wwu-mmll / confound_corrected_cpm / 28588670492

Builds Branch Commit Type Ran Committer Via Coverage
28588670492 develop Release 0.4.2: opt-in network marker for atlas generator tests Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> push NilsWinter github
84.75
28588676762 main Merge develop for 0.4.2 release push NilsWinter github
84.75
28587807377 develop Add whole-brain atlas variants (cortical + subcortical) Several bundled parcellations are cortical by design (Glasser HCP-MMP, Desikan-Killiany, Destrieux) or ship a cortical-only version (Harvard-Oxford). This adds *WholeBrain variants that appe... push NilsWinter github
84.75
28585783142 develop docs: document custom and built-in brain atlases Add a "Brain Atlases" user-docs page covering the single `atlas` parameter (built-in name or custom CSV path), a table of the 16 bundled atlases with node counts / network availability / coverage, ... push NilsWinter github
84.75
28583601537 develop Add Desikan-Killiany atlas (68 regions) via ENIGMA conte69 surface Bundles the DK FreeSurfer surface atlas as MNI-space coordinates, closing the last gap from the atlas design note (16 atlases total). ENIGMA ships DK as a per-vertex label vector ... push NilsWinter github
84.75
28577330990 develop Add built-in atlas registry with 15 bundled MNI coordinate sets Users can now select an atlas by name (e.g. atlas="Schaefer100-17") instead of hand-building a coordinate CSV. A single `atlas` parameter accepts either a built-in name or a path to ... push NilsWinter github
84.75
28551407101 develop Release 0.4.1: increment baseline & TFCE rounding fixes, dead-code cleanup Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> push NilsWinter github
83.6
28551404406 main Release 0.4.1: increment baseline & TFCE rounding fixes, dead-code cleanup Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> push NilsWinter github
83.6
28550949079 develop Fix increment baseline and TFCE threshold rounding; remove dead code Increment model now computes full - covariates (the connectome's added value over the confounds), matching the report/docs, instead of full - connectome. The latter measured the... push NilsWinter github
83.6
28545310784 develop Document the fixed-statistic invariant behind batched edge selection Note at the batching site that sharing one r/p pass across runs is valid only because the edge statistic is fixed across runs; if it ever becomes a per-run hyperparameter, r/p m... push NilsWinter github
72.46
28545012926 develop Batch edge-statistic computation over runs in _select_edges The direct edge-selection path recomputed the correlation r/p from scratch once per run (per permutation), even though the statistic depends only on the data and the fixed correlation ty... push NilsWinter github
72.46
28544354110 develop Fix edge selection running on CPU when GPU requested; drop dead correlation helpers _select_edges called fit_transform without passing device, so the default (CPU) was always used even when device='gpu'/'cuda'. Edge selection — often the heaviest... push NilsWinter github
72.43
28521900213 main Migrate examples to SEM simulator; add simulation docs; bump 0.3.2 Migrate regression/classification quickstarts and example_simulated_data.py to the SEM-based simulator (simulate_data_given_kappa) for confound-aware example data with a known gro... push NilsWinter github
72.51
28521855038 develop Migrate examples to SEM simulator; add simulation docs; bump 0.3.2 Migrate regression/classification quickstarts and example_simulated_data.py to the SEM-based simulator (simulate_data_given_kappa) for confound-aware example data with a known gro... push NilsWinter github
72.51
28519122297 develop RELEASE_PLAN: record sklearn equivalence tests; plan quickstart migration to SEM simulator Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> push NilsWinter github
71.91