0.5.0 (#39)

Author: PierreGtch

CHANGELOG.md

@@ -7,16 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+
+## [0.5.0] - 2026-05-28
+
 ### Added
 - Add a required `revision` field on `Dataset` (forwarded to `BaseConcatDataset.pull_from_hub`) and pin every default dataset config to its current HuggingFace commit SHA for reproducibility ([#37](https://github.com/braindecode/OpenEEGBench/pull/37)).
-- Allow custom normalization methods by subclassing `Normalization`, now based on `exca.helpers.DiscriminatedModel`. Builtin subclasses pin their pre-existing `kind` value to preserve cached experiment UIDs ([#35](https://github.com/braindecode/OpenEEGBench/pull/35)).
 - Add `training_required_parameters` field on `_BackboneBase` for top-level `nn.Parameter` names that must remain trainable (e.g. Labram's `temporal_embedding`). Distinct from `training_required_modules`, which only accepts `nn.Module` names. Finetuning methods declare compatibility via the `supports_training_required_parameters` class variable; `IA3` and `OFT` opt out. `LoRA`/`AdaLoRA`/`DoRA` forward the list to PEFT's `target_parameters`; `Frozen`/`TwoStages` extend their unfreeze list ([#25](https://github.com/braindecode/OpenEEGBench/pull/25)).
 
 ### Changed
-- X
-
-### Fixed
-- X
+- Allow custom normalization methods by subclassing `Normalization`, now based on `exca.helpers.DiscriminatedModel`. Builtin subclasses pin their pre-existing `kind` value to preserve cached experiment UIDs ([#35](https://github.com/braindecode/OpenEEGBench/pull/35)).
 
 
 ## [0.4.0] - 2026-05-07
@@ -89,7 +88,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 Initial release.
 
-[Unreleased]: https://github.com/braindecode/OpenEEGBench/compare/v0.4.0...HEAD
+[Unreleased]: https://github.com/braindecode/OpenEEGBench/compare/v0.5.0...HEAD
+[0.5.0]: https://github.com/braindecode/OpenEEGBench/releases/tag/v0.5.0
 [0.4.0]: https://github.com/braindecode/OpenEEGBench/releases/tag/v0.4.0
 [0.3.0]: https://github.com/braindecode/OpenEEGBench/releases/tag/v0.3.0
 [0.2.1]: https://github.com/braindecode/OpenEEGBench/releases/tag/v0.2.1

CITATION.cff

@@ -37,8 +37,8 @@ authors:
     family-names: Delorme
     email: adelorme@ucsd.edu
     affiliation: "Swartz Center for Computational Neuroscience, Institute for Neural Computation, San Diego Supercomputer Center, University of California San Diego, USA; CNRS, France"
-version: 0.4.0
-date-released: "2026-05-07"
+version: 0.5.0
+date-released: "2026-05-28"
 identifiers:
   - type: doi
     value: 10.5281/zenodo.19698863

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "open-eeg-bench"
-version = "0.4.0"
+version = "0.5.0"
 description = "Benchmarking parameter-efficient fine-tuning of EEG foundation models"
 readme = "README.md"
 requires-python = ">=3.11"