{"id":"W3097602436","doi":"10.18653/v1/2020.emnlp-main.648","title":"Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; McGill University","funders":"Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research","keywords":"Automatic summarization; Computer science; Task (project management); Scale (ratio); Multi-document summarization; Information retrieval; Data science; Natural language processing; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002028676,0.001121507,0.0007582241,0.006439524,0.0009840131,0.001635022,0.001542917,0.001657758,0.004575892],"category_scores_gemma":[0.009728466,0.0002948014,0.001172444,0.005642042,0.000531022,0.002435127,0.001908114,0.001596507,0.005127328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007917975,"about_ca_system_score_gemma":0.001985038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00263149,"about_ca_topic_score_gemma":0.008596601,"domain_scores_codex":[0.9978161,0.0005311197,0.0004071257,0.0005089805,0.0006287255,0.0001078506],"domain_scores_gemma":[0.9936045,0.002277053,0.0007714166,0.001348361,0.0014848,0.0005138583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00120355,0.0008321093,0.01379492,0.006468001,0.0006150287,0.0007082864,0.001127093,0.01250299,0.05445099,0.007688593,0.5865784,0.3140301],"study_design_scores_gemma":[0.0006718058,0.0009514139,0.0511893,0.0004889155,0.0003581628,0.0009666763,0.001209164,0.07089893,0.05123261,0.01672086,0.8049521,0.0003599794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.08322953,0.006854271,0.104144,0.003700434,0.001824041,0.001794785,0.7504591,0.03466313,0.01333073],"genre_scores_gemma":[0.04990854,0.0009805695,0.1323191,0.000447481,0.0004279871,0.001113814,0.8105431,0.000622207,0.003637311],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.006439524,"threshold_uncertainty_score":0.01530784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1275074925419956,"score_gpt":0.3234923945206476,"score_spread":0.195984901978652,"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."}}