{"id":"W2103706669","doi":"10.5430/air.v2n3p35","title":"The role of statistical and semantic features in single-document extractive summarization","year":2013,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Automatic summarization; Anaphora (linguistics); Sentence; Context (archaeology); Artificial intelligence; Word (group theory); Feature (linguistics); Term (time); Representation (politics); Resolution (logic); Information retrieval; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001179645,0.00007058743,0.00009174614,0.000164283,0.0001655146,0.0004118583,0.0005536236,0.00005479875,0.00001298364],"category_scores_gemma":[0.0009415337,0.00004907325,0.00001202663,0.0005762372,0.0003209333,0.0004354219,0.0002983041,0.0003380582,0.00001844509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005611621,"about_ca_system_score_gemma":0.00005844198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001034743,"about_ca_topic_score_gemma":0.0003466256,"domain_scores_codex":[0.9984725,0.0002608192,0.0002493042,0.0002485441,0.0004437384,0.0003251112],"domain_scores_gemma":[0.9980267,0.001288941,0.00004807863,0.0002531195,0.0003287307,0.00005445763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007143622,0.0000358811,0.0001745902,0.000006445476,0.000001946147,0.000002511178,0.000623562,0.000002900153,0.02695057,0.4508846,0.0000245976,0.5212852],"study_design_scores_gemma":[0.000004543886,0.00007061001,0.0003730377,0.00002428012,4.662719e-7,0.000002193826,0.0005705279,0.01012631,0.3228974,0.6658608,0.0000267809,0.00004309011],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05878661,0.005360282,0.9306856,0.003178295,0.00008809337,0.0009795944,0.000001786771,0.0001032156,0.0008165326],"genre_scores_gemma":[0.9646508,0.00008599,0.03515798,0.000009121426,0.00001710461,0.00003871086,8.676482e-7,0.000004787188,0.00003464379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058642,"threshold_uncertainty_score":0.397156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04453799708544237,"score_gpt":0.3789329910890959,"score_spread":0.3343949940036536,"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."}}