bench: emergent stress-test — 3-word triangulation (blue-moon cadence)

scripts/bench_emergent.py + make bench-emergent + design doc.
Random word triangulation surfaces failure modes the curated
bench/qa_questions.txt doesn't reach.

Loop:
  /usr/share/dict/words → random.sample(3) →
  Hermes @ temp=0.8 weaves a creative question →
  aborist student answers via query() →
  append journey to bench/emergent_log.jsonl
  (teacher review = separate manual step, fox brings entries to
   Opus & gets judgment to append)

Word filter: ^[a-z]{5,12}$ after lowercasing. Skips short words
(too vague) + very long words (Hermes can't weave them).

Cadence: NOT every commit. ~20s per cycle (Hermes generator +
aborist student); N=10 ≈ 4 min, N=50 ≈ 17 min. Most cycles land
UNGROUNDED-by-corpus-design (random triplets rarely overlap with
2010-11 Wikipedia coverage); the interesting cases are STRICT/
HYBRID surprises and the verifier-disagreement cases the teacher
catches.

Teacher review is intentionally out of the bench script:

  - separation of concerns: generation is automated, judgment is
    contextual & needs the corpus-knowledge frame ("is this a
    2010 Wikipedia gap or a substrate failure?")
  - future flexibility: today the teacher is Claude Opus 4.7
    in this conversation; tomorrow GPT-5 or a review committee.
    Swapping teachers is a workflow change, not a code change.

Teacher output schema (appended to the same JSONL line):
  teacher.match           bool
  teacher.audit_agreement agree|disagree|unsure
  teacher.novelty_class   known_truth_grounding | emergent_synthesis
                          | novel_claim | no_signal
  teacher.score_0_5       0..5
  teacher.bench_max_signal retrieval | warrant | prompt | nil
  teacher.reasoning       one sentence
  teacher.reviewed_by     model id
  teacher.reviewed_ts     unix ts

Smoke verified (N=2, seed=42): 41s wall-clock, both UNGROUNDED
(expected — random triplets rarely overlap 2010 Wikipedia).
Append-only log seeded with the smoke entries.

Future flag (not yet wired): --generator-endpoint &
--student-endpoint to swap LLM upstreams per role.

Full design + teacher protocol: docs/bench-emergent-design.md.

bench/emergent_log.jsonl

@@ -0,0 +1,2 @@
+{"ts": 1777740048, "iso_ts": "2026-05-02T16:40:48Z", "words": ["brainier", "Goldman", "jealously"], "question": "Could the remarkable intellect of a brainier individual, possibly even surpassing that of the renowned investment banker Goldman, inadvertently lead to feelings of jealously among those who have not yet achieved such academic and professional heights?", "question_gen_seconds": 1.01, "answer": "{\"claims\":[{\"text\":\"A brainier individual surpassing the intellect of a renowned investment banker like Goldman could potentially lead to feelings of jealousy among those who have not yet achieved similar academic and professional heights.\",\"evidence_ids\":[\"E1\",\"E2\"]}]}", "audit_mode": "UNGROUNDED", "verifier_method": "claim_lattice", "n_quotes": 2, "n_verified": 0, "violation_kinds": ["CITATION_MISMATCH"], "sources": [{"title": "Virtue jurisprudence", "uri": "https://en.wikipedia.org/wiki/Virtue_jurisprudence", "used": false}, {"title": "Dirty War", "uri": "https://en.wikipedia.org/wiki/Dirty_War", "used": false}, {"title": "Salvation", "uri": "https://en.wikipedia.org/wiki/Salvation", "used": false}, {"title": "The Lord of the Rings film trilogy", "uri": "https://en.wikipedia.org/wiki/The_Lord_of_the_Rings_film_trilogy", "used": false}, {"title": "Central Philippine University", "uri": "https://en.wikipedia.org/wiki/Central_Philippine_University", "used": false}, {"title": "Koreans in Japan", "uri": "https://en.wikipedia.org/wiki/Koreans_in_Japan", "used": false}, {"title": "Korean Buddhist sculpture", "uri": "https://en.wikipedia.org/wiki/Korean_Buddhist_sculpture", "used": false}, {"title": "Jihad", "uri": "https://en.wikipedia.org/wiki/Jihad", "used": false}], "cache_key": "31860906e6424914f2f98dc515b189c42d4dce8e140245e691c281e73f09b707", "answer_mode": "claim_lattice", "answer_seconds": 25.13, "total_seconds": 26.14, "student_error": null, "teacher": null}
+{"ts": 1777740074, "iso_ts": "2026-05-02T16:41:14Z", "words": ["hastes", "freelanced", "coincident"], "question": "How do these three seemingly unrelated concepts - hastes, freelanced, and coincident - unexpectedly intertwine in the context of a time-crunched artist rushing to complete a project, resulting in a unique and unanticipated outcome?", "question_gen_seconds": 0.71, "answer": "{\"claims\":[{\"text\":\"In a time-crunched artist rushing to complete a project, hastes can lead to freelanced, coincident elements unexpectedly intertwining, resulting in a unique and unanticipated outcome.\",\"evidence_ids\":[\"E1\",\"E2\",\"E3\"]}]}", "audit_mode": "UNGROUNDED", "verifier_method": "claim_lattice", "n_quotes": 3, "n_verified": 0, "violation_kinds": ["CITATION_MISMATCH", "TOO_MANY_EVIDENCE_IDS"], "sources": [{"title": "Time reversibility", "uri": "https://en.wikipedia.org/wiki/Time_reversibility", "used": false}, {"title": "Wall clock time", "uri": "https://en.wikipedia.org/wiki/Wall_clock_time", "used": false}, {"title": "Ordinary least squares", "uri": "https://en.wikipedia.org/wiki/Ordinary_least_squares", "used": false}, {"title": "Bernheim Arboretum and Research Forest", "uri": "https://en.wikipedia.org/wiki/Bernheim_Arboretum_and_Research_Forest", "used": false}, {"title": "Dirac large numbers hypothesis", "uri": "https://en.wikipedia.org/wiki/Dirac_large_numbers_hypothesis", "used": false}, {"title": "1000000000 (number)", "uri": "https://en.wikipedia.org/wiki/1000000000_(number)", "used": false}, {"title": "José Antonio Conde", "uri": "https://en.wikipedia.org/wiki/José_Antonio_Conde", "used": false}, {"title": "L'étoile (opera)", "uri": "https://en.wikipedia.org/wiki/L'étoile_(opera)", "used": false}], "cache_key": "3aca45f06eea324602f28f120e6ca353c49107082e28c4392e85904c8ef735b8", "answer_mode": "claim_lattice", "answer_seconds": 13.51, "total_seconds": 14.23, "student_error": null, "teacher": null}