ExperimentEXP-2026-0106v0.1
Experiment D — physical trace alignment (declared)
On one machine, align GPU power telemetry, latency, peak memory, memory bandwidth and device occupancy with execution events — the telemetry side that XA-03 already provides — before any claim about data-center energy. Declared as the second v0.2 experiment in the recommended order; the pilot's XA-03 traces are its first raw material, but the alignment study itself has not been run.
Hypothesis
hypothesis- F2 (partial): with operations controlled, time, energy, memory traffic and residency still vary independently; device-level traces can be aligned to semantic-level events.
Procedure
procedure- Same hardware, matched workloads differing in memory pattern; XA-03 telemetry at reduced instrument cost (NVML) aligned to trajectory/tool/verifier spans.
Runs
run_count- 0
Interpretation
interpretation- Declared, not run; listed so the program's falsifiable propositions each have their intended test on record.
Limitations
limitations- No protocol package exists yet; the canonical index gives the design in one paragraph.
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
EXP-2026-0106 Experiment D — physical trace alignment (declared) | tests | CLM-2026-0102 F2 — FLOPs sufficiency | ACTIVE | REL-2026-0496 |
EXP-2026-0106 Experiment D — physical trace alignment (declared) | tests | THY-2026-0105 Physical computation cost vector and computational spacetime | ACTIVE | REL-2026-0497 |
EXP-2026-0106 Experiment D — physical trace alignment (declared) | tests | THY-2026-0104 Energy accounting hierarchy and thermodynamic type safety | ACTIVE | REL-2026-0498 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/experiments/EXP-2026-0106/
- Machine-readable
/ai/experiments/EXP-2026-0106/index.json- Snapshot
AI-SNAPSHOT-v0.1-fe85b9694a45- Provenance
source- EveMissLab research collection: Intelligence Physical Metrology (真本體論13)
extracted_by- Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports
extracted_at- 2026-09-11
generator- tools/extract_all.py
claim_boundary- status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports