Skip to content

Commit ee73dd1

Browse files
committed
P-037 B0: pre-register the proof-boundary audit (question, conditions, falsifiers, KILL/PASS)
Before any manifest or checker: docs/notes/p037-phase-b-proof-boundary.md §§A-D freezes the B0 question, the necessary conditions N1-N8, the cheap falsifiers F1-F10 and the hard KILL / PASS rule. §A.1 discloses what exploration saw before these criteria were written, so it is judged by the rule rather than argued afterwards: - the kernel is not referenced by production; - the kernel is bounded to one SCC; - solve/elect are full sweeps while solve_with/elect_with take a schedule (#368); - G-S4 placement is recoverable only through the body/sidecar line join (a refuted indistinguishability hypothesis, an observed same-line if ambiguity); - dispatch is statically resolved everywhere. KILL 9 adds the research question's own stop condition: an assumption that only the future B1 adapter could guarantee, and that cannot be discharged fail-closed from the A2 fact surface, is a hidden precondition (case 5). No semantic change. No audit code yet. Refs #304 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KmiyfrkaG9sJruTcshM2oq
1 parent 0ae8213 commit ee73dd1

1 file changed

Lines changed: 187 additions & 0 deletions

File tree

Lines changed: 187 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,187 @@
1+
# P-037 Phase B0: the formal/production proof-boundary audit (pre-registered)
2+
3+
> Status: **PRE-REGISTERED. No manifest, checker, or audit code written.**
4+
> §§A–D are committed before any audit artifact, so the result is judged
5+
> against them rather than an impression afterwards. Governance:
6+
> `docs/notes/p037-formal-kernel.md` §10.1 (finding classes), §10.4 (the
7+
> Phase-B proof boundary), §10.6 (the R ruling). Base: A2.2 closed on #371 at
8+
> `0ae821356ae03cd185e845cc46be45b700f1e064`. Branch:
9+
> `research/p037-phase-b-proof-boundary`.
10+
>
11+
> Evidence tags as elsewhere: `REPOSITORY FACT`, `MEASURED OBSERVATION`,
12+
> `INFERENCE`, `OWNER RULING`.
13+
14+
This change **starts no semantic wiring**. It does not touch guarded summary
15+
values, solver output, MOS, verdicts, `ConsumesParam`, Roslyn sidecar facts,
16+
the OwnIR schema, or kernel semantics.
17+
18+
## A. Question
19+
20+
Can every load-bearing formal assumption of P-037 be honestly linked to one of
21+
two things?
22+
23+
- a **production guarantor** that exists today, with a concrete mechanism and
24+
an executable control;
25+
- an explicit **outside-the-Kani-boundary** declaration, stating what is not
26+
proved, why, and what controls it.
27+
28+
And can this be done without finding a hidden precondition between the Roslyn
29+
facts and the guarded kernel?
30+
31+
If not: **STOP** before any semantic implementation.
32+
33+
### A.1 What was already seen before registration (disclosed, not hindsight)
34+
35+
Reading the governing text and the kernel, and running two extractor probes
36+
(scratch `.cs` files, not committed), established the following before these
37+
criteria were written. They are listed so they are judged by the rule below,
38+
not argued afterwards.
39+
40+
- `REPOSITORY FACT`: nothing in production (`rust/`, `ownlang/`) references
41+
the kernel crate `formal/p037-kernel`. The A1 production landing has not
42+
happened. The only production code on the P-037 path today is the fact
43+
producer (Roslyn `BuildGuardedFacts`) and the OwnIR doors, which validate the
44+
sidecar and keep it inert.
45+
- `REPOSITORY FACT`: the kernel is bounded (`MAX_COORDS = 3`,
46+
`MAX_EDGES = 2`), and its `System` holds one SCC. It models neither
47+
composition across SCCs nor a dynamic driver.
48+
- `REPOSITORY FACT`: `solve` / `elect` are Jacobi, so they visit every live
49+
coordinate on every pass by construction. `solve_with` / `elect_with` take an
50+
arbitrary schedule, which is the #368 hazard.
51+
- `MEASURED OBSERVATION` (probe): the kernel's G-S4 mask ("which forward sits
