mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-04 07:47:27 +01:00
garrytanandcapy-ai[bot]
28e483eca3
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
661 lines
25 KiB
JSON
661 lines
25 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"note": "R56 evidence ledger (ETHOS.md: 9. Earn Its Place). One row per inventory key (docs/inventory.md lists them); bin/gstack-inventory --check validates it and test/inventory.test.ts runs that check. Statuses and their required fields: helps, no-effect, hurts need sources, models (frontier per R54), prompt: preset, scope and masked: true, and no-effect and hurts also r48 {verdict, ref}; untested needs plan (a reference, or none only when grandfathered), and a new part also reason, owner and measure_by; safety needs reason. prior lists earlier results that do not count yet, with why. Seeded 2026-11-02 from GEVA-2's table (org-gstack-gbrain/research/gstack-part-evidence.json, gstack dac71371a); every row present at that base is grandfathered.",
|
|
"seed_source": "org-gstack-gbrain/research/gstack-part-evidence.json (GEVA-156 for GST-915, 2026-11-02, gstack-evals main 409ff47)",
|
|
"parts": {
|
|
"autoplan": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-3 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: autoplan: untested (never measured)"
|
|
},
|
|
"benchmark": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: benchmark: untested (never measured)"
|
|
},
|
|
"benchmark-models": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: benchmark-models: untested (never measured)"
|
|
},
|
|
"browse": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: browse: untested (never measured)"
|
|
},
|
|
"canary": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: canary: untested (never measured)"
|
|
},
|
|
"captain": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: captain: untested (never measured)"
|
|
},
|
|
"careful": {
|
|
"status": "safety",
|
|
"grandfathered": true,
|
|
"reason": "safety guard: warns before destructive commands (rm -rf, DROP TABLE, force-push); kept on that reason, an average score cannot see the rare bad run it stops",
|
|
"seed": "GEVA-2, 2026-11-02: careful: exempt (safety guard)"
|
|
},
|
|
"claude-code": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: claude-code: untested (never measured)"
|
|
},
|
|
"codex": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "not in GEVA-2's table (2026-11-02); never measured"
|
|
},
|
|
"context-restore": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: context-restore: untested (never measured)"
|
|
},
|
|
"context-save": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: context-save: untested (never measured)"
|
|
},
|
|
"cso": {
|
|
"status": "safety",
|
|
"grandfathered": true,
|
|
"reason": "security: supported security findings with explicit coverage; kept on its security reason (GEVA-2 marks it exempt; GStack Minder may reclassify it)",
|
|
"seed": "GEVA-2, 2026-11-02: cso: exempt (security audit skill, treated as exempt; GStack Minder may reclassify)"
|
|
},
|
|
"design-consultation": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-10 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: design-consultation: untested (never measured)"
|
|
},
|
|
"design-html": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: design-html: untested (never measured)"
|
|
},
|
|
"design-motion": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: design-motion: untested (never measured)"
|
|
},
|
|
"design-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-9 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: design-review: untested (never measured)"
|
|
},
|
|
"design-shotgun": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: design-shotgun: untested (never measured)"
|
|
},
|
|
"deslop-shared-libs": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: deslop-shared-libs: untested (never measured)"
|
|
},
|
|
"devex-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: devex-review: untested (never measured)"
|
|
},
|
|
