STEM BIO-AI Explain Report
Target  : Runchuan-BU/BioClaw
Policy  : default [ca-policy-1.0; mirror_only; authoritative_release]
Policy Mode: mirror-only in 1.7.8 — selected profile metadata is surfaced in artifacts, but authoritative scan scoring still follows deterministic runtime constants.
Score   : 60 / 100  (T2 Caution)
Replic  : 35 / 100  (R1)
========================================================================

S1_readme_bio_terms  [DETECTED]
  [001]  README.md
         reason  : README exposes bio/medical vocabulary.
         match   : bioinformatics, genomic, clinical

S1_clinical_boundary  [NOT_DETECTED]
  [001]  (repository)
         reason  : No evidence detected for S1_clinical_boundary. (Missing "Not for clinical use")

S1_R2_unsupported_legal_or_compliance_claim  [NOT_DETECTED]
  [001]  (repository)
         reason  : No explicit unsupported HIPAA claims detected.

S3_T1_workflow_files  [DETECTED]
  [001]  .github/workflows
         reason  : Workflow files present.

S3_T2_domain_tests  [NOT_DETECTED]
  [001]  (repository)
         reason  : No tests surface detected with clear bio-domain specificity.

S3_T3_changelog_release_hygiene  [NOT_DETECTED]
  [001]  (repository)
         reason  : No changelog or release-history file exists.

C5_compliance_boundary_integrity  [DETECTED]
  [001]  README.md
         reason  : Clinical-adjacent surfaces exist without an explicit non-diagnostic/non-clinical boundary.
         status  : WARN

========================================================================
Bio Deterministic Diagnostics

  SMILES Surface Integrity           not_detected=1
  SMILES RDKit Validation            not_detected=1
  Silent Mock Fallback               not_detected=1
  Traceability Manifest Surface      not_detected=1

========================================================================
AIRI Coverage

  covered_count                  2
  detector_scope_total           32
  coverage_rate                  0.062
  bundle_scope                   curated_medical_clinical_subset

  covered examples:
    - 24.01.03 | Safe exploration problem with widely deployed AI assistants | covered_by=C5_compliance_boundary_integrity
    - 69.01.00 | False information | covered_by=C5_compliance_boundary_integrity

========================================================================
DISCLAIMER: Evidence-surface pre-screen only.
Not clinical certification, regulatory clearance, or medical advice.