009433292,0.0001216373,0.00003739424,0.000001943538,0.005140577,0.003996876,0.0001248386,0.02568642,0.00001929365,0.9647655],"study_design_scores_gemma":[0.0007744693,0.00004607351,0.00003017391,0.0002056811,0.00002321227,0.000002046823,0.00005156293,0.927301,0.001553258,0.06939412,0.0002005198,0.0004178876],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003463517,0.0003459448,0.9950549,0.0004379285,0.001186148,0.001723275,0.000003785878,0.0004244298,0.0004772058],"genre_scores_gemma":[0.02693089,0.0000157758,0.9718573,0.0001236364,0.0003595758,0.0002497888,0.00004452979,0.00002622427,0.0003922765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9643477,"threshold_uncertainty_score":0.9998533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04177516383753157,"score_gpt":0.3165668470610178,"score_spread":0.2747916832234863,"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."}}