22
33epoch: ` b `
44
5- T_B (terminal-green, the measurement-instrument head): ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd `
5+ T_B (terminal-green, the measurement-instrument head): ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 `
66
7- population_commit (every take): ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd `
7+ population_commit (every take): ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 `
88
99environment: ` P037_B_MEASUREMENT_M3 `
1010
@@ -17,48 +17,59 @@ retaken, compared, or treated as a control here (`docs/evidence/p037-b-
1717epoch.json` 's own ` predecessor` / ` environment` sections state this
1818precisely).
1919
20- ## This is a retake , not the first or second R_B
20+ ## This is the third R_B , not the first or second
2121
2222The instrument this take measures against is not the one ` a02ccf1 ` /
23- ` df9a433 ` measured against. That earlier instrument was itself terminal-
24- green and honestly measured, but B1-F2 found a boundary defect in it:
25- ` frontend/roslyn/OwnSharp.Extractor/ ` was classified as full measurement
26- INSTRUMENT with no carve-out at all, while the frozen A1 acceptance matrix
27- (` docs/notes/p037-formal-kernel.md ` #8 .1, items 5 and 8) requires an
28- extractor-side semantic change there -- a treatment surface cannot
29- simultaneously be frozen measurement instrument. B1-F2
30- (` docs/notes/p037-formal-kernel.md ` #10 .8e) corrected the boundary:
31- ` scripts/p037_evidence_b.py ` 's ` INSTRUMENT_CARVE_OUTS ` /` TREATMENT_PATHS `
32- now carve the whole extractor directory out (the same shape ` mos.rs ` /
33- ` lower.rs ` already had), policed at method granularity by a new, second
34- item-level gate, ` scripts/p037_b_extractor_diff_gate.py ` . This is a
35- governance-boundary correction, not a semantic one: no byte of
36- ` mos.rs ` /` lower.rs ` /` Program.cs ` moved, ` p037_controls.py --post-a1 `
37- stayed fully RED throughout (reconfirmed below), and the fix is purely
38- about what counts as instrument versus treatment in the provenance
39- closure. ` a02ccf1 ` , ` df9a433 ` and ` bfa8647 ` are kept exactly as
40- committed -- honest records of the instrument and its baseline at the
41- boundary B1 originally drew -- superseded here, not rewritten: ` git log `
42- on this file's path still shows their content, and
23+ ` df9a433 ` or ` cfe7e19 ` /` 069d5bc ` measured against. B1-F2-F2
24+ (` docs/notes/p037-formal-kernel.md ` #10 .8f) found the B1-F2-corrected
25+ extractor seam -- ` ConsumeReleaseArgs ` /` ConsumesParam ` /` CallReleasesReceiver `
26+ alone -- was itself mechanically too narrow for the future B2.1a semantic
27+ treatment: ` ConsumeReleaseArgs ` 's answer is read by two different
28+ consumers, ` EmitFlowExpr ` (to fabricate the unconditional ` release ` ) and
29+ the escape/tracking admission check (` consumedArg ` , deciding whether a
30+ local stays tracked at all). A scratch prototype (never committed --
31+ ` git diff f8ffd42 -- frontend/roslyn/OwnSharp.Extractor/Program.cs ` is
32+ empty at this head) proved that changing ` ConsumeReleaseArgs ` 's answer
33+ to stop the fabrication also starves the tracking admission check: 7 of
34+ the 8 named acceptance fixtures had their caller orphaned out of
35+ ` functions[] ` entirely, and the 8th lost tracking of an unrelated,
36+ genuinely-owned local. B1-F2-F2 widened ` mutable_methods ` to include
37+ ` EmitFlowExpr ` as a fourth, separately-authorized method -- the seam that
38+ actually owns release-* emission* , decoupled from ` ConsumeReleaseArgs ` 's
39+ tracking role, which stays frozen and unchanged. This is a governance-
40+ boundary widening, not a semantic one: no byte of ` Program.cs ` moved
41+ (confirmed against ` f8ffd42 ` ), ` p037_controls.py --post-a1 ` stays fully
42+ RED (reconfirmed below), and the fix is purely about which existing
43+ methods a future B2.1a commit is authorized to change. ` a02ccf1 ` ,
44+ ` df9a433 ` , ` bfa8647 ` , ` cfe7e19 ` , ` 069d5bc ` , and ` 5579d80 ` /` f8ffd42 ` are
45+ kept exactly as committed -- honest records of the instrument and its
46+ baseline at the boundary each held at the time -- superseded here, not
47+ rewritten: ` git log ` on this file's path still shows their content, and
4348` docs/evidence/p037-b-epoch.json ` 's own ` superseded_by_b1_f2 ` section
44- names them explicitly, machine-readable, with the reason.