"diagram": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: diagram: untested (never measured)"
|
|
},
|
|
"document-generate": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: document-generate: untested (never measured)"
|
|
},
|
|
"document-release": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: document-release: untested (never measured)"
|
|
},
|
|
"eval-plan": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: eval-plan: untested (never measured)"
|
|
},
|
|
"freeze": {
|
|
"status": "safety",
|
|
"grandfathered": true,
|
|
"reason": "safety guard: hard-blocks edits outside one directory; kept on that reason",
|
|
"seed": "GEVA-2, 2026-11-02: freeze: exempt (safety guard)"
|
|
},
|
|
"gstack": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: gstack (root skill): untested (never measured)",
|
|
"aliases": [
|
|
"gstack (root skill)"
|
|
]
|
|
},
|
|
"gstack-upgrade": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: upgrade: untested (never measured)",
|
|
"aliases": [
|
|
"upgrade"
|
|
]
|
|
},
|
|
"guard": {
|
|
"status": "safety",
|
|
"grandfathered": true,
|
|
"reason": "safety guard: careful and freeze together; kept on that reason",
|
|
"seed": "GEVA-2, 2026-11-02: guard: exempt (safety guard)"
|
|
},
|
|
"health": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: health: untested (never measured)"
|
|
},
|
|
"investigate": {
|
|
"status": "no-effect",
|
|
"grandfathered": true,
|
|
"sources": [
|
|
"GST-814 (HARN-1, 2026-11-02)",
|
|
"org-gstack-gbrain handoffs/HARN-14/hard-follow-2026-11/decision-rule.md"
|
|
],
|
|
"models": [
|
|
"claude-opus-5-5"
|
|
],
|
|
"prompt": "preset",
|
|
"scope": "skill step procedure follow rate: 0 of 46 gstack sessions ran any step (0 of 30 on the claude_code preset); body loaded every time; the outcome check voided at ceiling (no-gstack fixed 8 of 8)",
|
|
"masked": true,
|
|
"r48": {
|
|
"verdict": "CUT-CANDIDATE",
|
|
"ref": "GST-938 (GSTA-251 plans hooks-or-drop)"
|
|
},
|
|
"plan": "R3 (GEVA-2, 2026-11-02): gstack-evals wiki/plans/2026-11-01-geva-101-r48-follow-ups-prereg (#112, main f0b81c0) and its amendment (open PR #133), told /investigate vs no gstack on SWE-bench Verified, preset, Opus 5.5 then GPT-6.1 Sol",
|
|
"prior": [
|
|
{
|
|
"ref": "gstack-evals #109 stacks round 1 TB2 (GEVA-89, GEVA-93), wiki/board/2026-11-01-geva-93-stacks-round-1-tb2-results",
|
|
"why": [
|
|
"stub",
|
|
"no-exposure",
|
|
"unmasked"
|
|
],
|
|
"note": "Opus +3 points [-3, +9] at 1.9x cost; debug report in 0 of 111 trials; particle-1 -5 [-14, +1]"
|
|
},
|
|
{
|
|
"ref": "GSTA-12 Lane B quick look 2, wiki/board/2026-10-29-gsta-12-laneb-quick-2-results",
|
|
"why": [
|
|
"stub",
|
|
"unmasked"
|
|
],
|
|
"note": "Opus gstack minus none -7 [-13, -2] at 1.7x cost; did not replicate"
|
|
},
|
|
{
|
|
"ref": "GSTA-30 Lane B quick look 3 (#89), wiki/board/2026-10-30-gsta-30-laneb-quick-3-results",
|
|
"why": [
|
|
"stub",
|
|
"small-tier"
|
|
],
|
|
"note": "gstack arms on Sonnet, particle-1, DeepSeek and Haiku; Opus ran the none arm only"
|
|
},
|
|
{
|
|
"ref": "HARN-14 replication (harness-evals #181, unmerged)",
|
|
"why": [
|
|
"stub",
|
|
"small-tier"
|
|
],
|
|
"note": "Haiku 5.5: gstack minus none +3.5 [-12.3, +20.0]"
|
|
}
|
|
],
|
|
"seed": "GEVA-2, 2026-11-02: investigate: measurement under way (R3)"
|
|
},
|
|
"ios-clean": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ios-clean: untested (never measured)"
|
|
},
|
|
"ios-design-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ios-design-review: untested (never measured)"
|
|
},
|
|
"ios-fix": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ios-fix: untested (never measured)"
|
|
},
|
|
"ios-qa": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ios-qa: untested (never measured)"
|
|
},
|
|
"ios-sync": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ios-sync: untested (never measured)"
|
|
},
|
|
"land-and-deploy": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-8 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: land-and-deploy: untested (never measured)"
|
|
},
|
|
