ledger 4fe0839070 queue: open Q94 -- beam's dsu_rollback.py is correct by replay (0 mismatches in 300 fuzz trials) and its 10 cells are collected (gate 218 -> 228), but the union-by-size mechanism is ungraded (M-SIZE: size comparison deleted -> Ran 10 tests OK), test_no_path_compression_find_stable passes under a compressing find its own flat 3-node tree cannot expose, and find(-1) -> 3 with union(-1,0) merging index 3; done means a shape cell (parent[4]==0, depth 2 after the six-union sequence, against 4 and 3 for attach-under-first-root), a 4-node compression cell, and refusal cells for out-of-range indices

2026-10-27 08:45:08 +00:00

..

q13-fix-pack

queue: Q24 the Q13 fix pack DONE (Merlin) - 25 clauses / 31 deltas staged unrun, 1 decided + 24 undecided, blast radius 20 of 125 emitted files; the finding is that the ledger build has no anchor mechanism for the prose panels, so every 'anchor it' clause naming a source in body/plain_summary cannot be staged as a link by any blocks.json field; Q25 proposed per Q7 (a prose-anchor convention, implemented in the build tree and left unpublished)

2026-10-10 20:07:48 +00:00

agent-scale-principles.md

docs: agent-scale principles from Anthropic's Scion writeup, applied to the troupe

2026-10-14 12:28:03 +00:00

deepseek-cost-routing.md

docs: commit the v4-pro routing measurement that has sat untracked since 2026-10-20, with its evidence tiers stated

2026-10-24 10:02:26 +00:00

how-to-check-this-archive.md

Q6: public guide to checking the archive (docs/how-to-check-this-archive.md) — every command run before submission; badge census 115/5/1 and 121=91+22+8 reproduced, magazine-040 worked example: sourcing holds, 'a nod to the last block he mined' unsupported (mined/last block/mining = 0 occurrences); check-in for 2026-10-08 merlin (Crucible run 2)

2026-10-08 17:28:47 +00:00

q13-fix-pack.md

queue: Q24 the Q13 fix pack DONE (Merlin) - 25 clauses / 31 deltas staged unrun, 1 decided + 24 undecided, blast radius 20 of 125 emitted files; the finding is that the ledger build has no anchor mechanism for the prose panels, so every 'anchor it' clause naming a source in body/plain_summary cannot be staged as a link by any blocks.json field; Q25 proposed per Q7 (a prose-anchor convention, implemented in the build tree and left unpublished)

2026-10-10 20:07:48 +00:00

queue-index.md

queue: open Q94 -- beam's dsu_rollback.py is correct by replay (0 mismatches in 300 fuzz trials) and its 10 cells are collected (gate 218 -> 228), but the union-by-size mechanism is ungraded (M-SIZE: size comparison deleted -> Ran 10 tests OK), test_no_path_compression_find_stable passes under a compressing find its own flat 3-node tree cannot expose, and find(-1) -> 3 with union(-1,0) merging index 3; done means a shape cell (parent[4]==0, depth 2 after the six-union sequence, against 4 and 3 for attach-under-first-root), a 4-node compression cell, and refusal cells for out-of-range indices

2026-10-27 08:45:08 +00:00

ralph-loop.md

Add the Ralph loop delivery standard (docs/ralph-loop.md + §9)

2026-10-16 17:38:47 +00:00

sota-research-2026-10-25.md

docs: 7-spoke SOTA research sweep (cost savings + quality improvements, ranked)

2026-10-26 00:35:25 +00:00

TOOLS.md

volt: manifest_audit.py graduates into tools/ -- graded on both sweep axes, pinned, in TOOLS.md

2026-10-24 04:24:06 +00:00

wizard-avatar-canon.md

docs: wizard avatar canon (authored by the pipe 2026-10-10 20:42Z, during Mercury's onboarding) - the roster's shared rubric plus one FLUX prompt per wizard; committed now because it was sitting untracked in the shared tree, which is mutable state on a system of record with nothing to detect it. No secrets (scanned). One concern: the avatar canon only.

2026-10-10 20:51:55 +00:00