49+ (plus the B1-F2-F2 treatment note) names them explicitly, machine-
50+ readable, with the reason. Full investigation detail (Finding A/B/C, the
51+ scratch-measured blast radius, the chosen not-yet-implemented direction)
52+ is in ` docs/notes/p037-formal-kernel.md ` #10 .8f and
53+ ` docs/evidence/p037-b-epoch.json ` 's ` treatment.b1_f2_f2_seam_investigation `
54+ -- not duplicated here.
4555
4656## Instrument identity
4757
4858```
49- 3591d8056a1debabca046ad1faa1715c71516f0ef37d2037da817a3bde2c5d2d
59+ d93e34e0a6e740ad4ffaa6c1894f32c14fbded79b50b5fc2f678da860d2108d7
5060```
5161
5262Read from each take's own ` instrument_identity ` field (computed by
53- ` p037_evidence_b.evidence_fields() ` , over Phase B's own, now-corrected
54- ` INSTRUMENT_PATHS ` /` INSTRUMENT_CARVE_OUTS ` -- the B1-F2 fix). All four
55- takes below agree on it, byte-for-byte. This differs from the value the
56- superseded baseline recorded
57- (` 75764c81ac49185adad6a02657b373a7453fc03ba337bb61b86d4694bd8d5065 ` ) --
63+ ` p037_evidence_b.evidence_fields() ` , over Phase B's own
64+ ` INSTRUMENT_PATHS ` /` INSTRUMENT_CARVE_OUTS ` , unchanged by B1-F2-F2 -- only
65+ the extractor diff-gate's own ` mutable_methods ` registration moved). All
66+ four takes below agree on it, byte-for-byte. This differs from the value
67+ the superseded baseline recorded
68+ (` 3591d8056a1debabca046ad1faa1715c71516f0ef37d2037da817a3bde2c5d2d ` ) --
5869expected and confirmed by direct measurement, not assumed: widening
59- ` INSTRUMENT_CARVE_OUTS ` to include the whole extractor directory is
60- exactly the kind of instrument-definition change that must move this
61- digest, and it does.
70+ ` scripts/p037_b_extractor_diff_gate.py ` 's ` MUTABLE_METHODS ` is exactly the
71+ kind of instrument-definition change that must move this digest, and it
72+ does.
6273
6374## Execution profile (M3, identical across all four takes)
6475
@@ -72,7 +83,7 @@ the fourth take (this retake reuses the same qualified M3 environment
7283every prior Phase-B take in this session used; only the instrument
7384definition changed, not the toolchain, so a fresh before/after pair was
7485not repeated -- the one capture below, byte-for-byte identical to both
75- prior R_B manifests' own recorded profile, is the evidence for that):
86+ prior ` R_B ` manifests' own recorded profile, is the evidence for that):
7687
7788``` json
7889{
@@ -99,7 +110,7 @@ prior R_B manifests' own recorded profile, is the evidence for that):
99110}
100111```
101112
102- Byte-for-byte identical to both prior ` R_B ` manifests' own recorded
113+ Byte-for-byte identical to all three prior ` R_B ` manifests' own recorded
103114profile (and, in turn, to ` docs/evidence/p037-a2d-baseline-mos-repo.json ` 's
104115recorded M2 profile) -- the same physical workspace and toolchain,
105116re-verified rather than assumed unchanged.
