AXIOM BOINC SESSION RESULTS LOG (Part 3 Consolidation)
Session timestamp: 2026-03-04 06:47
Sources: validate_2026-03-04_0643.txt, run_2026-03-03_1352.log, findings_summary.txt

KEY SCIENTIFIC FINDINGS
1. Missing-payload regime persisted in this validation window: 460/460 credited rows had no retrievable upload JSON artifacts, continuing the assimilator/file lifecycle concern.
2. Credited workload remained dominated by delay-family lines; observed failure bursts were concentrated in zero-elapsed timeout signatures (outcome=6, exit_status=0), supporting an infrastructure/runtime reliability bottleneck rather than interpretable payload failures.
3. Part 2 prioritized mechanism-level WD interaction experiments: a new batch-noise interaction test was added and deployed to CPU queues, while GPU queue pressure remained focused on curvature-trigger and timing-scale WD mechanisms.

PART 1 VALIDATION / CREDIT SUMMARY
- Terminal uncredited rows reviewed: 460 total (success=396, failed=64).
- App mix credited: CPU(appid=1)=442, GPU(appid=2)=18.
- Total credit awarded: 2010.00 (session cap 10,000 respected).
- Per-user credits were incrementally added to user.total_credit and host.total_credit (no absolute resets).
- Website counters updated:
  - credited_count.txt: 3043 -> 9112
  - total_results_count.txt: 3164 -> 3466
- Post-credit backlog snapshot:
  - Uncredited completed success rows: 27
  - Uncredited completed failure rows: 113

STUCK / BROKEN TASK CLEANUP
- Broken experiment active-task aborts:
  - exp_oscillatory_roughchannel_lbm_resonance*: 13 aborted
  - exp_potts_pulse_anneal_resonance*: 22 aborted
  - exp_abx_cycle_hgt_delay_resonance*: 0
  - exp_abx_cycle*: 0
  - exp_spatial_pgg_delay_fatigue*: 0
- Stuck-task cleanup:
  - Dead-host >12h running aborts: 0
  - Hard >48h running aborts: 0

PART 2 RESEARCH / DEPLOYMENT SUMMARY
- Retirement pass executed before deployment.
- Retirement candidates were over-completed but had no unsent inventory at action time; ABORT_TOTAL=0.

CPU DEPLOYMENT
- CPU scripts used:
  - wd_batchnoise_interaction.py
  - wd_labelsmooth_interaction.py
- Host targeting: fill to ~3x CPU queue depth, skip hosts with RAM <6 GB.
- CPU deployment checkpoint from run log:
  - CPU_HOSTS_SEEN=81
  - CPU_SKIPPED_LOW_RAM=2
  - CPU_WU_CREATED=2937

GPU DEPLOYMENT CHECKPOINT
- GPU scripts targeted:
  - wd_curvature_trigger_gpu.py
  - wd_timing_scale_gpu.py
- Part 2 run log terminated during GPU command capture on Windows (^C shown in log), so final in-log counters were not printed.
- Live DB checkpoint query after run window (create_time >= 2026-03-03 13:52:00):
  - GPU workunits created for these two script prefixes: 2721
  - GPU hosts receiving these workunits: 14
  - Currently queued for these two prefixes (server_state 1/2/4): 12 results across 7 hosts

NEW EXPERIMENTS DESIGNED + NOVELTY CHECK DOCUMENTATION
- Newly added script:
  - wd_batchnoise_interaction.py
- Core hypothesis:
  - Late weight decay improves generalization more under high gradient-noise conditions (small batch) than low-noise conditions (large batch).
- Novelty/literature search queries logged in Part 2 run:
  - "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"
  - "\"weight decay\" \"batch size\" \"schedule\" neural networks"
  - "arxiv 1711.05101 decoupled weight decay regularization"
- Novel angle recorded for this session:
  - Targets a specific interaction effect (timing x gradient-noise regime) rather than a generic WD ablation; deployed with host-derived seeding and fixed run-duration compliance.

OPERATIONAL NOTES
- No script edits were made during Part 1 validation.
- Persistent issue remains: frequent completed rows without retrievable payload artifacts at validation time.