laya-ledgar Copyright 2026 Cole Heideman This model and the code that built it are released under the Apache License 2.0 (LICENSE). The model is a fine-tune of Laya by Convai Innovations, released under the Apache License 2.0: https://huggingface.co/convaiinnovations/laya (revision 85cc74ddae6109077ebe2853a9b3077fb6606a78) M, N.; M, A. From Laya to Vega: Open Non-Autoregressive Decision Models with Calibrated Probabilities. Preprints 2026, 2026110781. https://doi.org/10.20944/preprints202611.0781.v1 It was trained and scored on LEDGAR as distributed in LexGLUE, under the Creative Commons Attribution 4.0 licence (CC BY 4.0) as declared on the LexGLUE dataset card: https://huggingface.co/datasets/coastalcph/lex_glue (revision c23fdff1a6bf74e0e1a71cb86f1e781d37da888c, config "ledgar") Tuggener, D.; von Daniken, P.; Peetz, T.; Cieliebak, M. LEDGAR: A Large-Scale Multi-label Corpus for Text Classification of Legal Provisions in Contracts. Proceedings of LREC 2020. Chalkidis, I.; Jana, A.; Hartung, D.; Bommarito, M.; Androutsopoulos, I.; Katz, D. M.; Aletras, N. LexGLUE: A Benchmark Dataset for Legal Language Understanding in English. Proceedings of ACL 2022. The provisions come from contracts filed with the US Securities and Exchange Commission (EDGAR). Changes: the option texts are the dataset's label names in lower case.