{"id":"W4400531953","doi":"10.1145/3626772.3657878","title":"C-Pack: Packed Resources For General Chinese Embeddings","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":269,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Packed bed; Computer science; Chemistry; Chromatography","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":[],"consensus_categories":[],"category_scores_codex":[0.0002251937,0.0001281877,0.0001106323,0.0001254015,0.00007795122,0.0006240162,0.0007127778,0.00006180863,0.00002108893],"category_scores_gemma":[0.00007262756,0.00008366622,0.00008349432,0.0004120074,0.00002587971,0.0005417261,0.0001978903,0.0001061548,0.00002149176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002718072,"about_ca_system_score_gemma":0.00003001707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002130343,"about_ca_topic_score_gemma":0.000005397879,"domain_scores_codex":[0.9991017,0.00001276763,0.0001323375,0.0003701969,0.0001563766,0.0002266498],"domain_scores_gemma":[0.9994806,0.0000959825,0.00002150878,0.0002937999,0.00005356854,0.00005452749],"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":[0.000006959746,0.00001831857,0.00007382207,0.0001519272,0.00002363889,0.00003446474,0.001883953,0.000001061261,0.0202441,0.805116,0.04623195,0.1262138],"study_design_scores_gemma":[0.0001536883,0.0001070003,0.000087751,0.00009306168,0.000007991871,0.0000570329,0.00001430607,0.2040809,0.02872862,0.6986894,0.06756676,0.0004135052],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04253963,0.004271453,0.9438924,0.002971504,0.0003715398,0.0001969633,0.000003384326,0.003541617,0.002211565],"genre_scores_gemma":[0.2106278,0.000005147511,0.7821757,0.0005613432,0.0002289822,0.00003336373,0.000002058594,0.00001390696,0.006351721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2040799,"threshold_uncertainty_score":0.6017402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007724179664062534,"score_gpt":0.297602640136452,"score_spread":0.2898784604723895,"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."}}