"landing-report": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: landing-report: untested (never measured)"
|
|
},
|
|
"learn": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"prior": [
|
|
{
|
|
"ref": "GSTA-13, GEVA-54 and GEVA-65 Lane A runs (wiki/board/2026-10-28-gsta-13-quick-look-3-results and the GEVA-54 and GEVA-65 posts)",
|
|
"why": [
|
|
"stub",
|
|
"no-true-no-gstack-arm",
|
|
"ceiling"
|
|
],
|
|
"note": "Opus contract tasks 27/30 vs 27/30"
|
|
},
|
|
{
|
|
"ref": "GEVA-65 Lane A rerun row 5 (GPT-6.1 Sol in Codex)",
|
|
"why": [
|
|
"not-claude-code",
|
|
"no-true-no-gstack-arm"
|
|
],
|
|
"note": "Sol failed the no-code-change safety task in 5 of 9 skill trials vs 0 of 3 without; small n, a lead to check, not a hurts verdict"
|
|
}
|
|
],
|
|
"seed": "GEVA-2, 2026-11-02: learn: untested (unfair test: SDK stub; no true no-gstack arm; Opus at ceiling; Sol ran in Codex, not Claude Code)"
|
|
},
|
|
"make-pdf": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: make-pdf: untested (never measured)"
|
|
},
|
|
"modernize": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: modernize: untested (never measured)"
|
|
},
|
|
"office-hours": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"prior": [
|
|
{
|
|
"ref": "GSTA-13 quick look 3 Lane A, wiki/board/2026-10-28-gsta-13-quick-look-3-results",
|
|
"why": [
|
|
"stub",
|
|
"no-true-no-gstack-arm"
|
|
],
|
|
"note": "contract tasks on Opus: gstack 74% vs none 28%; the tasks grade the skill's own contract, a manipulation check, not lift"
|
|
},
|
|
{
|
|
"ref": "GEVA-65 Lane A rerun, wiki/board/2026-10-31-geva-65-lanea-shakedown-rerun-results",
|
|
"why": [
|
|
"stub",
|
|
"no-true-no-gstack-arm"
|
|
],
|
|
"note": "Opus before 0.67, after 0.76, none 0.36"
|
|
}
|
|
],
|
|
"seed": "GEVA-2, 2026-11-02: office-hours: untested (unfair test: SDK stub; no true no-gstack arm; tasks grade the skill's own contract, a manipulation check, not lift)"
|
|
},
|
|
"open-gstack-browser": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: open-gstack-browser: untested (never measured)"
|
|
},
|
|
"pair-agent": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: pair-agent: untested (never measured)"
|
|
},
|
|
"plan-ceo-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-5 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"prior": [
|
|
{
|
|
"ref": "CEO panel v2 admission (GEVA-142), wiki/board/2026-11-02-geva-142-ceo-panel-v2-admission-results (open PR #131)",
|
|
"why": [
|
|
"ceiling",
|
|
"unmasked"
|
|
],
|
|
"note": "preset, Opus 5.5 only: must-fix recall 1.00 in all three arms; plain invocation ran the procedure in 0 of 16"
|
|
},
|
|
{
|
|
"ref": "Planning R1a pilot (GEVA-102), wiki/board/2026-11-01-geva-102-planning-r1a-pilot-stop (#114)",
|
|
"why": [
|
|
"stub",
|
|
"ceiling",
|
|
"unmasked"
|
|
],
|
|
"note": "none-opus 8/8; gstack-opus read the sections file in 0 of 4"
|
|
}
|
|
],
|
|
"r48": {
|
|
"verdict": "FIX-METHOD",
|
|
"ref": "CEO panel v2 admission (GEVA-142, open PR #131): FIX-METHOD on the panel, a harder panel is planned"
|
|
},
|
|
"seed": "GEVA-2, 2026-11-02: plan-ceo-review: untested (unfair test: ceiling, control 12 of 12 so no MDD; plain invocation ran the procedure in 0 of 16)"
|
|
},
|
|
"plan-design-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-7 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: plan-design-review: untested (never measured)"
|
|
},
|
|
"plan-devex-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-6 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: plan-devex-review: untested (never measured)"
|
|
},
|
|
"plan-eng-review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-2 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: plan-eng-review: untested (never measured)"
|
|
},
|
|
"plan-tune": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: plan-tune: untested (never measured)"
|
|
},
|
|
"qa": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: qa: untested (never measured)"
|
|
},
|
|
"qa-only": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: qa-only: untested (never measured)"
