Paper b13 — Extraction Prompt (Session Logs -> Knowledge Base)

Run this prompt in a Claude Code session BEFORE running the b13 writing prompt. It produces a structured knowledge base (KB) that the writing session loads as pre-digested input.

Note

Lessons from b12 extraction (2026m04d04): Categories A (Design Rationales) and F (OSCR/BABL) yield richest material. Organize KB by model structure (stages), not by category. 80% restate / 20% point. See BB/extraction-lessons-learned-for-next-extractons.rst for full recommendations. This prompt incorporates those lessons.

/effort max

TASK: Extract material from FORGE and PROMY session logs into a structured
knowledge base (KB) for writing Paper b13 (e7He Model) in the HEAVEN
study series. This is a preparation step --- you are NOT writing the
paper itself.

PHASE 1 --- ORIENT (read these in order):

1. .claude/CLAUDE.md --- especially Core Principle, Language Rules, LLog
   Rules, and the EDEN/BABL/ZION framework
2. The e7He model source (this is the STRUCTURE you will organize around):
   - source/matheology/model/e7he/ (read all files: overview, axioms,
     theorems, symbols)
3. The b13 writing prompt (this tells you what the paper NEEDS):
   source/matheology/hell/ll/study/b/13/b13-prompt-writing.rst
4. Paper b11 (PET) as format reference:
   source/matheology/hell/ll/study/b/11/study_ll_2026m04d03_a1-pet-paper.rst
5. The b12 extraction KB (for material already tagged as b13-relevant):
   source/matheology/hell/ll/study/b/12/study_ll_2026m04d04_a2-e7day-extraction-kb.rst
   (check the "Notes for Other Papers / For Paper b13" section)

After reading these, you should know:
- The 7 hero journey stages and their BABL temptation encodings
- The 14 axioms (7 prerequisites + 7 stage axioms) and 7+ theorems
- What the paper needs to cover
- What material was already flagged during the b12 extraction

PHASE 2 --- EXTRACT (walk each log systematically):

PRIMARY SOURCE --- read ALL of this file:
- source/matheology/hell/ll/forge/b/13/llog.rst (sa3, ~10K lines ---
  this is the PRIMARY e7He development session)

SECONDARY SOURCES --- scan for b13-relevant material:
- source/matheology/hell/ll/forge/b/12/llog.rst (sa2, ~14K lines ---
  th7 Gate 5 development, ~lines 8650-8920, supervillain theorem)
- source/matheology/hell/ll/promy/b/11/promy_ll_2026m03d29_e7he-pipeline-test.rst
- source/matheology/hell/ll/promy/b/12/promy_ll_2026m03d30_audit-e7he-reap.rst

For each log, extract ONLY material relevant to paper b13 (e7He).
Focus on these categories:

A. DESIGN RATIONALES --- Why was each stage formulated this way? What
   alternatives were considered? Why these specific BABL encodings?

B. TEMPER REFINEMENTS --- How did Iron Maiden testing change the
   formulations? Which axioms were rescued, reclassified, or reformulated?

C. REJECTED ALTERNATIVES --- Ideas explored but deliberately excluded.
   IMPORTANT: Look for ideas that appeared in HEAT but NOT in STRIKE ---
   the absence IS the rejection. (Lesson from b12: explicit rejections
   are rare; implicit ones are common.)

D. CONNECTIONS TO e7Day/PET/JUB --- How e7He relates to e7Day submodels,
   PET axioms, and JUB axioms. Especially: th7 Gate 5 instantiation,
   m6.ax4 cross-model load-bearing, ax19 h* dependency.

E. KEY INSIGHTS --- Observations, analogies, or explanations not captured
   in the formal axiom/theorem files. The Ie framework, 4D scope, ridge
   dynamics, and stopping-outcome analysis.

F. OSCR/BABL MATERIAL --- The binary temptation encoding, BA/ASH/MOL
   stage interactions, CWA mechanism, silent corruption gradient.

G. STOPPING OUTCOMES --- (NEW category for b13) Material about what
   happens when the hero stops at each stage. Irrelevance vs.
   supervillain outcomes. Rest vs. stopping distinction.

SCOPE RULE: Material about e7Day system-level architecture (submodel
construction, meta-axioms, system theorems) belongs to b12, not b13.
Skip it. EXCEPTION: If e7Day material illuminates an e7He concept,
note it briefly with a pointer.

PHASE 3 --- BUILD THE KB:

Save the knowledge base at:
source/matheology/hell/ll/study/b/13/study_ll_2026m04dNN_b13-e7he-extraction-kb.rst
(replace NN with today's date)

Structure the KB as follows:
1. One section per e7He stage (m0 prerequisites, m1-m7 stages) + one for
   theorems + one for BABL/ZION + one for cross-paper connections
2. Within each section, organize by the categories above (A-G)
3. For each extracted item: state the key point concisely, give the
   source reference with approximate line number. Restate when more
   efficient than pointing (target ~80% restate / 20% point).
4. End with a "Notes for Other Papers" section for material belonging
   to b14-b17, not b13.

LLOG: Create an extraction session llog at:
source/matheology/hell/ll/study/b/13/study_ll_2026m04dNN_b13-e7he-extraction-llog.rst
(replace NN with today's date)
Follow LLog Rules in CLAUDE.md: append-only, verbatim prompts.

BUILD CHECK: Run "make dev" after writing to check for RST errors.

PHASE 4 --- RETROSPECTIVE (do this LAST, append to the llog):

Answer the same 5 questions as the b12 retrospective (what worked, what
did not, KB structure, pointing vs. restating, recommendations for b14).
Also answer:
6. Did the new category G (Stopping Outcomes) add value?
7. Was the b12 KB's "Notes for Other Papers" section useful as a
   starting pointer?

Append recommendations to:
source/matheology/heaven/study/BB/extraction-lessons-learned-for-next-extractons.rst
(do NOT overwrite --- APPEND a new section for b13 lessons).

WHAT NOT TO DO:
- Do NOT write the paper --- that is a separate session
- Do NOT use "validate/verify" --- use "test/check" (Language Rule 4)
- Do NOT use YYYY-MM-DD dates --- use YYYYmMMdDD (Language Rule 6)
- Do NOT duplicate the full llog content --- extract, summarize, and point
- Do NOT skip the secondary sources --- sa2 has th7 Gate 5, PROMY has pipeline testing