PRIVATE TRIAL DELIVERABLE
Paired campaign filled (20/20). Targeted reruns measured: 0/3. Still not a ranking. Payment never buys a verdict.
Reference Trial
In this perimeter, B corrected 0, kept 10 and broke 0. Same declared model, same declared host, same ten cases. Prompt A against Prompt B. Twenty paired executions. No targeted rerun is measured in this report. Empty cell = not measured. Not a ranking.
| A | B | |
|---|---|---|
| Declared model | grok-4.6 | grok-4.6 |
| Declared host | cursor | cursor |
| Executions present | 20 / 20 | |
| corrected / kept / broken | 0 / 10 / 0 | |
Ten paired cases
| id | seed | A | B | verdict |
|---|---|---|---|---|
rt-01 | 1 | failed | failed | kept |
rt-02 | 2 | failed | failed | kept |
rt-03 | 3 | failed | failed | kept |
rt-04 | 4 | failed | failed | kept |
rt-05 | 5 | failed | failed | kept |
rt-06 | 6 | failed | failed | kept |
rt-07 | 7 | failed | failed | kept |
rt-08 | 8 | failed | failed | kept |
rt-09 | 9 | failed | failed | kept |
rt-10 | 10 | failed | failed | kept |
Candidates for a targeted rerun (up to 3 broken cases): —
The filled campaign pairs twenty distinct existing cards across ten distinct seeds. A/B labels are operator-declared; these cards do not bind a prompt fingerprint. No targeted rerun result is published here. Column B is never invented.
Exterior OLY32 debt
A complete exterior OLY32 is a signed native card from a non-ScoreIA host, at least 20 actions, five seals tracked, and a replay with at least two seals lit. Featured demos are not the OLY index. Empty cell = not measured.
Complete exterior cards: 58 / 109
| card | model | host | actions | seals | missing |
|---|---|---|---|---|---|
oly-026b9a3bcf4e46a1a522b08ea1aae360 | gpt-6-astra | codex-agent | 88 | 5/5 | complete |
oly-070c91c4729f4606bb35418eb5ab8b49 | claude-fable-5-1 | claude-code | 16 | 3/5 | tens_of_actions, replay_depth |
oly-091b62b1f5a042759bbc5c41fcf77771 | muse-1.3 | opencode | 2 | 1/5 | tens_of_actions, replay_depth |
oly-0a8cf3965e0d4bda8fec4e3ca251a2c3 | claude-fable-5-1 | claude-code | 2 | 1/5 | tens_of_actions, replay_depth |
oly-0b03af1efc594621bc2421f595537259 | scoreia-operator-codex | codex-agent | 2 | 1/5 | tens_of_actions, replay_depth |
oly-0dc24410498f48ca9ba8a1dfe3370779 | claude-fable-5-1 | claude-code | 28 | 3/5 | complete |
oly-1585b86d8bdd43ea8eb74ddf7b45a45d | claude-fable-5-1 | claude-code | 27 | 3/5 | complete |
oly-19c8580a0fd54ee4a696a1e5f6af17d8 | claude-fable-5-1 | claude-code | 38 | 3/5 | complete |
oly-1b1343626c3d4b4a8910f5d2ea0bc36e | gpt-5-codex | codex-agent | 1 | 1/5 | tens_of_actions, replay_depth |
oly-1f6b2abf7b054518b74ea5899a519a3e | gpt-5.6-sol | cursor | 54 | 4/5 | complete |
oly-1fe84ef7207f4728bad414371e47af7a | technical-postdeploy-smoke | scoreia-operator | 15 | 5/5 | exterior_agent, tens_of_actions, replay_depth |
oly-252e85ac493c4066be5ddec4faab6145 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-2789caf16a43469cb39e400a4057f218 | scoreia-deterministic-scout-0.1 | scoreia-lab | 46 | 1/5 | exterior_agent, replay_depth |
oly-28c469df42d54485b68f3370b3695c0d | codex | codex-agent | 7 | 3/5 | tens_of_actions, replay_depth |
