{"id":"W4404573785","doi":"10.48550/arxiv.2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Office of Naval Research; Canadian Institute for Advanced Research; U.S. Army Combat Capabilities Development Command; National Institutes of Health; National Science Foundation; VMware; Office of Science; Accenture; Canada Excellence Research Chairs, Government of Canada; U.S. Department of Energy","keywords":"Training (meteorology); Computer science; Natural language processing; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007197988,0.0003606489,0.0004006213,0.0002884464,0.0001903709,0.0009216702,0.006707038,0.0003500407,0.00001311092],"category_scores_gemma":[0.00004428281,0.0003830452,0.0001160453,0.0004564672,0.0000511058,0.001392994,0.01111578,0.0008073909,0.00001838214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001638572,"about_ca_system_score_gemma":0.0003625019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002498575,"about_ca_topic_score_gemma":0.0001486177,"domain_scores_codex":[0.9974389,0.0001029937,0.0002100887,0.001655718,0.00009947895,0.0004928214],"domain_scores_gemma":[0.9975372,0.00007862133,0.0001854799,0.001906687,0.0001108983,0.0001811427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003982303,0.0001028931,0.0000023067,0.0002996743,0.00008658937,0.0007706543,0.003128079,0.004345619,0.0001696471,0.9770141,0.009001294,0.005039339],"study_design_scores_gemma":[0.0002221987,0.00004886749,2.955005e-7,0.0001469901,0.00004656274,0.000006319974,0.0001939255,0.4854311,0.0002452758,0.5122284,0.001081754,0.0003483465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005554706,0.0008580182,0.9871113,0.0002016877,0.0003762781,0.0008686333,0.003476566,0.0009771319,0.0005756209],"genre_scores_gemma":[0.7803537,0.00002572455,0.2164932,0.0003113967,0.0001111494,0.000009554937,0.001843493,0.00003690892,0.0008148797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.774799,"threshold_uncertainty_score":0.9998621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.145504564827458,"score_gpt":0.2749186405515542,"score_spread":0.1294140757240962,"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."}}