|
| 1 | +# Overlap receipt for the fourth100 witness-MANIFEST pin family |
| 2 | + |
| 3 | +Scope key `757723e3fd38f20fa774` (`overlap-receipt`, consolidation track, |
| 4 | +priority revision 3, chooser nonce `6bc45fb7886eb99e0494a94781da0e58`), |
| 5 | +**refined** to one small named PR set: the seven entries of the fourth100 |
| 6 | +reconciliation whose contributed-package replay fails at `verify.py` line 39 |
| 7 | +with `AssertionError: larger_gain manifest pin` — |
| 8 | +[#636](https://github.com/CrocSwap/integer-mult-bounds/pull/636), |
| 9 | +[#638](https://github.com/CrocSwap/integer-mult-bounds/pull/638), |
| 10 | +[#639](https://github.com/CrocSwap/integer-mult-bounds/pull/639), |
| 11 | +[#640](https://github.com/CrocSwap/integer-mult-bounds/pull/640), |
| 12 | +[#642](https://github.com/CrocSwap/integer-mult-bounds/pull/642), |
| 13 | +[#644](https://github.com/CrocSwap/integer-mult-bounds/pull/644) |
| 14 | +(vectorsss / Chi Zhao) and |
| 15 | +[#646](https://github.com/CrocSwap/integer-mult-bounds/pull/646) |
| 16 | +(jeremydiviney). Base main `1f7a934975e5eacaf83511c9ac870263bf095e05`. |
| 17 | + |
| 18 | +This is a source-bound disposition receipt: a finite certificate of git-blob |
| 19 | +identities and one diagnosed source-pin defect. It is **not** a kappa claim, a |
| 20 | +construction, or a mathematical result, and it changes no disposition: the |
| 21 | +seven PRs stay open, the selected frontier is unchanged, and no closure is |
| 22 | +requested. |
| 23 | + |
| 24 | +## What was audited |
| 25 | + |
| 26 | +The existing receipt under audit is the fourth100 reconciliation |
| 27 | +(`research/community-reconciliation-fourth100-audit/`, |
| 28 | +`docs/research/community-reconciliation-fourth100-review.md`) as recorded in |
| 29 | +`docs/research/pr-ledger.json`, which leaves all seven with the identical |
| 30 | +unresolved question "Required contributed-package replay has not completed |
| 31 | +successfully" and identical evidence text |
| 32 | +`AssertionError: larger_gain manifest pin`. For each recorded head I checked |
| 33 | +(a) the source-pin block of the package's own `verify.py` (lines 36-42: package |
| 34 | +MANIFEST tree, each pinned source's `MANIFEST.json` pin, and each pinned file) |
| 35 | +against the exact bytes committed at that head, and (b) the byte-retention of |
| 36 | +every changed path against main's tree at the base commit. Method: exact |
| 37 | +git-blob identity only (SHA256 of raw bytes for pins, blob SHAs for retention); |
| 38 | +no heuristic matching. The fetching side is `tools/audit_witness_pins.py`, the |
| 39 | +receipt builder is `tools/build_receipt.py`. |
| 40 | + |
| 41 | +## Findings |
| 42 | + |
| 43 | +**F1 — the seven failures share one cause: a drifted `larger_gain` pin.** All |
| 44 | +seven SPECs register `larger_gain` with |
| 45 | +`manifest_sha256 = 54d67f45ad520f4a134e069336bd0ff639aaeada28d13539298e4f2655c9692d`, |
| 46 | +which is exactly `research/larger-gain/MANIFEST.json` at the pinned PR569 |
| 47 | +revision `897213a855b7fb8a1b8b0e552a2f5c42e6c1b326`. The same path **as staged |
| 48 | +into main** (commit `df417acd`, "Stage frozen PR family through 588") hashes |
| 49 | +`73c186c2807c703e43293c7cf785557a046958c245fa812e433f7fe208cdef6d`, and this |
| 50 | +drifted copy is what every one of the seven recorded heads carries in its base |
| 51 | +tree (checked at each head). The two manifests differ in exactly two `files` |
| 52 | +entries: `NOTICE` and `README.md` (both 64-hex digests changed; byte length |
| 53 | +40,559 in both). The staged package is self-consistent at its own revision: |
| 54 | +main's `NOTICE` and `README.md` hash to the staged manifest's values, not to |
| 55 | +PR569's. The other five pinned sources (`multicold`, `structural_gain`, |
