| .. |
|
blind-read
|
Record the negative result: judges named a winner on 29 of 30 pure-noise pairs, so the earlier cheap-arm advantage is indistinguishable from generation randomness
|
2026-09-02 22:23:34 +03:00 |
|
judge-prompts
|
|
|
|
prereg-4axes
|
Land the probe session's phase report and execution journal, including its replica findings on the low2 run and the measured sigma for the zh pair
|
2026-09-02 23:12:11 +03:00 |
|
prompts
|
|
|
|
adjud.py
|
|
|
|
bank.py
|
Land stage 0 item 1: the bank holds its terms, and the audit found on disk a production-profile run, a July measurement of the same question, and a ratified editor-price input this phase never executed
|
2026-08-30 20:10:54 +03:00 |
|
canon.py
|
|
|
|
chetyre.py
|
Pin the signature at seventy-nine on both prompts and record the execution log: the auto-bank grew between purchases and was driven to a verified fixed point before any cell was bought
|
2026-09-02 11:49:08 +03:00 |
|
chtenie.py
|
|
|
|
contam_d.py
|
|
|
|
contour.py
|
|
|
|
d1_gemini.py
|
|
|
|
d7_self.py
|
|
|
|
dreif.py
|
Collapse variants that are merely shortened forms of one another: the stem match counted Gao Van and Gao Vany as two renderings where the text has one
|
2026-09-03 00:19:08 +03:00 |
|
en_axis.py
|
|
|
|
etalon-panel0.json
|
|
|
|
gain.py
|
|
|
|
HANDOFF-21-08.md
|
|
|
|
itog_d4.py
|
|
|
|
ja6.py
|
|
|
|
ja_axis.py
|
|
|
|
KONSILIUM-22-08.md
|
|
|
|
KONSILIUM-30-08.md
|
Land stage 0 item 1: the bank holds its terms, and the audit found on disk a production-profile run, a July measurement of the same question, and a ratified editor-price input this phase never executed
|
2026-08-30 20:10:54 +03:00 |
|
material_ja.py
|
|
|
|
money_d.py
|
|
|
|
naklon.py
|
|
|
|
narezka.py
|
Turn the plan into a procedure: the fresh-eyes check found it unbuildable without invention, so the stand, the arms, the commands, the exit codes and the manual ceiling aggregate are now written down
|
2026-09-02 00:14:27 +03:00 |
|
NORMY-ZAMEROV.md
|
Record that the active null was ratified in July as the D39.7 floor gate, so phase D bought back a norm it already owned, and tie the result to the owner's three questions
|
2026-09-03 00:24:42 +03:00 |
|
pachka.sh
|
Pin the signature at seventy-nine on both prompts and record the execution log: the auto-bank grew between purchases and was driven to a verified fixed point before any cell was bought
|
2026-09-02 11:49:08 +03:00 |
|
para.py
|
|
|
|
paritet.py
|
|
|
|
PLAN-01-09.md
|
Freeze the pre-registration: design, models, decision rule, ceiling, sampling frame and seed are now fixed, and the known rough edges are named rather than hidden
|
2026-09-02 02:48:22 +03:00 |
|
PLAN-16-08.md
|
|
|
|
PLAN-17-08.md
|
|
|
|
PLAN-21-08.md
|
|
|
|
PLAN-22-08.md
|
|
|
|
plan.py
|
|
|
|
podacha.py
|
|
|
|
poryadok.py
|
Freeze the probe stand before the first paid cell: configs, scripts, hashes and the ceiling rule, with the deviations from the procedure named rather than silently applied
|
2026-09-02 10:12:10 +03:00 |
|
power.py
|
|
|
|
predpolet.sh
|
Pin the signature at seventy-nine on both prompts and record the execution log: the auto-bank grew between purchases and was driven to a verified fixed point before any cell was bought
|
2026-09-02 11:49:08 +03:00 |
|
predpolet_proverka.py
|
Pin the signature at seventy-nine on both prompts and record the execution log: the auto-bank grew between purchases and was driven to a verified fixed point before any cell was bought
|
2026-09-02 11:49:08 +03:00 |
|
proba_gemini.py
|
|
|
|
PROMPT-PROBE-4AXES.md
|
Close the last four: the pre-flight now flies five cells, the empty-output rule binds only the cross arms, the few-shot fork is decided, and the arm order is a contract
|
2026-09-02 02:47:10 +03:00 |
|
PROMPT-RESEARCH-HARNESS.md
|
Rewrite the research prompt against the live orchestrator norm and fix what the refuter found: the zone belongs to the orchestrator and one hard-contour fact contradicted its own source
|
2026-08-30 23:55:54 +03:00 |
|
promptdiff.py
|
|
|
|
proverka_pribora.py
|
Freeze the probe stand before the first paid cell: configs, scripts, hashes and the ceiling rule, with the deviations from the procedure named rather than silently applied
|
2026-09-02 10:12:10 +03:00 |
|
requirements.md
|
|
|
|
REVIEW-21-08.md
|
|
|
|
rol.py
|
Write the post-compaction restoration file: the sanctioned purchase is one command away with its decision rule frozen, and the seven mistakes of this session are listed so the next one does not repeat them
|
2026-08-30 00:56:26 +03:00 |
|
runs.py
|
Raise the cap by five so the second circle fits, and record that my own arithmetic left it one session short
|
2026-08-30 12:02:06 +03:00 |
|
schet.py
|
|
|
|
sessii.py
|
|
|
|
SESSION-30-08.md
|
Repair my own botched substitution and mark every stale ceiling figure as history rather than leaving two live numbers
|
2026-09-02 02:33:48 +03:00 |
|
SESSION2-LOG.md
|
|
|
|
spanjoin.py
|
|
|
|
stupen.py
|
Report the interleaved run: the default path itself moved thirty-eight-fold in nine days, which measures the confound and leaves the knob magnitude unestablished
|
2026-08-30 02:13:39 +03:00 |
|
sud.py
|
|
|
|
sysmsg.py
|
Freeze the step-4 pre-registration and prove from bought cells that Gemini drops the FIRST system message, so the engine loses the stage prompt rather than the glossary
|
2026-08-29 21:32:01 +03:00 |
|
tier2.py
|
|
|
|
vtoroe.py
|
|
|
|
zakhod.py
|
Teach the rig that DeepSeek peak pricing is weekdays only, and record the vendor wording with the near-miss that a single page read caused
|
2026-08-30 12:55:42 +03:00 |
|
zsud.py
|
|
|