AXIOM BOINC SESSION RESULTS LOG
Session timestamp: 2026-03-03 23:01:02
Mode: Part 3 (save + upload), consolidating Part 1 validation and Part 2 deployment

SOURCE LOGS
- Validation log: validate_2026-03-03_2255.txt
- Auto-review log: run_2026-03-03_1352.log
- Findings memory: findings_summary.txt

PART 1 - RESULTS REVIEWED AND CREDIT AWARDED
- Reviewed completed uncredited results: 1657531, 1657535, 1657540 (host 1, Pyhelix).
- Payload quality: 3/3 included valid experiment_result JSON (science-bearing output).
- Credit awarded this validation pass:
  - Result 1657531: +3
  - Result 1657535: +3
  - Result 1657540: +8
  - Session total: +14 credit (within 10,000 cap)
- Post-credit totals recorded in validation log:
  - User PyHelix total_credit: 13326.571579000007
  - Host 1 total_credit: 10136.571579000007
- Counter updates recorded:
  - credited_count.txt = 54441
  - total_results_count.txt = 55057
  - remaining uncredited completed success rows = 0

STUCK / BROKEN TASK CLEANUP
- Active-prefix fail-rate check: no active CPU or GPU experiment prefix >50% fail in the validation window.
- Broken experiment aborts: none applied in Part 1.
- Stuck cleanup dead-host >12h: 0 tasks aborted.
- Hard cleanup >48h: 0 tasks aborted.
- Retirement pass in Part 2 identified over-seeded families, but unsent backlog for listed candidates was 0 at action time (ABORT_TOTAL=0).

PART 2 - DEPLOYMENT SUMMARY
CPU DEPLOYMENT
- Deployment scripts used: wd_batchnoise_interaction.py, wd_labelsmooth_interaction.py.
- Auto-review run reported: CPU_HOSTS_SEEN=81, CPU_SKIPPED_LOW_RAM=2, CPU_WU_CREATED=2937.
- Time-window BOINC snapshot (from 2026-03-03 13:52:13) shows workunits created for these CPU lines:
  - wd_batchnoise_interaction: 3695
  - wd_labelsmooth_interaction: 3243
- CPU target hosts (window-derived host IDs, excluding parser artifact 0):
  1,6,7,9,16,23,29,31,57,60,61,67,71,72,74,80,85,86,87,95,105,107,115,116,123,126,127,137,140,141,143,192,202,205,206,209,212,216,217,219,223,235,249,251,253,255,258,267,270,287,292,299,321,322,323,324,325,326,327,328,329,330,331,332,333,336,337,338,339,340,341,342,343,344,345,346,347,348,350,351.

GPU DEPLOYMENT (GPU CHECKPOINT)
- GPU scripts used: wd_curvature_trigger_gpu.py, wd_timing_scale_gpu.py.
- Run log shows GPU deployment pass launched; final tail is truncated in run_2026-03-03_1352.log, so checkpoint is taken from BOINC state snapshot.
- Time-window BOINC snapshot (from 2026-03-03 13:52:13):
  - wd_curvature_trigger_gpu workunits: 1853
  - wd_timing_scale_gpu workunits: 1575
  - Total GPU workunits for the two GPU scripts: 3428
  - Distinct GPU-targeted hosts (window-derived): 88
- Current active GPU queue snapshot for these two scripts:
  - Active GPU hosts: 3
  - Active GPU results: 11 total (curvature 3, timing 8)
  - Active hostnames: Pyhelix (1), jisoo (23), Foxtrot-2 (339)

NEW EXPERIMENTS DESIGNED + NOVELTY CHECK DOCUMENTATION
- Newly added script in Part 2: wd_batchnoise_interaction.py (compiled successfully with python3 -m py_compile).
- Novelty-search evidence logged during Part 2 included:
  - 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
  - "weight decay" "batch size" "schedule" neural networks
  - arxiv 1711.05101 decoupled weight decay regularization
- Novel angle documented for new CPU line: test interaction term (late-WD gain under small-batch noise minus late-WD gain under large-batch regime), rather than re-running single-factor WD timing sweeps.

KEY SCIENTIFIC FINDINGS
1. Validation sample quality remained high: all 3 newly completed uncredited GPU-oriented results reviewed in Part 1 contained valid experiment_result payloads and were creditable science outputs.
2. The longest reviewed run (617.224s, wd_timing_scale_gpu_gpu) completed with valid structured output, supporting continued operational stability of the GPU WD timing pipeline for this batch.
3. Across this session, no contradictory evidence against previously established ICP/WD directionality was observed; the session primarily strengthened confidence/coverage while expanding interaction-focused experimental lines.

OPERATIONAL NOTES
- No cumulative result ID ledger was maintained; database remains source of truth for credited results.
- This consolidated session log is formatted for website "Latest Findings" parsing via the SCIENTIFIC FINDINGS numbered section.