{"id":"W4376167025","doi":"10.48550/arxiv.2305.05858","title":"Vārta: A Large-Scale Headline-Generation Dataset for Indic Languages","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Headline; Computer science; Natural language processing; Scale (ratio); Artificial intelligence; Variety (cybernetics); Quality (philosophy); Information retrieval; Data science; Linguistics; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001223708,0.001833639,0.0007765479,0.006540702,0.001548766,0.001712437,0.001832421,0.001864029,0.01675205],"category_scores_gemma":[0.007390967,0.000481081,0.001078605,0.005460896,0.0006647172,0.002404581,0.001831634,0.001816266,0.0209711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009998659,"about_ca_system_score_gemma":0.001987072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01183196,"about_ca_topic_score_gemma":0.02992735,"domain_scores_codex":[0.9985868,0.0003261204,0.0002101297,0.000340529,0.0004019466,0.000134532],"domain_scores_gemma":[0.9953985,0.001620073,0.0004001587,0.0008906357,0.001294215,0.0003964974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003127721,0.0002716665,0.00477482,0.001893781,0.00009598857,0.0006980651,0.0005415587,0.00161225,0.004707056,0.001636815,0.9412285,0.04222672],"study_design_scores_gemma":[0.000601946,0.0002032898,0.01994042,0.0003226539,0.0001494328,0.001435921,0.001481776,0.01985476,0.01311776,0.003144583,0.9395694,0.0001779471],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02935421,0.001419058,0.005955609,0.0007532377,0.000436904,0.0004077399,0.9328522,0.01621232,0.01260878],"genre_scores_gemma":[0.01165772,0.0002025554,0.009795621,0.0001484459,0.00006416416,0.0002731082,0.9752456,0.000576035,0.00203687],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01675205,"threshold_uncertainty_score":0.05604124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09930359967213902,"score_gpt":0.255901518137751,"score_spread":0.1565979184656119,"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."}}