From 30cc9f744d76f29d6bf0497da50dba97f4b86e67 Mon Sep 17 00:00:00 2001 From: almondsun Date: Mon, 13 Jul 2026 02:10:25 -0500 Subject: [PATCH] fix Hamlet preregistration reference --- docs/codex/experiments.md | 2 +- experiments/027-hamlet-external-distribution.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/codex/experiments.md b/docs/codex/experiments.md index e7dfc32..a0a3dab 100644 --- a/docs/codex/experiments.md +++ b/docs/codex/experiments.md @@ -176,7 +176,7 @@ region unavailable to tokenizer fitting, training, early stopping, and checkpoin One-shot best-checkpoint test evaluation confirms ByteBPE512 by `0.0614` BPC on Alice and `0.0258` on Peter Pan. Those test segments are consumed and must not guide further tuning. -Milestone 027 was preregistered in commit `d4a17dc` before Hamlet corpus access. Under the unchanged +Milestone 027 was preregistered in commit `6f130d5` before Hamlet corpus access. Under the unchanged seed-1337 sealed protocol, ByteBPE512 beats character by `0.0673` test BPC on the dramatic-play distribution. Hamlet's terminal segment is easier than validation for both models, so gap direction and effect magnitude remain corpus-dependent. The Hamlet test is consumed. diff --git a/experiments/027-hamlet-external-distribution.md b/experiments/027-hamlet-external-distribution.md index 5eb8bf9..6bef089 100644 --- a/experiments/027-hamlet-external-distribution.md +++ b/experiments/027-hamlet-external-distribution.md @@ -67,7 +67,7 @@ be reported. Test results will not trigger configuration changes or additional H ## Observations -The preregistration above was committed as `d4a17dc89138c9ff6b6271b70a7d04d176a9da5e` at +The preregistration above was committed as `6f130d5b3c9c7b9deaeac09d8e4bb2bd8d325a33` at `2026-07-13T01:50:48-05:00`, before the first network request. The declared protocol was executed without substitution or post-access configuration changes.