SLEF Reference Evaluation Dataset v1.1

Reference evaluation dataset for SLEF (Synthetic Learner Evaluation Framework) — a controlled-Ground-Truth framework for evaluating learner-state inference under synthetic learner conditions. This release contains the scientific evidence produced by the SLEF Reference Evaluation across five tutor conditions: the synthetic-learner dialogue corpora, assigned hidden Ground Truth, generator-native behavioral characterization, and transcript-level learner-state recoverability analysis. Version 1.1.0 is an additive reproducibility release. It preserves the v1.0.0 scientific corpus and scientific values unchanged while adding the exact DAS extractor prompt used in the reference experiment, offline reproducibility software, tests, and frozen expected analysis outputs. Licensing: Dataset and instrument materials are released under CC BY 4.0. The reproducibility software under software/ is released under the Apache License 2.0, as documented in software/LICENSE and software/NOTICE.