wassname 026de8fd74 journal (i): state-of-the-problem -- loop ceiling is coherence collapse not starvation ...

Three loop arms (#100 starve-crash r5, #101 walk-C full-10r-but-collapse, #102
round-ramp partial) all lose coherence; the constraints only change how it dies.
Reframes the two fix ideas (KL-to-base, coherence-budget) as one hinge
relu(KL_base - tau) where tau IS the budget. Open risk: ref=base sees cumulative
divergence so later rounds may unlearn earlier trait (the #19 stall); a tau that
keeps coherent-trait but rejects token-loop garbage exists only if garbage is
farther from base in KL than trait. Next: base-anchor tau bracket #103/#104.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-06 12:23:46 +08:00

..

brainstorming

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

evidence

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

literature

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

personas

metric fix: auth_nats = diagonal log(p) not raw forced-choice logit

2026-06-04 14:25:40 +08:00

spec

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00

writeup

writeup: NeurIPS quarto scaffold + paper/paper-html recipes

2026-06-05 06:36:30 +08:00

human_journal.md

walk-C adaptive-dose controller + 10-round paired loop result (journal h)

2026-06-06 07:13:51 +08:00

RESEARCH_JOURNAL.md

journal (i): state-of-the-problem -- loop ceiling is coherence collapse not starvation

2026-06-06 12:23:46 +08:00

results.md

setup-repo gap-fill: results ledger + docs structure

2026-06-04 09:51:36 +08:00