52+
under which literal") has no field in the sidecar.
53+
- A hypothesis was tested and **refuted**: that two programs differing only in
54+
whether a borrowing forward sits inside or after an eligible `if` produce
55+
byte-identical facts. They don't. Legacy lowering emits a `use` op placed in
56+
the body tree, and the sidecar call carries its `statement_line`.
57+
- Placement is therefore recoverable only by *joining* the sidecar to the
58+
legacy body by line (the §10.5 call-site identity). Body `if` ops carry no
59+
column, so two `if`s on one line make the guard↔`if` join ambiguous
60+
(observed).
61+
- `REPOSITORY FACT`: the legacy `ConsumesParam` and the whole-analyzer summary
62+
keying read the *statically resolved* callee's body. Virtual or override
63+
dispatch is not represented anywhere in the facts.
64+
65+
## B. Necessary conditions (all must hold)
66+
67+
- **N1 — harness inventory complete.**
68+
- The set of `#[kani::proof]` functions under `formal/p037-kernel/src` is
69+
derived from source, never from a maintained number.
70+
- The fast set (`ci.yml` job `formal-p037`) and the heavy set
71+
(`formal-p037-gate.yml`) are also derived from source.
72+
- It must hold that `fast ∩ heavy = ∅` and `fast ∪ heavy = source`, with
73+
`missing = extra = overlap = 0`.
74+
- A harness in no set, or a CI name that is no harness, is a FAIL.
75+
- **N2 — every harness has a human claim.** Each records:
76+
- the harness;
77+
- its P-037 claim;
78+
- a concrete production subject: kernel symbols such as `Transfer::join`,
79+
`System::step`, `solve`, `apply`, never "kernel correctness";
80+
- its assumptions;
81+
- its CI class.
82+
- **N3 — every load-bearing assumption is classified exactly once**, as
83+
`PRODUCTION_GUARANTOR` or `OUTSIDE_KANI_BOUNDARY`.
84+
- A `PRODUCTION_GUARANTOR` needs a mechanism that exists today. It must say
85+
what it guarantees, where, up to which consumer, and what happens on
86+
violation. It also needs an executable control.
87+
- An `OUTSIDE_KANI_BOUNDARY` entry states what is not proved, why that is
88+
deliberate, and what controls it. "Nothing yet, because nothing consumes
89+
it" is allowed only when a named obligation binds the first consumer (B1).
90+
- An assumption that holds only on a comment fails.
91+
- "assumed", "obvious", "frontend handles this" and "well_formed somehow"
92+
are rejected.
93+
- **N4 — the bounded adapter is stated honestly.**
94+
- Kani `MAX_COORDS = 3`, `MAX_EDGES = 2`, checked against `lib.rs`.
95+
- Production is a dynamic coordinate/edge count.
96+
- No claim that Kani proved a production-size bound. The generic Rocq result
97+
(#369/#370) may be cited as external research evidence only, never as a
98+
dependency.
99+
- **N5 — production well-formedness has guarantors.** Election shape and
100+
import, `Uncond` diagonality, `id`/`neg` admissibility, guard stability
101+
(G-V4), cell-local release consistency, finalization before application,
102+
fair/full visitation, and missing record/sidecar under R. Each must have one
103+
of:
104+
- a producer invariant;
105+
- runtime/kernel validation;
106+
- construction-by-API;
107+
- an executable negative control;
108+
- `OUTSIDE_KANI_BOUNDARY`.
109+
- **N6 — application ordering is pinned.** F2 (`fin` before
110+
select/collapse/apply) has a control that breaks if raw solver state is
111+
applied before finalization, and a mutant proves it breaks. A Kani harness
112+
alone does not count.
113+
- **N7 — fairness / #368 is not hidden.** The production-side contract is one
114+
of three:
115+
- (A) full visitation by construction;
116+
- (B) validated coverage;
117+
- (C) #368 as a mandatory blocker before any schedule-taking API is used.
118+
119+
"The caller is expected to pass a fair schedule" is a FAIL. So is any
120+
production path that could call the solver with an unchecked, externally
121+
supplied schedule.
122+
