docs: comparison protocol ledger — every row we cite, by what was actually run - #67
Merged
Conversation
…ually run Makes the disclosure discipline structural: our rows (reproducible, windowed zero-skip, greedy contract), reproduced LLM rows (GLM-5.2 plain completion; GLM-5.3-Flash at reasoning_effort=low because thinking cannot be disabled), vendor-published numbers (Claude, Gemini, GPT-4 — not reproducible), Sadeed (published under its own split), and the Hy4 internal-blind-pairwise class. Encodes the standing rules incl. the checkpoint-sentinel guard.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Structural form of the disclosure discipline (TODO 08 plan, B2): one table rowing every comparison — ours (reproducible, greedy windowed zero-skip contract), our LLM reproductions (GLM-5.2 plain completion; GLM-5.3-Flash at reasoning_effort=low because the API rejects disabled thinking), vendor-published numbers (not reproducible — Claude/Gemini/GPT-4), Sadeed's own-split caveat, the Hebrew run-by-us rows, and the Hy4 internal-blind-pairwise class. Enforces the standing rules (full-set-only, subset labeling, protocol disclosure, checkpoint-sentinel guard) and notes paired-bootstrap CIs as the delta qualifier.