Repository navigation
Conversation
This was referenced Nov 18, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Result and scope
This package proves the kind B removal criterion at every address width in the formal frame game. For a nonplain part
y=WD+cW gamma, an admissible removing call T removes the part exactly when T exchanges both term frames and c is +1 or -1. The hypotheses are gamma free, c nonzero rational,level(WD)=level(TW)=2, andW gammaoutside the first-call frame PD.PR #7629 supplied finite evidence and asked for a proof of frame-swap sufficiency. This package proves necessity as well, at arbitrary width. Exchanging only one frame is insufficient. The proof forces a nonzero target coefficient at each endpoint, then constructs an even alternating cycle and gives every free preparation needed for removal.
Read the proof, exact receipt, verifier and scope record. The kind A finishing and removal results in PR #7649 and PR #7677 concern a different placement of gamma. They do not classify this kind B part.
No new kappa, native supplier or selected-assumption discharge is claimed. All five assumptions and selected PR #7000 remain unchanged. This completes the advance claim on the narrowed formal-frame question of
complex-rank-shape-decoder. It does not classify finishing, joint decoding or a general two-in-five program.Evidence and reproduction
Normal and optimized CPython 3.12.16 checks passed on macOS arm64. A binary row-matrix checker enumerates all 10752 three-bit free elements and all 48 admissible removing calls. After 768 plain cases are excluded, it covers 479232 part/call pairs. For 478720 pairs, a target coefficient is absent from every available column. For the other 512 pairs, complete cyclic-span checks give exactly the two allowed signs. The cycle lengths are two, four and eight; every positive has its explicit alternating relation checked.
The five tested coefficients {1,-1,2,1/2,-2/3} give 2396160 coefficient contracts. There are 128 distinct removable parts at each sign. That finite 128-part count belongs to the predecessor; the new result is the arbitrary-width theorem. Another route runs full span checks for 150 wider cases, including free conjugations that mix a core coordinate with a spare bit. Five boundary controls and two rational-solver controls pass.
Package metadata, committed bytes, executable modes, source ancestry, the official seven-file export and its integrity check passed. An optimized read-only export replay passed without Git or a usable PATH, with all eight payload/manifest hashes and modes unchanged. No external run-time input is used. The proof and README were rendered with GitHub Markdown and checked.
From the repository root, with CPython 3.12:
Expected status markers:
Hosted CI did not certify this package. The plan job failed in the shared
test_current_ci_section_matches_selected_record: the base guide names frontier6030 while the selected record requiresmake frontier7000-verify. The log reports 760 tests, one failure and 24 skipped; package replay was skipped. This package changes no shared CI file. Local replay remains the scientific evidence. Predecessor scientific replays, the selected cold replay, Lean and Docker were not run. Independent human and formal-kernel review are unclaimed.Credit and remaining obligations
Prepared by @aliromman with substantial OpenAI Codex assistance. Jacob Sussman (@jacobalansussman) defined kind B removal, supplied the finite evidence and posed the frame-exchange question in PR #7629, exact source. Nick Petalas (@petalas) supplied the related coset method in PR #7649, exact proof. Ali Romman's kind A removal result is PR #7677, exact proof. The source's original geometry includes PR #4628 and PR #4743. The new verifier uses binary row matrices. New work is Apache-2.0.
The next question is whether these single-part cancellations can be used jointly while preserving both targets and shared preparation constraints. Pauli phases, native execution, precision, restoration and the complete signed physical invoice remain open. Free formal combinations are not a priced physical decoder. Base: canonical main
e54523517d0f03e58352e647c403a5af3e525a57, priority revision 8. Live open/closed PR and Discussion overlap was checked; sparse local notes and unpublished work remain coverage limits.