willtanoe
9fe584d08e
chore: version-control sweep analysis scripts
...
Copy analyze_sweep.py, check_noise.py, compare_with_grid.py and
compare_repro.py out of the git-ignored results/ tree into scripts/sweep/.
Replace the implicit script-location repository root with a --repo-root
argument (relative default) without changing any computation. Outputs were
verified byte-identical to the originals on a scratch copy of the data.
2026-10-29 18:17:43 +01:00
willtanoe
91b0e371f7
chore: declare matplotlib and apply three behavior-preserving nits
...
- pyproject.toml: add a figures extra with matplotlib (used by the two figure
scripts) so the environment is reproducible from pyproject alone.
- partition.py: correct the partition_eval_split docstring (simulated per-client
eval sets from the global split, not client-owned held-out data).
- protean_cnn.py: extract_embeddings now moves batches to the model device.
- posthoc_statistical_audit.py: refuse to write an empty table.
2026-10-17 04:08:38 +07:00
willtanoe
111adb272e
research: add post-hoc statistical audit and defense preparation aids
...
- scripts/posthoc_statistical_audit.py + docs/research/POSTHOC_STATISTICAL_AUDIT.md:
read-only paired audit of the completed grid (exact sign-flip / Wilcoxon,
selection stability, per-class/per-client summaries); writes only posthoc__*.
- kisikisithesis/: robustness audit and examiner-preparation document with
deterministic read-only checks (robustness_checks.py).
- artifacts/analysis/posthoc__*.csv: audit outputs (6 tables).
- artifacts/analysis: track the 4 remaining beta0-snapshot effect/weight CSVs
(xiiotid a0.5 seeds 1-2), completing the tracked beta0 set.
- .gitignore: codify that non-beta0 prototype snapshots stay untracked.
2026-10-17 04:06:04 +07:00
willtanoe
34bab45865
docs: improve readability of PROTEAN comparison figures
2026-10-09 14:19:33 +07:00
willtanoe
ad8b2d7671
research: add paired original vs proposed PROTEAN analysis
2026-10-09 13:40:20 +07:00
willtanoe
87f9b14ada
docs: redesign final research figures and update README
2026-10-09 00:47:01 +07:00
willtanoe
2d27abc350
experiment: complete xiiotid three-alpha beta study
2026-09-27 15:12:58 +07:00
willtanoe
6b97a0d38b
experiment: validate beta selection across three seeds
2026-09-25 13:14:28 +00:00
willtanoe
50f2da7216
experiment: validate beta selection on one paired full condition
2026-09-25 04:22:55 +00:00
willtanoe
ad9aa53ba7
feat: implement support-weighted prototype aggregation
2026-09-24 23:37:26 +00:00
willtanoe
16b3add2cf
docs: validate baseline and add deterministic regression coverage
...
Session 3 baseline validation (no beta/support-weighted code added).
- Two measured full-data original_protean conditions (X-IIoTID and 5G-NIDD,
alpha=0.5, seed=0); frozen manifests reused and reload-verified.
- Partition consistency, per-class/per-client inspection, round-0, loss audit,
inference validation, reproducibility and a deterministic end-to-end test.
- S_j participant rule remains an explicitly labelled REPRODUCTION ASSUMPTION;
|S_j| < M quantified in 53/162 class-condition cells (32.7%), 15/18 conditions.
- Adds docs/baseline/BASELINE_VALIDATION.md, tests/test_baseline_validation.py,
scripts/validate_sj_participant_rule.py and small analysis artifacts.
- Test suite: 46 passed.
planningawal/ and raw datasets unchanged.
2026-09-24 20:42:56 +00:00
willtanoe
0aa8e2ba79
feat: implement reproducible PROTEAN baseline pipeline
2026-09-24 17:39:00 +00:00
willtanoe
2cc6a9859e
chore: checkpoint PROTEAN research planning and architecture
2026-09-24 17:08:56 +00:00
willtanoe