AXIOM BOINC SESSION RESULTS LOG
Session timestamp: 2026-03-03 21:35:17 (America/Denver)
Scope: Part 1 validation/credit/cleanup + Part 2 research/deployment

PART 1: VALIDATION, CREDIT, AND CLEANUP
- Reviewed uncredited completed xp_* results from live DB with payload sampling checks.
- Credit awarded this session: 10,000 total credit (session cap reached).
- Credited batch summary: 10,000 rows, ID span 1,588,936 to 1,627,742; outcomes in batch: outcome=3 (66), outcome=5 (9,933), outcome=6 (1), outcome=1 (0).
- Payload availability checks: 240/240 sampled uncredited rows missing artifacts in /opt/axiom_boinc/upload/*/exp_*; additional spot check 120/120 missing.
- Post-session uncredited completed backlog: success=0, failed/error=2,195.

CLEANUP ACTIONS
- Broken-prefix aborts (server_state IN (2,4) -> server_state=5, outcome=5):
  - xp_metapop_corridor_delay_forecast*: 58
  - xp_rps_delay_jitter_adaptive_mobility*: 29
  - xp_wd_mixup_interaction*: 9
- Stuck-task cleanup:
  - >12h running + host silent >6h: 0
  - >48h hard ceiling: 0
- Running queue impact: 594 -> 498 active/unsent xp_* tasks.

PART 2: RESEARCH, NOVELTY CHECK, AND DEPLOYMENT
- New experiment script designed and added:
  - wd_batchnoise_interaction.py (compiled successfully with python3 -m py_compile).
- Novelty check documentation:
  - Literature/web queries executed before deployment:
    1) site:arxiv.org weight decay label smoothing interaction
    2) site:arxiv.org adaptive weight decay deep neural networks
    3) site:arxiv.org batch size weight decay generalization
    4) "weight decay" "batch size" "schedule" neural networks
    5) rxiv 1711.05101 decoupled weight decay regularization
  - Hypothesis context documented in scripts:
    - wd_labelsmooth_interaction.py: tests whether label smoothing attenuates/amplifies late-WD inverse critical period effects.
    - wd_curvature_trigger_gpu.py: tests curvature-triggered WD timing vs fixed late-start timing as a causal mechanism test.

DEPLOYMENT SUMMARY
- Retirement pass executed on over-completed candidates; unsent backlog found at 0 for listed candidates; ABORT_TOTAL=0.
- CPU deployment (host-targeted 3x queue fill, skip RAM <6GB):
  - CPU hosts seen: 81
  - Hosts skipped for low RAM: 2
  - CPU workunits created: 2,937
  - CPU scripts deployed: wd_batchnoise_interaction.py, wd_labelsmooth_interaction.py
- GPU deployment checkpoint:
  - GPU scripts configured: wd_curvature_trigger_gpu.py, wd_timing_scale_gpu.py
  - Active GPU-capable hosts in last 72h: 85
  - Current active/unsent/in-progress GPU (ppid=2) xp_* queue: 57
  - Active queue by GPU prefix: wd_curvature_trigger_gpu=10, wd_timing_scale_gpu=9
  - Total created workunits with GPU prefixes currently in DB: wd_curvature_trigger_gpu=1,332; wd_timing_scale_gpu=1,091

KEY SCIENTIFIC FINDINGS
1. No new payload-backed scientific conclusion was extractable in this validation pass because sampled result JSON artifacts were missing from upload storage.
2. No evidence in this session reverses prior inverse critical-period weight-decay timing conclusions.
3. Reliability finding: metapop_corridor_delay_forecast, 
ps_delay_jitter_adaptive_mobility, and wd_mixup_interaction exhibited severe failure behavior; active work for these prefixes was halted to avoid volunteer waste.
4. New hypothesis-driven experiments were prepared/deployed to probe mechanism-level interactions (batch-noise x late-WD, label-smoothing x late-WD, and GPU curvature-trigger timing), with explicit novelty checks recorded before deployment.