You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 667873e
Browse filesBrowse the repository at this point in the historyBrowse files
P-037 B1: amend the pre-registration per owner review (no code)
Four corrections the owner required after reviewing 571669e, applied
before any implementation and recorded in §G:
1. N5: G-T2a is only the pre-finalization refinement against F_C and
never a legacy-comparison justification.
- Legacy classification rests on G-T2b.
- The summary report and the application report are separate
classifications.
- G-T2a may be checked as an internal invariant; a violation is a
defect, never a class.
2. Population: every first-shadow input is frozen at population_commit
571669e. Later B1 fixtures are acceptance tests only (G14).
3. Hard caps replace the approximate and 2x budgets: own-guarded 900
non-test Rust, own-shadow 200, A14 C# 150, and 2500 in total for
everything B1 hand-writes. Reaching a cap unfinished means STOP.
4. A14 side report, measurement only: exact | open plus the observed
first-party targets in this compilation. It never claims to be
exhaustive, computes no summary class, and never marks open as safe
(G15).
N2's zero-cut evidence and the §0 architecture are accepted as written.
Implementation is authorized from this commit on.
Refs #304
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KmiyfrkaG9sJruTcshM2oq
- candidates whose admissible first-party implementations (in the
138
-
compilation) have **different** guarded summary classes;
139
-
- the subset where the static target yields MUST and some admissible target
140
-
does not (the A14 hard-KILL witness count).
159
+
- candidates whose **observed first-party targets in this compilation**
160
+
have different guarded summary classes. The class is computed by the
161
+
shadow measurement, never by the side report;
162
+
- the subset where the static target yields MUST and some observed target
163
+
does not: the A14 hard-KILL witness count.
141
164
142
165
Dispatch class is not in the facts. The measurement therefore comes from a
143
-
**side report** of the extractor: an opt-in flag that writes a separate JSON
144
-
keyed by call site. It is not OwnIR, not read by either engine, and facts
145
-
are byte-identical when it is off (N2). It is an instrument, not a fact, and
146
-
it is reported, not acted upon.
166
+
**side report** of the extractor. It is strictly measurement:
167
+
- it is opt-in, and writes a separate JSON keyed by call site;
168
+
- it is not OwnIR and not read by either engine, and facts are
169
+
byte-identical when it is off (N2);
170
+
- it emits only Roslyn/source dispatch metadata: `dispatch: exact | open`,
171
+
plus the **observed first-party targets in this compilation**;
172
+
- it never calls those targets "admissible" or "the implementations". For
173
+
an open-world virtual/interface call they are not the exhaustive runtime
174
+
set, and the report says so;
175
+
- it computes no guarded summary class and decides nothing about safety;
176
+
that is the shadow measurement's job;
177
+
- no conflicting observed target never turns an `open` call into one proven
178
+
safe for phase C. `open` stays `open` in every count.
147
179
-**R record-absence:** first-party resolved callees with no `functions[]`
148
180
record, how many guarded paths end there, and the share of otherwise-eligible
149
181
guarded chains that break on R.
@@ -167,7 +199,9 @@ exactly one of:
167
199
| G10 | the contradictory sidecar no longer changes the shadow | the N4 required-read test fails |
168
200
| G11 | the report drops `static_dispatch_conditional` or acts on dispatch | the A14 report test fails |
169
201
| G12 | an own-bridge / own-cli source change sneaks in | the N2 path guard fails |
170
-
| G13 | a synthetic guarded-vs-legacy pair outside the three classes | the classifier reports `UNEXPLAINED` (it is not silently bucketed) |
202
+
| G13 | a synthetic guarded-vs-legacy pair outside the classes of its level | the summary or application classifier reports `UNEXPLAINED` (it is not silently bucketed); a pair whose only justification would be G-T2a is `UNEXPLAINED` too |
203
+
| G14 | a shadow run over any input not at `population_commit``571669e`| the report generator refuses; population drift is not a measurement |
204
+
| G15 | the side report marks an `open` call as safe, or emits a summary class | the side-report schema test fails |
171
205
172
206
## D. Hard KILL / PASS
173
207
@@ -181,21 +215,23 @@ semantics here, and triggers when:
181
215
comment;
182
216
4. any positive guarded conclusion (a selected MUST / NO, or borrow) is
183
217
produced where §0.9 requires `NO_GUARDED_EVIDENCE`;
184
-
5.`UNEXPLAINED > 0` on the population. Each such difference is classified
185
-
under §10.1 before anything else happens; case 5 goes to the owner;
218
+
5.`UNEXPLAINED > 0` in the summary or the application report. Each such
219
+
difference is classified under §10.1 before anything else happens; case 5
220
+
goes to the owner;
186
221
6. the fail-closed join (A15) cannot be implemented from the A2 facts without
187
222
a sidecar/OwnIR change. That is a case-5 STOP, as B0 §E.3 item 3 foresaw;
188
223
7. A14 is assumed away or acted on;
189
224
8. the kernel is re-implemented rather than reused;
190
-
9. the budget below is exceeded.
225
+
9. any hard cap in §F is reached with the work unfinished. That is a STOP
- the first shadow report is committed as evidence (population, commit,
197
233
toolchain), together with the A14 and R metrics;
198
-
- the degradation census, and the classification counts with
234
+
- the degradation census, and the classification counts of both reports with
199
235
`UNEXPLAINED = 0`.
200
236
201
237
A PASS authorizes nothing further by itself. The A14 gate and the R value
@@ -205,7 +241,15 @@ authorization.
205
241
206
242
## E. Population (the first shadow run)
207
243
208
-
All of it is at one commit and one toolchain. The legacy side is `own-bridge`'s MOS (the Rust production core); Python/Rust parity is already gated by P-022, and B1 does not re-measure it. The population:
244
+
**`population_commit` = `571669e`** (frozen by the owner). Every input is
245
+
read from that exact commit, materialized from git as the A2 evidence harness
246
+
does, and the run uses one toolchain.
247
+
- The legacy side is `own-bridge`'s MOS, the Rust production core. Python/Rust
248
+
parity is already gated by P-022, and B1 does not re-measure it.
249
+
- Fixtures B1 adds later are **acceptance tests only**; they are never added
250
+
to this measurement population (G14).
251
+
252
+
The population:
209
253
- the repository C# tree (`frontend/`, `audit/`);
210
254
- the committed corpus (the 137 files of `corpus/real-world`, `wpf`, `di`,
211
255
`fixtures`, `p036-bakeoff`);
@@ -219,21 +263,56 @@ evidence, not a gate on verdicts.
219
263
220
264
## F. Budget and stop point
221
265
222
-
Budget:
223
-
-`own-guarded`: at most ~900 lines of non-test Rust. That covers the join,
224
-
the fact-to-system builder, the dynamic full-sweep driver, application
225
-
through `apply`, and the classifier.
226
-
-`own-shadow`: one report entry point, at most ~200 lines, following owner
227
-
decision R-1: stdin is the facts document, stdout is the report, and it
228
-
takes no path arguments.
229
-
- The extractor side report (A14): at most ~150 lines of C#, opt-in.
230
-
- The architecture and reuse guards, plus fixture tests.
231
-
- No new framework.
266
+
Hard caps (owner amendment; measured as handwritten lines, excluding blank
267
+
lines and comments, by the same counter for every file):
232
268
233
-
Twice the budget is a STOP and a re-plan, not a quiet overrun (the #369 lesson).
269
+
| scope | cap |
270
+
|---|---|
271
+
|`own-guarded`, non-test Rust |**900**|
272
+
|`own-shadow`, B1 additions (the report entry point) |**200**|
0 commit comments