ExperimentEXP-2026-0201v0.1

Phase I company and bridge measurements (2026-09-20 to 2026-09-22)

The exploratory code-search pilot, the AI-native company existence check (N = 12), two tiny real blind runs (6 + 6), the 60-repository stratified bridge across three commercial strata, the README pass on the same panel and the 3×3 surface matrix.

Research status: STABLE the current conclusions are relatively stable
Evidence level: E2 Controlled experiment
Result: MIXED
Data basis: BLIND PUBLIC DATA Real public files measured by an algorithm inside a sealed process. No person and no AI model read them; only coded features left the process. The numbers may be distorted.
Version: 0.1
Updated: 2026-10-13
Created: 2026-09-22
Domain: Privacy, Evaluation
Program: PRG-2026-0201 AI Agent Publication Boundary and Security Closure (APBSC)
Authors: Neo.K (EveMissLab)
AI collaborators: ChatGPT (OpenAI) — RBPM v0.8.3 instrument and its Phase I evidence packages

Runs

run_count

metrics

code_search_raw_ratio_with_Users_prefix

CLAUDE.md: 3.55%
AGENTS.md: 2.13%
.cursor/rules: 1.45%

company_check

candidates: 12
with_public_ai_surface: 11
with_bounded_finding: 2
escalation_required: 0

tiny_runs

samples

features

workstation_path: 1
personal_identity_context: 2

n60_bridge_levels

L0_GENERIC: 43
L1_OPERATIONAL_NON_SENSITIVE: 15
L3_LIKELY_PUBLICATION_BOUNDARY_INCIDENT: 2

readme_pass_levels

L0_GENERIC: 46
L1_OPERATIONAL_NON_SENSITIVE: 13

surface_matrix_high_warning

GENERAL_README: 0
59
AI_INSTRUCTION_SELECTED: 2
40
GOVERNANCE_FAMILY: 0
51

Limitations

limitations: Exploratory, non-probability frame; not a prevalence estimate.
No human checked any finding; secret-like means a shape and was never tested.
Current public state only, observed once.

Results

Source	Relation	Target	Status	ID
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`produces`	`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`ACTIVE`	`REL-2026-0575`

Recorded fields

completed_at: 2026-09-22

Relations

Source	Relation	Target	Status	ID
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`runs_on`	`SYS-2026-0201` RBPM v0.8.3 — the frozen researcher-blind measurement instrument	`ACTIVE`	`REL-2026-0571`
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`produced`	`DAT-2026-0201` Phase I released features — company panel, README pass and surface matrix	`ACTIVE`	`REL-2026-0572`
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`tests`	`THY-2026-0203` Agent context as an egress surface	`ACTIVE`	`REL-2026-0573`
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`tests`	`THY-2026-0207` Researcher-blind privacy measurement	`ACTIVE`	`REL-2026-0574`
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`produces`	`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`ACTIVE`	`REL-2026-0575`
`EXP-2026-0204` R1 — re-executing the frozen RBPM v0.8.3 package	`evaluates`	`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`ACTIVE`	`REL-2026-0621`

History and provenance

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0201/

Machine-readable

/ai/experiments/EXP-2026-0201/index.json

Snapshot

AI-SNAPSHOT-v0.1-58e716495670

Provenance

source: EveMissLab research collection: AI Agent Publication Boundary and Security Closure (真本體論14)
extracted_by: Splice (Claude Code), reading the open-source release's own manifests, locks and pooled outputs, and the hashes of the internal drafts
extracted_at: 2026-10-13
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