ExperimentEXP-2026-0107v0.1

Experiment E — token / FLOPs proxy failure test (declared)

Executions of the same task quality under different languages, verbosity, context lengths and memory pressure, comparing token count, FLOPs, energy, time, memory traffic and N_μ^eff to see where token and FLOPs stop tracking cost and work. Declared as the last v0.2 experiment; not run.

Research status: IDEA only a question or a concept so far
Evidence level: E0 Concept only
Result: INCONCLUSIVE
Data basis: NOT RUN Designed and validated as a harness; never executed with a real model.
Version: 0.1
Updated: 2026-09-02
Created: 2026-09-02
Domain: Evaluation
Program: PRG-2026-0101 Intelligence Physical Metrology (IPM)
Authors: Neo.K (EveMissLab)
AI collaborators: Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)

Hypothesis

hypothesis: F1 and F2: N_μ^eff per token drifts across phrasings/languages, and same-FLOPs executions differ in T, E, B_M, V_M.

Procedure

procedure: Matched-quality executions varied in language, verbosity, context and memory pressure; record TokenCount, FLOPs, E, T, B_M, N_μ^eff.

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-2026-0107` Experiment E — token / FLOPs proxy failure test (declared)	`tests`	`CLM-2026-0101` F1 — Token hypothesis	`ACTIVE`	`REL-2026-0499`
`EXP-2026-0107` Experiment E — token / FLOPs proxy failure test (declared)	`tests`	`CLM-2026-0102` F2 — FLOPs sufficiency	`ACTIVE`	`REL-2026-0500`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0107/

Machine-readable

/ai/experiments/EXP-2026-0107/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