{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002068184,0.0001118383,0.0001158413,0.00009425446,0.0003443201,0.001260938,0.0005920521,0.0000510991,0.00007136381],"category_scores_gemma":[0.0001355904,0.0001100787,0.00003239383,0.0004644977,0.00002915396,0.0009569572,0.0005163599,0.00006929936,0.000007796716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005635817,"about_ca_system_score_gemma":0.0001647222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007134006,"about_ca_topic_score_gemma":0.0004801142,"domain_scores_codex":[0.9985977,0.00003040343,0.0002160899,0.0006156063,0.0002675341,0.0002726539],"domain_scores_gemma":[0.9988739,0.00005617109,0.0000572169,0.0007761045,0.0001633068,0.00007326389],"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":[0.00003198679,0.0002285755,0.02447967,0.0009056088,0.0003015772,0.0001393778,0.009001525,0.02976453,0.09325879,0.3453107,0.1051644,0.3914132],"study_design_scores_gemma":[0.0005898664,0.00001345527,0.0004206871,0.00004415339,0.00001278072,0.00001148985,0.00008894487,0.8962973,0.03634685,0.01356303,0.05229329,0.0003181029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01938258,0.00006966833,0.9786642,0.0005100056,0.0008235965,0.0001870946,0.0001759644,0.00009628515,0.00009063142],"genre_scores_gemma":[0.5978136,0.000002851125,0.3941933,0.000478637,0.00008570567,0.00001473841,0.005334278,0.00001427194,0.002062606],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8665328,"threshold_uncertainty_score":0.9997758,"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."}}