AXIOM BOINC SESSION LOG
Timestamp: 2026-03-04 08:56 (America/Denver)
Source logs: validate_2026-03-04_0853.txt, run_2026-03-03_1352.log

PART 1 - VALIDATION, CREDIT, AND CLEANUP
- Results reviewed: 210 successful exp_* outputs.
- Credit awarded this session: 2,469 total (all incremental updates applied in Part 1).
- App mix reviewed: CPU(appid=1)=186, GPU(appid=2)=24.
- Runtime profile: min=21.07s, median=844.03s, max=1156.25s.
- Dominant families in reviewed set: metacorr, kuraisle, fputadamp, antibswitch, lor96dar, alleeclim, fishcull, grayscot.

CREDIT HIGHLIGHTS (TOP CONTRIBUTORS)
- ChelseaOilman: +878
- Steve Dodd: +744
- Orange Kid: +384
- PyHelix: +259

STUCK/BROKEN TASK CLEANUP
- Dead-host stuck tasks (>12h running and >6h no contact): 0 aborted.
- Hard-ceiling stuck tasks (>48h running): 0 aborted.
- Broken experiment mass-aborts: none applied (no qualifying high-failure active prefix).

PART 2 - DEPLOYMENT AND RESEARCH
CPU deployment (from run_2026-03-03_1352.log)
- CPU hosts considered for fill: 81
- Hosts skipped for RAM<6GB: 2
- CPU workunits deployed: 2,937
- CPU scripts deployed:
  - wd_batchnoise_interaction.py (new in this session)
  - wd_labelsmooth_interaction.py

GPU checkpoint (from run_2026-03-03_1352.log)
- GPU deployment pass started as a separate mandatory phase.
- GPU scripts targeted:
  - wd_curvature_trigger_gpu.py
  - wd_timing_scale_gpu.py
- Final GPU host count and GPU workunit count were not emitted in this run log because execution was interrupted before completion output.

RETIREMENT / OVERSEEDED CHECK
- Retirement candidate scan executed.
- Candidate families included svdrank, percolation, wdlr, wdwindow, wdoptim, repcrystal, wddepth, wdtasksweep, wdwidthtrans.
- Unsent abort actions applied in this run: 0 (ABORT_TOTAL=0).

NEW EXPERIMENTS DESIGNED + NOVELTY CHECK
1) wd_batchnoise_interaction.py (new CPU experiment)
- New angle: explicit interaction test of late weight decay benefit under small-batch (high-noise) vs large-batch (low-noise) regimes.
- Novelty/documentation evidence captured in run log via targeted literature searches:
  - "weight decay batch size interaction neural networks"
  - "arxiv weight decay batch size interaction deep learning"
  - "Scheduled Weight Decay paper arxiv 2021"
  - "site:arxiv.org weight decay label smoothing interaction"
  - "site:arxiv.org adaptive weight decay deep neural networks"
  - "site:arxiv.org batch size weight decay generalization"
  - "arxiv 1711.05101 decoupled weight decay regularization"
- Validation: uploaded to server experiments directory and py_compile passed.

KEY SCIENTIFIC FINDINGS
1. This cycle added 210 newly validated successful outputs spanning CPU and GPU applications, increasing replication depth for delay/control and WD-focused families.
2. The validated runtime distribution remained centered near ~844s median, supporting stable throughput/credit behavior for the current experiment mix.
3. No completed failures were present in the reviewed Part 1 batch and no high-failure active prefix required emergency broad aborts, indicating stable queue health at validation time.
4. Part 2 introduced a new mechanistic interaction line (wd_batchnoise_interaction) to test whether late-WD gains scale with gradient-noise regime, extending prior ICP findings beyond main-effect analyses.

NOTES
- Cumulative credited result ID lists are intentionally omitted; database state is the source of truth.