@@ -115,16 +126,16 @@ the environment):
115126- Rust: rustc/cargo 1.94.1.
116127
117128recipe sha256 (unchanged since qualification; the environment itself was
118- not touched by B1-F2):
129+ not touched by B1-F2-F2 ):
119130
120131```
1211325fe4ece4c24b720f659a49bbc68b8438080c9e4b8ba554ee40f6eea94c66eb26
122133```
123134
124135Recipe: ` provision.sh ` , retained outside this repository at
125136` /root/p037-a2d-m2-recipe/provision.sh ` on the qualified machine. The
126- environment/toolchain was not changed by B1-F2 -- only the instrument's
127- own ` INSTRUMENT_PATHS ` / ` INSTRUMENT_CARVE_OUTS ` definition moved.
137+ environment/toolchain was not changed by B1-F2-F2 -- only the extractor
138+ diff-gate's own ` mutable_methods ` definition moved.
128139
129140## Workspace
130141
@@ -146,23 +157,23 @@ new T_B before the next was started. None ran concurrently.
1461574 . verdict/rust snapshot (` --epoch b --engine rust ` )
147158
148159All four takes and verifies exited 0. The checkout was clean at
149- ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd ` before the first take and
160+ ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 ` before the first take and
150161remained at that exact commit, clean, after the fourth verify.
151162
152- | p037-b-baseline-mos-repo.json | ` bf8c6a9bb9595b2cfe53eeba368365a583dde561ceb174e843e92585e64e5e09 ` |
153- | p037-b-baseline-mos-corpus.json | ` d4fd0f7e553c33b144656be8b4df3c5e82f8d4b28b86ed1324e6cd3a371e98db ` |
154- | p037-b-baseline-verdict-python.json | ` 970f80ceb23215127ecd1838ff640ffd0b26294425523ba90e4b88a8688edc85 ` |
155- | p037-b-baseline-verdict-rust.json | ` cbad406da85ffa71bc6028e2b9fc066c570ea62c5d5bfe86f40d7382bb72a311 ` |
163+ | p037-b-baseline-mos-repo.json | ` 9d06afd0471485c93979a4c1f9355a6fcd7f91408d1dd6293ded2bc6f8934c1c ` |
164+ | p037-b-baseline-mos-corpus.json | ` c0421181f37c41b685f14cdf0c37f1251b3fbf7f34056ccd0eeaa87634b62423 ` |
165+ | p037-b-baseline-verdict-python.json | ` 96623cf01d289ead9df0ee67aa0df1b8b77b0cd740d3a0e62630827d0cbfcaab ` |
166+ | p037-b-baseline-verdict-rust.json | ` e98ff9b81a1c3aab7059a86495cf48a5169888f8512966450182af78ac4649d6 ` |
156167
157168Every record above carries, and all four agree on:
158169
159- - ` source_commit ` : ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd `
160- - ` population_commit ` : ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd `
170+ - ` source_commit ` : ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 `
171+ - ` population_commit ` : ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 `
161172- ` epoch ` : ` b `
162173- ` environment_id ` : ` P037_B_MEASUREMENT_M3 `
163174- ` dirty ` : ` false `
164175- ` is_evidence ` : ` true `
165- - ` instrument_identity ` : ` 3591d8056a1debabca046ad1faa1715c71516f0ef37d2037da817a3bde2c5d2d `
176+ - ` instrument_identity ` : ` d93e34e0a6e740ad4ffaa6c1894f32c14fbded79b50b5fc2f678da860d2108d7 `
166177
167178## Cross-engine parity at baseline
168179
@@ -176,17 +187,24 @@ snapshots do not have a built-in cross-engine comparator by design
176187pair: "measures the engine, not the change"), so parity was checked
177188directly: all 192 corpus files carry identical ` (line, code, level) `
178189finding sets and identical exit codes on both engines -- 105 findings
179- each side, 0 mismatches, exactly matching both prior ` R_B ` takes' own
180- numbers. This is the empirical form of the frozen ` facts_expectation `
181- claim (` docs/evidence/p037-b-epoch.json ` 's ` measurement_policy ` ): nothing
182- about the pre-treatment facts or verdict surface moved -- not on the
183- first instrument, not on the B1-F1-corrected instrument, and not on the
184- B1-F2-corrected instrument boundary either, because B1-F2 changed no
185- production semantics.