| 56 | +`joint_prefix`, `frame_coalescing`, `direct_delivery`) still match their pins in |
| 57 | +the live repository packages. |
| 58 | + |
| 59 | +**F2 — the six vectorsss packages vendor the pinned revision byte-exactly.** |
| 60 | +For #636/#638/#639/#640/#642/#644, each source pin resolves to the package's |
| 61 | +own `vendor/<name>/MANIFEST.json`, and every one matches its registered |
| 62 | +`manifest_sha256` in raw bytes (zero CRLF bytes anywhere, so the repository's |
| 63 | +text normalization is not involved). All their pinned files match too. Run |
| 64 | +through their own `verify.sh` source overrides, these six pass the pin block |
| 65 | +that the reconciliation recorded as failing; they evidently ran with the |
| 66 | +sources resolved to live repository packages (as #646's defaults do), where |
| 67 | +`larger_gain` is the first pin that fails. #646 has no vendored copy at all: |
| 68 | +its `verify.py` defaults resolve `larger_gain` to the live |
| 69 | +`research/larger-gain`, which reproduces its failure on any checkout of main. |
| 70 | + |
| 71 | +**F3 — retention is partial, and dominated by re-vendored predecessor |
| 72 | +content.** Against main's tree at the base commit (exact blob identity): |
| 73 | + |
| 74 | +| PR | changed paths | byte-retained in main (other path) | not byte-retained | |
| 75 | +|---|---:|---:|---:| |
| 76 | +| #636 | 348 | 285 | 63 | |
| 77 | +| #638 | 347 | 281 | 66 | |
| 78 | +| #639 | 340 | 281 | 59 | |
| 79 | +| #640 | 339 | 282 | 57 | |
| 80 | +| #642 | 354 | 281 | 73 | |
| 81 | +| #644 | 355 | 280 | 75 | |
| 82 | +| #646 | 186 | 77 | 109 | |
| 83 | + |
| 84 | +No path matches at the same path, and no path exists in main with different |
| 85 | +content, so retention is entirely "same bytes at a different path": the |
| 86 | +vendored copies of the six pinned source packages already live in main under |
| 87 | +their own `research/` directories. The unretained remainder is each package's |
| 88 | +own witness, tools, data and result files (listed path by path in |
| 89 | +`evidence/pr{N}-audit.json`). |
| 90 | + |
| 91 | +**F4 — the six vectorsss members share their vendored core with each other** |
| 92 | +(250-268 shared blobs pairwise; #646 shares 31-33 with each). A reviewer can |
| 93 | +treat the six as one content family plus six small per-PR deltas. |
| 94 | + |
| 95 | +**F5 — predecessor credit is present.** `CONTRIBUTORS.md` credits vectorsss for |
| 96 | +#636/#638/#639/#640/#642/#644 (line 835) and jeremydiviney for #646 (line |
| 97 | +833). No missing attribution was found for this family; the downstream |
| 98 | +incorporated work that credits vectorsss's owner-search methods (e.g. #654, |
| 99 | +#671, #676, #699) is separate and unaffected. |
| 100 | + |
| 101 | +## Reproduction |
| 102 | + |
| 103 | +```sh |
| 104 | +python3 -B research/pr636-family-witness-manifest-receipt/verify.py |
| 105 | +python3 -B scripts/research_package.py --package research/pr636-family-witness-manifest-receipt |
| 106 | +``` |
| 107 | + |
| 108 | +`verify.py` is offline and standard-library only. It recomputes the drift |
| 109 | +identity from the two committed MANIFEST copies (and against the working tree's |
| 110 | +`research/larger-gain/MANIFEST.json`), re-derives every pin verdict and every |
| 111 | +retention class from the per-PR audit rows against `git ls-tree -r <base>`, |
| 112 | +recomputes the cross-PR shared-blob counts, runs a positive fixture of the |
| 113 | +classification rule, and runs four failure controls (tampered digest, |
| 114 | +substituted manifest diff, omitted row, substituted class) that must each be |
| 115 | +rejected. The evidence copies under `evidence/` are byte-exact unmodified |
| 116 | +copies of two `MANIFEST.json` revisions, kept so the digests are checkable |
| 117 | +without network access. |
