Sprint 003 findings + Sprint 004 pipeline decision audit plan

Browse Source

- split_prereq_op_dataset.py: extract accepted/rejected/schema-drift rows per gate
- gen_prereq_op_rsa_data.py: convert accepted rows to Fabricate TSV format
- 1000-run extracted dataset: 1297 accepted prereq_op rows, 24 schema-drift
- Key finding: needs_validate_intake always True; effective gate is binary
  (needs_resolve_dependencies 77%, needs_architect_review 20%)
- Key finding: run corpus text is template-driven (17 unique inputs) — not
  suitable for text-based training; RSA exists before ideal input is available
- ROADMAP: gate lifecycle framing — goal is choice of backend, not forced
  determinism; RSA operates on imperfect/mixed/incomplete input by design
- training_data_strategy.md: taskitem-as-self-contained-work-unit constraint
- SPRINT-003: updated with 1000-run results, text audit findings, design constraints
- SPRINT-004: pipeline decision audit — manual walkthrough of every decision
  from project description to generated artifact; execute next session

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

...

This commit is contained in:

Bill Holcombe

2026-04-12 21:43:17 -06:00

parent 0253a92f28

commit c4569de9ca

18 changed files with 10209 additions and 4 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1297

semantic/prereq_op_dataset_1000/accepted.ndjson Normal file

File diff suppressed because one or more lines are too long

24

semantic/prereq_op_dataset_1000/rejected.ndjson Normal file

File diff suppressed because one or more lines are too long

24

semantic/prereq_op_dataset_1000/schema_drift.ndjson Normal file

File diff suppressed because one or more lines are too long