|
|
},
|
|
"retro": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: retro: untested (never measured)"
|
|
},
|
|
"review": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "R2 (GEVA-2, 2026-11-02): gstack-evals wiki/plans/2026-11-02-geva-122-r2-amendment (#129, main eae6efc), told /review vs a no-gstack arm, Opus 5.5, preset on both arms",
|
|
"prior": [
|
|
{
|
|
"ref": "gstack-evals #108 stacks round 1 review (GEVA-89), wiki/board/2026-11-01-geva-89-stacks-round-1-review-results",
|
|
"why": [
|
|
"stub",
|
|
"no-exposure",
|
|
"unmasked"
|
|
],
|
|
"note": "Opus 5.5 blocking recall 9.5% vs 7.1%, +2.4 points [-6.4, +11.1]; specialists and adversarial pass ran in 0 of 66 sessions"
|
|
},
|
|
{
|
|
"ref": "gstack-evals #120 R1 blind re-judge (GEVA-113), wiki/board/2026-11-01-geva-113-r1-blind-rejudge-results",
|
|
"why": [
|
|
"stub",
|
|
"unmasked"
|
|
],
|
|
"note": "gstack-opus minus none-opus +3.5 points [-9.6, +16.7]"
|
|
},
|
|
{
|
|
"ref": "GSTA-11 quick look 1 review replay, wiki/board/2026-10-28-gsta-11-review-replay-results",
|
|
"why": [
|
|
"not-claude-code",
|
|
"unmasked"
|
|
],
|
|
"note": "/review's prompts through the Messages API; Opus recall 44% vs 39% plain, 12 bugs"
|
|
}
|
|
],
|
|
"r48": {
|
|
"verdict": "FIX-METHOD",
|
|
"ref": "org-gstack-gbrain/research/why-null-stacks-r1.md (GEVA-100); R2 is the fix"
|
|
},
|
|
"seed": "GEVA-2, 2026-11-02: review: measurement under way (R2)"
|
|
},
|
|
"scrape": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: scrape: untested (never measured)"
|
|
},
|
|
"setup-browser-cookies": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: setup-browser-cookies: untested (never measured)"
|
|
},
|
|
"setup-deploy": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: setup-deploy: untested (never measured)"
|
|
},
|
|
"setup-gbrain": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: setup-gbrain: untested (never measured)"
|
|
},
|
|
"ship": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-4 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"seed": "GEVA-2, 2026-11-02: ship: untested (never measured)"
|
|
},
|
|
"skillify": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: skillify: untested (never measured)"
|
|
},
|
|
"spec": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: spec: untested (never measured)"
|
|
},
|
|
"sync-gbrain": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: sync-gbrain: untested (never measured)"
|
|
},
|
|
"test-audit": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: test-audit: untested (never measured)"
|
|
},
|
|
"ubicloud": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: ubicloud: untested (never measured)"
|
|
},
|
|
"unfreeze": {
|
|
"status": "safety",
|
|
"grandfathered": true,
|
|
"reason": "safety guard: the off switch for freeze's edit restriction; kept with the guard it releases",
|
|
"seed": "GEVA-2, 2026-11-02: unfreeze: exempt (safety guard (undoes freeze))"
|
|
},
|
|
"verify": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "not in GEVA-2's table (2026-11-02); never measured"
|
|
},
|
|
"write-skill": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: write-skill: untested (never measured)"
|
|
},
|
|
"preamble": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "I1 ceremony cut (GEVA-2, 2026-11-02): gstack-evals wiki/plans/2026-11-01-geva-108-ceremony-cut-prereg (#122, main 409ff47) with its G3 amendment (#128), preset, Opus 5.5 and particle-1",
|
|
"prior": [
|
|
{
|
|
"ref": "GEVA-100 exposure counts, org-gstack-gbrain/research/why-null-stacks-r1.md (GEVA-100)",
|
|
"why": [
|
|
"stub",
|
|
"no-exposure"
|
|
],
|
|
"note": "ceremony sections ran in 0 of 66 Opus review sessions and 6 of 111 Opus TB2 trials; no effect estimate"
|
|
}
|
|
],
|
|
"r48": {
|
|
"verdict": "CUT-CANDIDATE",
|
|
"ref": "org-gstack-gbrain/research/why-null-stacks-r1.md (GEVA-100); taken by Garry as the I1 ceremony-cut eval"
|
|
},
|
|
"seed": "GEVA-2, 2026-11-02: preamble (ceremony): measurement under way (I1, ceremony-cut eval)",
|
|
"aliases": [
|
|
