Axiom BOINC Session Results Log
Session timestamp: 2026-03-03 18:22:46 -07:00
Workflow: Part 3 (save, publish, archive) with Part 1 + Part 2 consolidation

PART 1 VALIDATION / CREDIT SUMMARY
- Reviewed and credited 8,934 completed uncredited exp_* results.
- Result ID span: 1,532,432 to 1,542,029.
- Outcome mix: 6,591 success and 2,343 failed/error outcomes.
- Upload payload availability in this credited batch: 8,934 missing; 0 experiment_result; 0 error.
- Total credit awarded: 10,000 (session cap respected exactly).
- Top session credit additions: ChelseaOilman +6,658; Anandbhat +1,280; Steve Dodd +781; WTBroughton +687; marmot +219; kotenok2000 +167; Coleslaw +81.
- Counters updated in Part 1: credited_count 43,161 -> 52,095; total_results_count remained 54,848.

STUCK / BROKEN TASK CLEANUP
- Dead-host stuck cleanup (>12h running and >6h no contact): 0 tasks aborted.
- Hard-ceiling cleanup (>48h running): 0 tasks aborted.
- Retirement cleanup pass in Part 2: ABORT_TOTAL=0 (all listed retirement candidates had unsent=0 at execution time).
- Broken-prefix check: reservoir_extended showed high fail ratio (3 success / 18 failed) but only 1 active task; no blanket abort applied.

PART 2 DEPLOYMENT / RESEARCH SUMMARY
- Existing active scripts reviewed before design/deploy:
  - wd_labelsmooth_interaction.py (CPU)
  - wd_curvature_trigger_gpu.py (GPU)
- New experiment script designed and deployed:
  - wd_batchnoise_interaction.py
  - Hypothesis: late WD gains are larger under high-noise (small-batch) training than low-noise (large-batch) training.
  - Upload + syntax validation completed (python3 -m py_compile -> OK).

NOVELTY CHECK DOCUMENTATION
- Literature/search checks recorded in run log:
  - "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 kept for deployment: interaction-focused mechanism tests (timing x batch-noise, timing x label smoothing, curvature-triggered timing) rather than repeating settled WD timing main-effect lines.

CPU DEPLOYMENT
- CPU scripts used for queue fill:
  - wd_batchnoise_interaction.py
  - wd_labelsmooth_interaction.py
- Deployment run output: CPU_HOSTS_SEEN=81; CPU_SKIPPED_LOW_RAM=2; CPU_WU_CREATED=2937.
- Verified targeted CPU host IDs with newly created rows for these two scripts:
  1, 6, 7, 29, 85, 123, 287, 321, 324, 327, 330, 332, 333, 339, 340, 342, 345, 347.
- Verified DB counts for these two script prefixes in this window:
  - exp_wd_batchnoise_interaction_h*: 585 workunits across 18 hosts.
  - exp_wd_labelsmooth_interaction_h*: 579 workunits across 18 hosts.

GPU CHECKPOINT
- Planned GPU scripts:
  - wd_curvature_trigger_gpu.py
  - wd_timing_scale_gpu.py
- GPU deployment command was started but interrupted in run log (^C) before completion output.
- Post-run verification for these two prefixes in current window:
  - GPU hosts with created rows: 0
  - GPU workunits created: 0
- GPU status this session: deployment attempt initiated; no confirmed new WUs recorded for the two intended GPU scripts.

KEY SCIENTIFIC FINDINGS
1. No new payload-driven reversal was established in Part 1 because credited rows in that batch had missing upload JSON payloads at validation time.
2. Operationally, the project reduced backlog and preserved volunteer fairness by crediting 8,934 results with a strict 10,000-credit cap.
3. Part 2 introduced and deployed an interaction-focused mechanism test (wd_batchnoise_interaction) aimed at causal refinement of WD timing effects, with novelty checks documented against prior literature queries.
4. Immediate scientific interpretation from Part 2 is pending returned result payloads; this session primarily advanced test coverage and queue targeting rather than delivering new completed-result science.