oly-28ce1b593fe14a49b2a2472c1f457ed4 | claude-fable-5-1 | claude-code | 16 | 3/5 | tens_of_actions, replay_depth |
oly-2911186b473347d6958df5106e0f2e65 | grok-4.6 | grok-cli | 9 | 3/5 | tens_of_actions, replay_depth |
oly-296e339d21f74ba1b7da197629c342eb | gpt-5.6-sol | cursor | 32 | 3/5 | complete |
oly-2e8ae95f1ee94b66bc705efce271970d | claude-fable-5-1 | claude-code | 15 | 3/5 | tens_of_actions, replay_depth |
oly-301353663b814965b1b3a585f574c376 | claude-fable-5-1 | claude-code | 32 | 3/5 | complete |
oly-36a406d0196c43629a89c17685ccc089 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-3c88d9a8d2d94fe3b535294e38eec778 | grok-4.7 | grok-build | 163 | 3/5 | complete |
oly-3d7a1800bf4e45889d95118d0a65325a | gpt-6-astra | codex-agent | 49 | 3/5 | complete |
oly-3f2a19a4464d47b69227e8250b59ecd2 | grok-4.6 | cursor | 24 | 3/5 | complete |
oly-4257f3a42d484691bb590c9ce62eaca6 | scoreia-deterministic-scout-0.1 | scoreia-lab | 31 | 3/5 | exterior_agent |
oly-4335118ee0974a33a6d8f9946b188546 | grok-4.6 | grok-cli | 1 | 1/5 | tens_of_actions, replay_depth |
oly-4497125bde084f37ad24504244d68fb7 | scoreia-commitments-r8 | scoreia-prod-smoke | 1 | 1/5 | exterior_agent, tens_of_actions, replay_depth |
oly-4625ae61e4bc439bb35e922b1c6ad292 | grok-4.6 | grok-cli | 80 | 1/5 | replay_depth |
oly-4bb5f0660d764ddbbe8f3404cea5fd8b | deepseek-flash | grok-build | 41 | 3/5 | complete |
oly-502b3019179842ddaa23f530e9f31051 | composer-2.5 | cursor | 20 | 3/5 | complete |
oly-504ca72796b848f2b5096f10e72e27b0 | scoreia-operator-codex | codex-agent | 2 | 1/5 | tens_of_actions, replay_depth |
oly-566be1ba56d44077885e5fc7bc07b909 | grok-4.7 | grok-build | 77 | 3/5 | complete |
oly-5889fea51be54a839fcffe6ba7da6b3c | codex | codex-agent | 10 | 3/5 | tens_of_actions, replay_depth |
oly-5ba79d7e1ddb4dc3ab267f0c90bf60dd | grok-4.6 | cursor | 21 | 3/5 | complete |
oly-5f3195c277fd4276a00e5be1967d4339 | scoreia-operator-live-smoke | codex-agent | 4 | 1/5 | tens_of_actions, replay_depth |
oly-64db57cae8644665a3eb95c1d0f52ad9 | claude-fable-5-1 | claude-code | 45 | 3/5 | complete |
oly-6aacd969de444a52b83431cfb2d1e573 | gpt-6-astra | codex-agent | 21 | 3/5 | complete |
oly-6ae37e8e03fd487bb4ab06b90207d793 | grok-4.6 | cursor | 21 | 3/5 | complete |
oly-6b799ff84dd14673a4f1a3f319dadd3d | muse-1.3 | opencode | 65 | 4/5 | complete |
oly-6c504c0d0d974c90bab242a56bedc60c | scoreia-deterministic-scout-0.1 | scoreia-lab | 18 | 1/5 | exterior_agent, tens_of_actions, replay_depth |
oly-7057a40e531f42f29c6b2dcd68dfff2a | scoreia-prod-acl-r6 | scoreia-prod-smoke | 1 | 1/5 | exterior_agent, tens_of_actions, replay_depth |
oly-726f77fe33e54a45b4259cfcc466c8a5 | scoreia-operator-codex | codex-agent | 19 | 3/5 | tens_of_actions, replay_depth |
oly-73fc81dcd4c34f949617de0bce077d2e | claude-fable-5-1 | claude-code | 2 | 1/5 | tens_of_actions, replay_depth |
oly-79dd2192419846e1bfceb1c6f12f6319 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-7c059ec04d1045c1993054758a5a71d4 | grok-4.6 | cursor | 23 | 3/5 | complete |
oly-7d82d3e895ec42aaa3c9c196f86a6395 | grok-4.6 | grok-cli | 24 | 2/5 | complete |
oly-7dfc063fc1414ec19dce7fb64c10c06e | claude-fable-5-1 | claude-code | 20 | 3/5 | complete |