190+ each side, 0 mismatches, exactly matching all three prior ` R_B ` takes' own
191+ numbers. Diffing the four new JSON artifacts against their immediately
192+ preceding (` cfe7e19 ` -based) counterparts confirms the same thing from the
193+ other direction: every changed line is a commit-identity field
194+ (` source_commit ` , ` population_commit ` , ` materialization_root ` ,
195+ ` instrument_identity ` , ` blob ` , an ephemeral ` sealed_path ` tmpdir) or a
196+ population-commit substring embedded in a sampled file path -- zero
197+ findings, facts, or verdict content differs. This is the empirical form
198+ of the frozen ` first_semantic_hypothesis.facts_expectation ` claim
199+ (` docs/evidence/p037-b-epoch.json ` ): nothing about the pre-treatment facts
200+ or verdict surface moved -- not on the first instrument, not on the
201+ B1-F1-corrected instrument, not on the B1-F2-corrected instrument
202+ boundary, and not on the B1-F2-F2-widened extractor seam either, because
203+ B1-F2-F2 changed no production semantics.
186204
187205## P-037 conformance baseline at T_B
188206
189- Both re-run fresh at ` cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd ` , `OWEN_
207+ Both re-run fresh at ` fdde0a026d264ceff0e44f8c86e7d059207f67e6 ` , `OWEN_
190208RUST_CORE` pointed at the qualified ` own-cli` release build:
191209
192210- ` python scripts/p037_controls.py --engine both ` : ` RESULT: all match ` (the
@@ -195,15 +213,16 @@ RUST_CORE` pointed at the qualified `own-cli` release build:
195213- ` python scripts/p037_fact_shapes.py check --engine both ` : `RESULT: all 55
196214 shape(s) match their recorded facts and verdicts`.
197215
198- Identical results to both prior ` R_B ` takes' own recorded conformance
199- state. Also reconfirmed at this same head: `python scripts/p037_controls.py
200- --post-a1 --engine both` stays fully RED ( ` RESULT: mismatch`) on all four
201- controls, both engines -- no semantic treatment occurred as part of this
202- boundary fix. Recorded here as the P-037 conformance state at the new
203- T_B, per the B1 brief's own instruction to measure and record it, not to
204- chase or repair it as part of this baseline.
216+ Identical results to all three prior ` R_B ` takes' own recorded
217+ conformance state. Also reconfirmed at this same head: `python
218+ scripts/p037_controls.py --post-a1 --engine both` stays fully RED
219+ (` RESULT: mismatch ` , exit code 1, all four controls disagreeing with the
220+ post-A1 target on both engines) -- no semantic treatment occurred as part
221+ of this seam-widening fix. Recorded here as the P-037 conformance state at
222+ the new T_B, per the B1 brief's own instruction to measure and record it,
223+ not to chase or repair it as part of this baseline.
205224
206- Run time/date: 2026-09-24, ~ 04:26-05:10 UTC, operator run.
225+ Run time/date: 2026-09-24, operator run.
207226
208227This commit is evidence-only: it updates exactly five files under
209228` docs/evidence/ ` (these four JSON artifacts plus this manifest, all
@@ -212,5 +231,5 @@ instrument, treatment, spec, tooling, or CI file is touched.
212231` docs/evidence/p037-b-epoch.json ` 's ` named_later.T_B ` /` R_B ` are not
213232updated by this commit -- that is the naming commit's own, separate act,
214233after this evidence is itself terminal-green, mirroring exactly how
215- ` df9a433 ` preceded ` bfa8647 ` the first retake , and ` 40cb9b4 ` preceded
216- ` 2ed4d92 ` before that .
234+ ` df9a433 ` preceded ` bfa8647 ` , and ` 069d5bc ` preceded ` 5579d80 ` / ` f8ffd42 ` ,
235+ before it .
0 commit comments