| 118 | + |
| 119 | +## Limitations (not checked) |
| 120 | + |
| 121 | +- Head-side blob identities rest on the GitHub pulls/contents APIs at the |
| 122 | + recorded head SHAs; the seven PR trees are not fetched into the reviewer's |
| 123 | + git, so `verify.py` re-derives the main-tree side only. |
| 124 | +- The `multicold` sources declare `full_tree: true`; their whole-tree manifests |
| 125 | + were not recomputed file by file (the recorded failure is earlier, at the |
| 126 | + `MANIFEST.json` pin). |
| 127 | +- The seven packages' full contributed replays (construction, owner search, |
| 128 | + admission) were not executed. This receipt resolves the recorded pin failure |
| 129 | + and the retention/credit question only. |
| 130 | +- That the fourth100 harness resolved sources to live packages is inferred |
| 131 | + from the uniform `larger_gain manifest pin` assertion plus the pin data; the |
| 132 | + harness's exact invocation was not recorded in the ledger. |
| 133 | +- Retention matching is byte identity. Content rewritten equivalently would be |
| 134 | + reported as not retained; no such case appeared at these paths. |
| 135 | + |
| 136 | +## Open next questions |
| 137 | + |
| 138 | +1. **What did the fourth100 harness actually pass to `verify.py`?** It matters |
| 139 | + because the six vectorsss packages pass their pin block via their own |
| 140 | + `verify.sh` overrides, so their ledger questions may be resolvable by a |
| 141 | + re-run rather than a content fix. First step: re-run #636's `verify.sh` pin |
| 142 | + block (`--check-pins`) in a byte-preserving checkout of its recorded head |
| 143 | + `679621828a85bac68af869fb0e55b54508e6b14b`. Blocked by: the recorded |
| 144 | + traceback stops at the assertion and does not record the harness's source |
| 145 | + resolution. |
| 146 | +2. **Should the `larger_gain` pin drift be reconciled in main?** The staged |
| 147 | + `research/larger-gain` package is self-consistent but is a later revision |
| 148 | + (NOTICE/README.md changed) than the pinned PR569 revision that all seven |
| 149 | + packages register; every live-package resolution fails until someone either |
| 150 | + re-pins or vendors the pinned revision. First step: confirm with the |
| 151 | + maintainers whether `df417acd`'s NOTICE/README.md rewrite was intentional |
| 152 | + (it looks like license/attribution staging) and then update the seven SPECs |
| 153 | + or restore the pinned revision. Blocked by: maintainer decision on pin |
| 154 | + policy; this receipt does not change any pin. |
| 155 | +3. **Is any of the unretained content worth retaining for reuse?** The 57-109 |
| 156 | + unretained paths per PR are mostly per-package witness outputs; a bounded |
| 157 | + follow-up could classify them into method code worth retaining versus |
| 158 | + generated evidence. First step: classify the `not_retained` lists in |
| 159 | + `evidence/pr{N}-audit.json` by extension and directory. Blocked by: nothing. |
| 160 | + |
| 161 | +## Credit and attribution |
| 162 | + |
| 163 | +Predecessor authors: vectorsss / Chi Zhao (#636/#638/#639/#640/#642/#644) and |
| 164 | +jeremydiviney / Jeremy Diviney (#646); the fourth100 reconciliation authors |
| 165 | +for the audited receipt and recorded evidence; the PR569 (`larger_gain`) |
| 166 | +authors and the `df417acd` staging authors for the two manifest revisions |
| 167 | +compared here. The receipt follows the source-retention receipt style of |
| 168 | +[#1572](https://github.com/CrocSwap/integer-mult-bounds/pull/1572) (PR148), |
| 169 | +which audited a different family. |
| 170 | + |
| 171 | +Prepared by Aaron Wang / navinor with help from opencode. Substantial AI |
| 172 | +assistance is disclosed; no independent human review is claimed. Apache-2.0. |
0 commit comments