ept.git/ep_run/runs, branch master

--holoavg shipped (gate 0.913->0.936 @t2sel160, batch2 +0.051) + farm wave-2 tooling

2026-07-06T12:15:30+00:00

trend-aware stop + plateau averaging recovers the semi-convergence victims
exactly as predicted. Estimator pack now: holofast+sdpa+t2sel80(+holoavg).
Also: bp_lm stdinit/beta2/sched flags (anchor archaeology), dipfarm_freezer,
staged tol_sweep.sh (gated on hr2 verdict), bp_sweep.sh.

Co-Authored-By: Claude Fable 5 
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn

queue v3: 5th arm abl_delay_hr2 (redx-faithful hr0.2 front) + every-100 saves on delay arms for dip-screening

2026-07-05T04:04:53+00:00

Co-Authored-By: Claude Opus 4.8 
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn

magic-s2000 study: reg_delay/noadaptc flags, 4-arm queue v2, redx trajectory audit

2026-07-05T03:35:16+00:00

- lt_ep_train: --reg_delay N (reg-free early phase: resreg/jr/floss/adaptc off
  for first N steps) + --noadaptc (kill hidden jacreg==0 damping feedback that
  would pollute single-reg ablation arms)
- queue v2: 4 arms delay-first (abl_delay = reg-free 2k -> proven pair)
- eig_traj/2/3: ARPACK audit of redx_traj — the run crossed the edge EARLY and
  oscillated (s1000 rotating-unstable, s1400 excursion mu=+2.1 self-recovered,
  s2000 the ONLY stable snapshot mu=-0.02, s2100/s2200 already back out) =>
  s2000 is a post-excursion STABILITY-DIP capture, dip width <100 steps;
  learning survives mild instability (val fell through unstable stretches).
  lead_rho cold-40 under-reads clusters — NOT a classifier; ARPACK for audits.

Co-Authored-By: Claude Opus 4.8 
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn

floss-ept: graded finite-horizon LE penalty (--floss) + three-arm from-scratch ablation queue

2026-07-03T23:21:21+00:00

- ep_step: floss block after resreg — unroll q=10 steps past z_T1 on a
  sub-batch WITH graph, rho_hat = mean per-step delta growth, one-sided
  relu(rho_hat - 0.995)^2, ramp keyed on (rho_hat - target) NOT resT1
  (de-cliffed resreg: same fundamental path-LE quantity, linear early signal),
  capped at floss fraction of task-grad norm (resreg convention).
- smoke: below-target = untouched (cos 1.0000); force-fire = finite grads,
  capped perturbation (cos 0.9803).
- runs/abl3_queue.sh (runner live): waits for free GPU slots (0/1/3, GPU2
  excluded), launches abl_floss (floss-only) / abl_resreg (resreg-only, never
  cleanly run) / abl_pair (proven 2.09 recipe, control) with identical
  remaining flags + seed.

Co-Authored-By: Claude Opus 4.8 
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn