Skip to content

Commit a319a95

Browse files
committed
P-037 Phase B / B1-F2-F2: name T_B at the widened instrument (9418f57's evidence)
Fills exactly the one named_later field this retake authorizes changing, after both the seam-widening fix and the R_B retake went terminal-green (naming last, not before -- the same order every prior T_B/R_B naming in this epoch used): T_B = fdde0a0 Supersedes cfe7e19, kept exactly as committed, not rewritten: that head was terminal-green in its own right, but its evidence was measured against an extractor seam later proven mechanically insufficient (formal-kernel.md #10.8f) -- ConsumeReleaseArgs/ConsumesParam/ CallReleasesReceiver alone cannot remove EmitFlowExpr's fabricated release without destroying caller obligation tracking (7/8 named fixtures orphaned, the 8th corrupted, proven via a never-committed scratch prototype). fdde0a0 is the first head where the seam itself is widened (EmitFlowExpr added as a fourth, separately-authorized method) and terminal-green: CI 32/32 (run #2244), fast Kani independently reconfirmed 15/15 from the raw job log, instrument_identity d93e34e0a6e740ad4ffaa6c1894f32c14fbded79b50b5fc2f678da860d2108d7 (confirmed different from cfe7e19's value, as expected). R_B stays named by the same manifest path (docs/evidence/p037-b-baseline- manifest.md) -- its content was retaken in place at 9418f57 (CI 32/32, fast Kani 15/15 independently reconfirmed from the raw job log), identical facts/verdicts/conformance to the superseded take (192/192 file parity, 105/105 findings, 55/55 fact shapes, all match; --post-a1 still fully RED on both engines). 9418f57 went CI-green before this naming commit was written, per the same order. Adds superseded_by_b1_f2_f2 (cfe7e19/069d5bc, the record this fix supersedes) alongside the existing superseded_by_b1_f2 (a02ccf1/df9a433). B_treatment_head and B_after_evidence stay null -- no semantic treatment exists yet; B2.1a remains separate, later, and not yet authorized. This commit touches nothing else: not mos.rs, not lower.rs, not Program.cs, not any script, test, or formal-kernel file. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AN6xHbpovxrmZ4AMjS7WQA
1 parent 9418f57 commit a319a95

1 file changed

Lines changed: 9 additions & 2 deletions

File tree

‎docs/evidence/p037-b-epoch.json‎

Lines changed: 9 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -255,12 +255,19 @@
255255
"R_B": "docs/evidence/p037-b-baseline-manifest.md",
256256
"status": "historical: honest B1 evidence at a boundary later found incomplete; not a baseline for any future comparison; superseded by the T_B/R_B this same field family names once B1-F2's own retake lands (see named_later below)"
257257
},
258-
"named_later": {
258+
"superseded_by_b1_f2_f2": {
259+
"reason": "B1-F2's own corrected extractor seam (ConsumeReleaseArgs/ConsumesParam/CallReleasesReceiver, mos.rs/lower.rs-style carve-out) was itself mechanically too narrow for the future B2.1a treatment. B1-F2-F2 (formal-kernel.md #10.8f) proved, via a never-committed scratch prototype run against all 8 named acceptance fixtures plus the full corpus/p036-bakeoff and corpus/p037-shapes populations, that the existing 3-method seam cannot remove EmitFlowExpr's fabricated release without destroying caller obligation tracking: 7 of 8 fixtures had their caller orphaned out of functions[] entirely, the 8th lost tracking of an unrelated, genuinely-owned local. The fix widens scripts/p037_b_extractor_diff_gate.py's MUTABLE_METHODS to include EmitFlowExpr as a fourth, separately-authorized method -- the seam that owns release-emission, decoupled from ConsumeReleaseArgs's tracking role, which stays frozen. The measurements below were honest at the boundary B1-F2 drew -- the boundary was incomplete, not the measurement -- so they are superseded, never deleted or rewritten.",
259260
"T_B": "cfe7e19c4f6a9f4d2d7606bcc6f288b52f196bcd",
260261
"T_B_title": "P-037 Phase B / B1-F2: correct the extractor's instrument/treatment boundary",
261262
"R_B": "docs/evidence/p037-b-baseline-manifest.md",
263+
"status": "historical: honest B1-F2 evidence at a boundary later found mechanically insufficient; not a baseline for any future comparison; superseded by the T_B/R_B this same field family names once B1-F2-F2's own retake lands (see named_later below)"
264+
},
265+
"named_later": {
266+
"T_B": "fdde0a026d264ceff0e44f8c86e7d059207f67e6",
267+
"T_B_title": "P-037 Phase B / B1-F2-F2: the extractor seam itself was still too narrow",
268+
"R_B": "docs/evidence/p037-b-baseline-manifest.md",
262269
"B_treatment_head": null,
263270
"B_after_evidence": null,
264-
"note": "filled by B1-F2, naming last per the same order used every prior time (boundary fix terminal-green at cfe7e19 -- CI 32/32, fast Kani 15/15 independently reconfirmed from the raw log -- THEN R_B retaken fresh at it and itself terminal-green at 069d5bc -- CI 32/32, fast Kani 15/15 -- THEN this naming commit). B_treatment_head/B_after_evidence stay null: no semantic treatment exists yet. See superseded_by_b1_f2 for what T_B/R_B named before this fix."
271+
"note": "filled by B1-F2-F2, naming last per the same order used every prior time (seam-widening fix terminal-green at fdde0a0 -- CI 32/32, fast Kani 15/15 independently reconfirmed from the raw log -- THEN R_B retaken fresh at it and itself terminal-green at 9418f57 -- CI 32/32, fast Kani 15/15 independently reconfirmed from the raw log -- THEN this naming commit). B_treatment_head/B_after_evidence stay null: no semantic treatment exists yet -- B2.1a is separate, later, and not yet authorized. See superseded_by_b1_f2_f2 for what T_B/R_B named before this fix, and superseded_by_b1_f2 for the one before that."
265272
}
266273
}

0 commit comments

Comments
 (0)