{"id":"W3176125464","doi":"10.18653/v1/2021.acl-short.137","title":"Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Automatic summarization; Computer science; Zhàng; Volume (thermodynamics); Joint (building); Computational linguistics; Natural language processing; Information retrieval; Library science; History; China; Engineering; Archaeology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001598048,0.001440333,0.001055284,0.006490723,0.001394849,0.00163794,0.001518344,0.001891029,0.003683512],"category_scores_gemma":[0.006963403,0.000346017,0.001047554,0.005730896,0.0003737709,0.0020488,0.001948413,0.000963216,0.004671366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008745836,"about_ca_system_score_gemma":0.00190853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0076167,"about_ca_topic_score_gemma":0.0257215,"domain_scores_codex":[0.9985065,0.000349445,0.0002670669,0.0004223831,0.0003247063,0.0001297882],"domain_scores_gemma":[0.995669,0.00125671,0.000427914,0.0008072162,0.001310016,0.000529142],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001279033,0.0006143686,0.01606398,0.004494131,0.0006510706,0.0007039403,0.001669301,0.003344842,0.01747414,0.002407652,0.743755,0.2075425],"study_design_scores_gemma":[0.001219298,0.001361971,0.07597423,0.0007719376,0.001077265,0.001343077,0.004880312,0.04535126,0.02524694,0.01478491,0.8275497,0.0004390508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.05949364,0.009797599,0.0155818,0.002144063,0.0006576501,0.0006273824,0.8974096,0.009436242,0.004852028],"genre_scores_gemma":[0.0301084,0.0009232325,0.02606989,0.000148821,0.0001721608,0.0004217154,0.9400687,0.0001785138,0.001908626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9984019,"threshold_uncertainty_score":0.01514471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01783199090790697,"score_gpt":0.2763486229645114,"score_spread":0.2585166320566044,"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."}}