|
analysis
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
configs
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
docs
|
Phase 00: environment audit, corpus retrieval, mandate preservation |
|
|
evaluators
|
Transfer tasks T1-T3 (validated, frozen, 24 runs registered); amendment A-004... |
|
|
evidence
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
paper
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
protocol
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
release
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
reports
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
research
|
Task suite (F1,F2,F4,F5,F6 + partial F3), evaluator validation, analysis... |
|
|
results
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
runs
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
src
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
tasks
|
Transfer tasks T1-T3 (validated, frozen, 24 runs registered); amendment A-004... |
|
|
tests
|
Transfer results and section, amendment A-006 (prompt quoting) with post-fix... |
|
|
.DS_Store
|
Transfer tasks T1-T3 (validated, frozen, 24 runs registered); amendment A-004... |
|
|
.gitignore
|
Phase 11-12: adversarial reviews addressed (A-007, A-008), post-fix verification... |
|
|
CLAUDE.md
|
Phase 00: environment audit, corpus retrieval, mandate preservation |
|
|
Makefile
|
Disclosure statement, failure analysis, final report, release assembly, series... |
|
|
pyproject.toml
|
Phases 02-05: protocol, harness, viewer/capture, live smoke experiment (4 arms) |
|
|
README.md
|
Task suite (F1,F2,F4,F5,F6 + partial F3), evaluator validation, analysis... |
|
|
texput.log
|
Main benchmark running; appendix generators, gallery, reflexive draft, paper... |
|