oly-80c6d8069e3843a19e8eb82ccef811a2 | grok-4.6 | grok-cli | 16 | 3/5 | tens_of_actions, replay_depth |
oly-814713ea382a445f8f039ee4a2c0f87e | grok-4.6 | cursor | 24 | 3/5 | complete |
oly-82738f2ca83743e1b8f14fc8854de179 | unknown | local-cli | 28 | 3/5 | complete |
oly-82ea517c17554a24baa3ce2159015509 | scoreia-deterministic-scout-0.1 | scoreia-lab | 62 | 3/5 | exterior_agent |
oly-843e8eaef1294263932d5c1657280db2 | codex | codex-agent | 2 | 1/5 | tens_of_actions, replay_depth |
oly-85a552ea453046fcb3992c19fd92553d | claude-opus-5-thinking-high | cursor | 34 | 3/5 | complete |
oly-877a50147477479ebe417c2954c5e407 | claude-fable-5-1 | claude-code | 40 | 1/5 | replay_depth |
oly-8824742ce82f4c8bacc9c988a97ea3a0 | gpt-6-astra | codex-agent | 45 | 3/5 | complete |
oly-883d85226f6a48018a125c6f9513b737 | grok-4.6 | grok-cli | 1 | 1/5 | tens_of_actions, replay_depth |
oly-8d3af18a9fc844e5bd3dc85fe79341b9 | scoreia-operator-codex | codex-agent | 61 | 3/5 | complete |
oly-8db1327bc8894f6aab855cc2280288b1 | deepseek-flash | grok-build | 17 | 3/5 | tens_of_actions, replay_depth |
oly-8e2e357e324b4e8f9bffbae600999a3d | grok-4.6 | cursor | 24 | 3/5 | complete |
oly-8ec1b052d3954b9291cb0df4dabf4f9a | scoreia-deterministic-scout-0.1 | scoreia-lab | 33 | 3/5 | exterior_agent |
oly-9533f71fb1014c398546651f86310957 | scoreia-prod-canary-r5 | scoreia-prod-smoke | 1 | 1/5 | exterior_agent, tens_of_actions, replay_depth |
oly-956822d719674fbdb80a16567bb1d19e | claude-fable-5-1 | claude-code | 10 | 3/5 | tens_of_actions, replay_depth |
oly-96ed93319c674b86824a218e4d65629d | composer-2.5 | cursor | 76 | 3/5 | complete |
oly-978909a299e34a79aa9c5a2e02091e23 | prod-warden-smoke | cursor | 1 | 1/5 | tens_of_actions, replay_depth |
oly-97d5752b9c1d4ebf9c6f435f10aa9053 | gpt-5-codex | codex | 0 | 0/1 | tens_of_actions, five_seals_tracked, replay_depth |
oly-99333d2e37704bb394867d74da88f966 | grok-4.6 | cursor | 89 | 3/5 | complete |
oly-9d5a21ecb85749fcb855db483cb78975 | grok-4.6 | cursor | 23 | 3/5 | complete |
oly-9e285a8c3e574c7180d1e3fe7da9a3f7 | scoreia-deterministic-scout-0.1 | scoreia-lab | 33 | 3/5 | exterior_agent |
oly-9e4fdb43ba924369a390bc10a34fbdc9 | claude-fable-5-1 | claude-code | 52 | 3/5 | complete |
oly-9f3275d0a0284be2898a626515fd2b2d | scoreia-deterministic-scout-0.1 | scoreia-lab | 58 | 3/5 | exterior_agent |
oly-a13b8c25e2794d928d2a94ae33866011 | scoreia-deterministic-scout-0.1 | scoreia-lab | 46 | 1/5 | exterior_agent, replay_depth |
oly-a5aa4e9fc2374f0fbb5e985dff6f95db | scoreia-fable-final-smoke | codex-cli | 7 | 3/5 | tens_of_actions, replay_depth |
oly-a93c35f0d5184661929d3eb2affe9e42 | claude-fable-5-1 | claude-code | 2 | 1/5 | tens_of_actions, replay_depth |
oly-aa6a339a9883479989362cb69ef49f94 | grok-4.6 | cursor | 26 | 1/5 | replay_depth |
oly-ab603c03b66946af9bd7136ef0bd5575 | claude-fable-5-1 | claude-code | 73 | 4/5 | complete |
oly-af4fa30bc6e0470ebe7fbf7c99709db1 | grok-4.7 | grok-build | 40 | 3/5 | complete |
oly-af598764bc194448be4f19c16cfa8b4d | codex | codex-agent | 7 | 3/5 | tens_of_actions, replay_depth |
oly-b0430767e2974eed85bb574452298467 | technical-postdeploy-smoke | scoreia-operator | 13 | 3/5 | exterior_agent, tens_of_actions, replay_depth |
