AXIOM BOINC SESSION LOG
Session timestamp: 2026-03-04 08:45:56 -07:00
Combined workflow: Part 1 (validation/credit/cleanup) + Part 2 (deployment/research)

PART 1 - VALIDATION, CREDIT, CLEANUP (source: validate_2026-03-04_0840.txt)
- Completed-success results reviewed: 116
- Payload quality: experiment_result=105, missing_upload_artifact=11, error=0, invalid_json=0
- Runtime profile: min=50.66s, median=844.90s, max=1011.92s
- Dominant reviewed experiment families: pitinh(6), alleeclim(6), battres(6), chemcross(6), nmtrap(6), fishcull(6)
- Credit posted this session: 1001 total credit across 101 results (within 10,000 cap)
- Uncredited success rows remaining after posting snapshot: 109 (concurrent queue growth during pass)
- Counter updates: credited_count_now=4972, total_results_count_now=4896
- Stuck/broken cleanup actions:
  - Dead-host >12h running aborts: 0
  - Hard >48h running aborts: 0
  - No active prefix met cross-host broken-state threshold for global abort

PART 2 - DEPLOYMENT AND RESEARCH (source: AutoReviewLogs run summary)
- Retirement/cleanup for over-seeded unsent lines executed before deployment:
  svdrank=34, wdlr=29, wdwindow=27, wdoptim=81, wddepth=54, wdtasksweep=54, wdwidthtrans=27
- New experiments designed and deployed:
  1) wd_labelsmooth_interaction.py (CPU)
     Hypothesis: label smoothing attenuates/amplifies late-WD inverse critical-period behavior.
  2) wd_curvature_trigger_gpu.py (GPU-aware)
     Hypothesis: effective WD onset is curvature-triggered rather than fixed-onset.

DEPLOYMENT DETAILS
- CPU deployment:
  - Targeted CPU WUs created: 2,844 (hosts seen=79, skipped low-RAM hosts=2)
  - Untargeted CPU fallback WUs created: 2,788
  - Total new CPU WUs from session prefixes: 5,632
- GPU deployment:
  - GPU hosts with idle capacity detected: 80
  - Targeted GPU WUs created: 313
  - Untargeted GPU fallback WUs created: 316
  - Total GPU WUs deployed: 629
  - GPU scripts used: wd_curvature_trigger_gpu.py (with wd_timing_scale_gpu.py available in GPU pool)

GPU CHECKPOINT
- GPU hosts active in deployment pass: 80
- GPU workunits deployed: 629 total
- GPU script line deployed: wd_curvature_trigger_gpu.py

NOVELTY CHECK DOCUMENTATION
- Query: "weight decay label smoothing interaction neural networks"
  - References reviewed: arXiv 2010.16402, 1706.05350, 1910.00482, 1711.05101
  - Novelty note: no established direct test found for WD timing ICP interaction with label smoothing in this controlled setup.
- Query: "adaptive weight decay schedule deep learning"
  - References reviewed: arXiv 2111.09764, 2001.04796, 2404.03672, 2201.00519
  - Novelty note: curvature-triggered WD onset versus fixed-late onset as a causal ICP mechanism test appears unaddressed directly.

KEY SCIENTIFIC FINDINGS
1. Validation pass confirmed continued throughput stability (median runtime ~845s) across active delay/ecology families, indicating no broad reliability collapse in current production lines.
2. New successful outputs in pitinh/alleeclim/battres/chemcross/nmtrap/fishcull broadened cross-host replication coverage for active ecological/control pipelines.
3. GPU WD/matmul-family runs continue to deliver usable successes despite elevated failure pressure, reinforcing a host/environment bottleneck interpretation rather than universal algorithmic failure.
4. Part 2 introduced two mechanism-focused lines (WD x label smoothing interaction and curvature-triggered WD onset) that directly target unresolved causal questions in WD timing dynamics.
5. Novelty screening against recent literature did not identify prior direct matches for these exact controlled interaction/mechanism tests, supporting continued execution priority.

END OF SESSION LOG