"preamble (ceremony)"
|
|
]
|
|
},
|
|
"catalog": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "Run D (GEVA-2, 2026-11-02): gstack-evals wiki/plans/2026-11-01-geva-125-untold-discovery-prereg (#125, main 9820b14), untold gstack vs placebo vs no gstack, preset vs stub, Opus 5.5, GPT-6.1 Sol and particle-1; also measures /investigate's description",
|
|
"prior": [
|
|
{
|
|
"ref": "GSTA-12 Lane B quick look 1, wiki/board/2026-10-29-gsta-12-laneb-quick-results",
|
|
"why": [
|
|
"stub",
|
|
"no-exposure",
|
|
"unmasked"
|
|
],
|
|
"note": "untold skill opened in 0 of 180 gstack-arm trials; Opus gstack minus none +5 [-3, +17]"
|
|
}
|
|
],
|
|
"seed": "GEVA-2, 2026-11-02: always-on skill catalog (descriptions): measurement under way (Run D)",
|
|
"aliases": [
|
|
"always-on skill catalog (descriptions)"
|
|
]
|
|
},
|
|
"capy-skill": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: capy/skill/gstack/SKILL.md (Capy context): untested (never measured)",
|
|
"aliases": [
|
|
"capy/skill/gstack/SKILL.md (Capy context)"
|
|
],
|
|
"note": "loads only in Capy sessions, which the claude_code preset fair test cannot reach yet; needs a Captain call on how to test it"
|
|
},
|
|
"capy-factory": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "none",
|
|
"seed": "GEVA-2, 2026-11-02: capy/skill/gstack/factory.md (Capy context): untested (never measured)",
|
|
"aliases": [
|
|
"capy/skill/gstack/factory.md (Capy context)"
|
|
],
|
|
"note": "loads only in Capy sessions, which the claude_code preset fair test cannot reach yet; needs a Captain call on how to test it"
|
|
},
|
|
"ship-review-panel": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "GEVA-2 registry row R56-1 (org-gstack-gbrain/research/gstack-part-evidence.json registry_rows; proposed, not yet preregistered)",
|
|
"prior": [
|
|
{
|
|
"ref": "gstack-evals #120 R1 blind re-judge (GEVA-113), wiki/board/2026-11-01-geva-113-r1-blind-rejudge-results",
|
|
"why": [
|
|
"stub",
|
|
"not-claude-code",
|
|
"unmasked"
|
|
],
|
|
"note": "arm C minus none +56.9 points [40.5, 72.2]; the none arm ran on the stub, arm C in Capy at another gstack version, on a cohort mined from gstack's own catches"
|
|
},
|
|
{
|
|
"ref": "GSTA-48 review no-loss arm D (#77), wiki/board/2026-10-30-gsta-48-review-noloss-arm-how-to",
|
|
"why": [
|
|
"variant-only",
|
|
"not-claude-code"
|
|
],
|
|
"note": "arm D vs pooled arm C, no no-gstack arm"
|
|
}
|
|
],
|
|
"seed": "GEVA-2, 2026-11-02: ship: review panel (specialist, adversarial, targeted, outside voice, red team): untested (unfair test: none arm on the SDK stub; arms from different harnesses and gstack versions; cohort mined from gstack's own catches)",
|
|
"aliases": [
|
|
"ship: review panel (specialist, adversarial, targeted, outside voice, red team)"
|
|
]
|
|
},
|
|
"ship-docs-audit": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "folded into GEVA-2 registry row R56-4 (ship); proposed, not yet preregistered",
|
|
"seed": "GEVA-2, 2026-11-02: ship: docs audit (Step 14.5): untested (never measured)",
|
|
"aliases": [
|
|
"ship: docs audit (Step 14.5)"
|
|
]
|
|
},
|
|
"autoplan-phases": {
|
|
"status": "untested",
|
|
"grandfathered": true,
|
|
"plan": "folded into GEVA-2 registry row R56-3 (autoplan); proposed, not yet preregistered",
|
|
"seed": "GEVA-2, 2026-11-02: autoplan: CEO, design, DX and eng phases, outside voice: untested (never measured)",
|
|
"aliases": [
|
|
"autoplan: CEO, design, DX and eng phases, outside voice"
|
|
]
|
|
}
|
|
},
|
|
"unmapped": [
|
|
{
|
|
"row": "review: Review Army and adversarial pass",
|
|
"why": "a section inside /review, not its own key; R2 measures it as part of the review row's plan"
|
|
},
|
|
{
|
|
"row": "ship: QA probes (Step 9.2.1)",
|
|
"why": "a step inside /ship with no separate size; folded into the ship row (GEVA-2 registry row R56-4)"
|
|
},
|
|
{
|
|
"row": "gstack as a whole (installed, any skill)",
|
|
"why": "not a single text part; GEVA-2's real-world outcome lane measures it (gstack-evals plan #111), not a measurement plan for any one part"
|
|
}
|
|
]
|
|
}
|