oly-b262c7354f3a4f709663f1e6a4491e69 | claude-opus-5-thinking-high | cursor | 24 | 3/5 | complete |
oly-b9234226232f4306827d3f41e444a429 | claude-fable-5-1 | claude-code | 14 | 2/5 | tens_of_actions, replay_depth |
oly-b9d51ba9284c4cb4987567242e35e19d | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-ba47652c4b1141da8ec549bd5818ec5c | claude-fable-5-1 | claude-code | 39 | 3/5 | complete |
oly-baec12321ba84f8597b891a857806828 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-bb01b7f6fe4a407d9d2a74025c8ad81f | scoreia-zero-action-conformance | scoreia-lab | 0 | 0/1 | exterior_agent, tens_of_actions, five_seals_tracked, replay_depth |
oly-bc38073076544a59ba835d6b10dae04f | codex | codex | 56 | 3/5 | complete |
oly-c01d71d2507b4637a1d9df380b70a4fe | grok-4.6 | cursor | 26 | 1/5 | replay_depth |
oly-c7ee07b1f35a4e6fb481608fc64081c5 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-c95cfad265db4d188112fee69e583f6f | grok-4.6 | cursor | 23 | 3/5 | complete |
oly-ce9936df33c740e8b18ad2c7f5ad2f64 | scoreia-internal-proof-smoke | scoreia-lab | 0 | 0/5 | exterior_agent, tens_of_actions, replay_depth |
oly-d1b9faef157f49a287f7c474ba9b315b | gpt-6-astra | codex-agent | 40 | 3/5 | complete |
oly-d22e6a5386a841aebc13373457647b34 | codex | codex-agent | 7 | 3/5 | tens_of_actions, replay_depth |
oly-d746646002fc4b3a87626cd3635d3d41 | grok-4.6 | grok-cli | 2 | 1/5 | tens_of_actions, replay_depth |
oly-daccd52499744b08be349e39dc879b0a | scoreia-deterministic-scout-0.1 | scoreia-lab | 18 | 1/5 | exterior_agent, tens_of_actions, replay_depth |
oly-dcf8a3034f994f70a735ad50e1a05e80 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-de4104e37b164a88b1f11b8325ae1b25 | claude-fable-5-1 | claude-code | 37 | 3/5 | complete |
oly-e12bde7457d24666be5e50bdb29d929b | gpt-6-astra | codex-agent | 57 | 5/5 | complete |
oly-e5e6fd6d7bb846d0b1a90c65dc17cd4d | claude-fable-5-1 | claude-code | 26 | 4/5 | complete |
oly-e7683fcffefc4cbb8d7a2042d994e187 | scoreia-operator-codex | codex-agent | 44 | 3/5 | complete |
oly-ec9a26bff0c940d4979d0115ed079541 | scoreia-deterministic-scout-0.1 | scoreia-lab | 31 | 3/5 | exterior_agent |
oly-ed04930f3c124a9aa0e4c53429656c9c | grok-4.6 | cursor | 23 | 3/5 | complete |
oly-efa62c29dcf04f97a09042069bc0dc8d | muse-1.3 | opencode | 75 | 3/5 | complete |
oly-f1e591eeac1b4122b1e626dd9735486c | claude-fable-5-1 | claude-code | 22 | 3/5 | complete |
oly-f5ee7cad12c743f28868b04c8d0bc28f | scoreia-cuda-route-smoke | codex-cli | 6 | 3/5 | tens_of_actions, replay_depth |
oly-f606856d8ce14d0799f1fc19ad641426 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-f669f9de329b4ff480e04070b2d48418 | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-f7db9f06404c4818928bcac13d004c92 | gpt-6-astra | codex-agent | 34 | 3/5 | complete |
oly-f897ca932715496fbcbb89fdd2f78344 | scoreia-operator-codex | codex-agent | 44 | 3/5 | complete |
oly-f93906a49f1b4ce59ac447fe34439bec | gpt-6-astra | codex-agent | 49 | 3/5 | complete |
oly-f9e27f5325224a0dbf8999490a0dd7ed | grok-4.6 | cursor | 26 | 3/5 | complete |
oly-fa84c2e6bb884854816fc132f9f42df9 | codex | codex-agent | 24 | 1/5 | replay_depth |
Private Trial offer · 10×20 report template · Codex · JSON · Campaign spec