- **N8 — R stays fail-closed.** A missing `functions[]` record and a missing
123+
`guarded_facts` are both recorded as `NO_GUARDED_EVIDENCE`. They are never
124+
`no effects`, borrow, unconditional, guard-irrelevant, or `must`.
125+
`record-absence-boundary` is the Phase-B negative control.
126+
127+
## C. Cheap falsifiers (each must be demonstrated to fire)
128+
129+
| id | mutation | must happen |
130+
|---|---|---|
131+
| F1 | drop one real harness from a CI set; add a fake harness name | audit FAIL (missing / extra) |
132+
| F2 | put one harness in both fast and heavy | audit FAIL (overlap) |
133+
| F3 | a manifest assumption with no class, or a vague guarantor | audit FAIL |
134+
| F4 | a guarantor or control pointing to a path/symbol that does not exist | audit FAIL |
135+
| F5 | the kernel's `apply` stops finalizing (`apply before fin`) | the finalize-before-apply control goes red (`cargo test`, temp copy) |
136+
| F6 | R absence reinterpreted as any positive claim | audit FAIL |
137+
| F7 | a minimal #368-class unfair schedule | an executable witness shows `Some(non-fixpoint)`, and the audit fails if fairness is "the caller's job" |
138+
139+
Additional falsifiers found before registration (§A.1), judged by the same
140+
rule:
141+
142+
| id | mutation | must happen |
143+
|---|---|---|
144+
| F8 | a production file (outside `formal/`) that calls a schedule-taking kernel API (`solve_with`, `elect_with`, `lfp_chaotic`) | audit FAIL: this makes N7 option (C) executable, not prose |
145+
| F9 | a production file that imports the kernel and lowers or collapses cells directly instead of through `apply` | audit FAIL: the N6 bypass |
146+
| F10 | a harness whose body uses an assumption-bearing generator or predicate (`any_system`, `any_schedule`, `release_cells_have_no_edges`, `no_unknown_seed`, …) without listing the matching assumption | audit FAIL: load-bearing assumptions are derived from source, not only declared |
147+
148+
## D. Hard KILL / PASS rule
149+
150+
**KILL**: `RESULT: FAIL — PHASE B BLOCKED`, with the blockers listed and no
151+
semantic code fixed here, if any of these holds:
152+
153+
1. the harness inventory does not match the CI partition;
154+
2. a load-bearing assumption is unclassified;
155+
3. a `PRODUCTION_GUARANTOR` lacks an existing mechanism plus a control;
156+
4. no fairness production contract exists;
157+
5. the finalization ordering is not pinned by an executable control at the
158+
seam production will use;
159+
6. R absence can be interpreted positively;
160+
7. a bounded Kani result has to be presented as a production-unbounded proof;
161+
8. going green requires changing P-037 semantics;
162+
9. an assumption whose only possible guarantor is the future B1 adapter cannot
163+
be discharged fail-closed from the A2 fact surface. That is a **hidden
164+
precondition between the Roslyn facts and the kernel**: STOP. Such an
165+
amendment is case 5 (§10.1), not case 2.
166+
167+
**PASS**: `RESULT: PASS — PROOF BOUNDARY CLOSED FOR PHASE B SHADOW` only if:
168+
169+
- the inventory is exact and the CI partition exact;
170+
- every assumption is classified and every guarantor concrete;
171+
- negative controls are mapped;
172+
- #368 is explicitly handled;
173+
- R is explicitly fail-closed;
174+
- no semantic wiring was done;
175+
- F1–F10 all fire.
176+
177+
A PASS authorizes the separate step B1 (guarded shadow read, no verdict). It
178+
also carries the list of B1 entry obligations recorded in the manifest. B0
179+
does not implement B1.
180+
181+
Assumptions discovered by this audit are case 2 (a proof-boundary manifest
182+
amendment) when they can be discharged fail-closed. They are case 5 (STOP)
183+
under KILL 9.
184+
185+
**Budget.** One small checker (`scripts/p037_proof_boundary.py`), one manifest
186+
(`formal/p037-kernel/proof-boundary.json`), this note, small selftests and
187+
mutants. A new general verification framework is a STOP.

0 commit comments

Comments
 (0)