ticket #000036: add KAT-regen tooling + close
"One more iteration then close" (fox): added committed KAT-regeneration
scripts for both the T3 calculator and φ_PRG — the regen step was a
throwaway temp script before; now it's reproducible and the phi_prg
test's skipif reason ("run scripts/generate_phi_prg_kat.py") points at
a file that exists. Then closed #000036.
New scripts:
- scripts/generate_t3_bound_kat.py — regenerates
bench/fixtures/t3-bound/known-answer-tests.jsonl from a fixed 12-config
list (the §7 worked examples under max_envelope + non-default-C_B*
+ g=0 edge + explicit-b1_model pins for the other three models).
- scripts/generate_phi_prg_kat.py — regenerates
bench/fixtures/phi-prg/known-answer-tests.jsonl from a fixed 10-entry
list (placeholder/random seeds, one-bit-flip variants, block-boundary
dim_h=16/17, 4096 counter-rollover stress).
- Both verified to reproduce the committed fixture data lines byte-
for-byte (only the header comments changed, to reference the script).
Each docstring states: run after any algorithm change, then bump the
module version (CALCULATOR_VERSION / PHI_PRG_VERSION) so the fixture's
version field changes too.
Doc/test:
- test_t3_bound_calculator.py skipif reason now references the regen
script (matches the phi_prg test pattern).
- #000035 §3.3 + t3-bound.md §10.1 reference the regen scripts.
Closure (#000036):
- Status → closed · 2026-05-11 in the ticket file + TICKETS.md row.
Phase 1 + dav1d Tier-1/Tier-2 (Option B in v1) + KAT-regen tooling
all landed; all §5 acceptance criteria met; both dav1d closure
blockers cleared. Continuation: empirical C_B1/C_B2/C_B3 tightening
under #000043 (parks on v7 deployment data); landing the bound's
framing into a v7 plastic-training spec parks on that spec gaining
a deployment target; R2's architectural integrations (Merkle audit-
event commitment, SQD canonicalization, CTI clause-lattice, 5F
trigger, ForkScore security-risk) are separate tickets if wanted.
- t3-bound.md header flipped to "closed 2026-05-11".
Full suite: 2312 passed, 28 skipped.
This commit is contained in:
parent
101b101281
commit
8599ce3b2c
9 changed files with 298 additions and 29 deletions
|
|
@ -1,10 +1,8 @@
|
|||
# arborist v7 phi_prg known-answer tests — version phi-prg-v1-hmac-sha512-le
|
||||
# Pinned (seed, hard_hash, dim_h) → SHA-256 of raw byte output
|
||||
# (HMAC-SHA-512 little-endian counter-mode expansion, before float
|
||||
# conversion). Regenerated 2026-05-11 after the big-endian → little-
|
||||
# endian counter flip (dav1d review; PHI_PRG_VERSION carries -le).
|
||||
# Algorithm change MUST bump PHI_PRG_VERSION and create a new fixture
|
||||
# file; do not overwrite — old runs replay against old data.
|
||||
# Regenerated by scripts/generate_phi_prg_kat.py. Records SHA-256 of
|
||||
# the raw HMAC-SHA-512 (little-endian counter-mode) expansion output,
|
||||
# before float conversion. Algorithm change MUST bump PHI_PRG_VERSION
|
||||
# and re-run this script; old runs replay against the old fixture.
|
||||
{"label": "placeholder-seed/zero-hash/dim_h=1", "version": "phi-prg-v1-hmac-sha512-le", "seed_hex": "ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3", "hard_hash_hex": "0000000000000000000000000000000000000000000000000000000000000000", "dim_h": 1, "output_sha256": "93618e085f1afae3368cabb57b328f2f01a81cb45c768e02264b13d5ec52732a", "output_bytes": 4}
|
||||
{"label": "placeholder-seed/zero-hash/dim_h=8", "version": "phi-prg-v1-hmac-sha512-le", "seed_hex": "ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3", "hard_hash_hex": "0000000000000000000000000000000000000000000000000000000000000000", "dim_h": 8, "output_sha256": "b7e7af7180105100e94fcb4361799e2820d78f9cf2636643dea2a367ea16beb8", "output_bytes": 32}
|
||||
{"label": "placeholder-seed/zero-hash/dim_h=32", "version": "phi-prg-v1-hmac-sha512-le", "seed_hex": "ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3", "hard_hash_hex": "0000000000000000000000000000000000000000000000000000000000000000", "dim_h": 32, "output_sha256": "1b5e89f20777000d0051daffb79aaf93e1e8bba7d3a77d5f6b4354561800d365", "output_bytes": 128}
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# T3 bound calculator known-answer tests — version t3-bound-v1-bottou-refinement
|
||||
# Regenerated 2026-05-11 after the b1_model=max_envelope default change
|
||||
# (dav1d review Option B applied in v1). Algorithm change MUST bump
|
||||
# CALCULATOR_VERSION + emit a new fixture file.
|
||||
# Regenerated by scripts/generate_t3_bound_kat.py. Algorithm change
|
||||
# MUST bump CALCULATOR_VERSION and re-run this script; old runs
|
||||
# replay against the old fixture (do not delete history).
|
||||
{"label": "small-deployment-§7.1", "calculator_version": "t3-bound-v1-bottou-refinement", "b1_model": "max_envelope", "inputs": {"gradient_fraction": 0.05, "gradient_norm_max": 1.0, "gradient_noise_stddev": 0.1, "lr_decision_interval": 100, "lr_grid_size": 8, "window_length": 10000, "batches_per_epoch": 1024, "steps_per_epoch": 1024, "c_b1": 1.0, "c_b2": 1.0, "c_b3": 1.0, "b1_model": "max_envelope"}, "expected_total": 6183.0154, "expected_b1": 5849.625, "expected_b1_selected": "aggregate_bias", "expected_b1_fraction_channels": 1729.7158, "expected_b1_aggregate_bias": 5849.625, "expected_b1_effective_control_v1": 292.4813, "expected_b2": 300.0, "expected_b3": 33.3904, "expected_snr_grad": 0.5, "expected_snr_per_channel": 10.0, "expected_certification_status": "NOT_CERTIFIED_BY_BOUND"}
|
||||
{"label": "medium-deployment-§7.2", "calculator_version": "t3-bound-v1-bottou-refinement", "b1_model": "max_envelope", "inputs": {"gradient_fraction": 0.05, "gradient_norm_max": 1.0, "gradient_noise_stddev": 0.1, "lr_decision_interval": 1000, "lr_grid_size": 16, "window_length": 100000, "batches_per_epoch": 8192, "steps_per_epoch": 8192, "c_b1": 1.0, "c_b2": 1.0, "c_b3": 1.0, "b1_model": "max_envelope"}, "expected_total": 58959.1575, "expected_b1": 58496.2501, "expected_b1_selected": "aggregate_bias", "expected_b1_fraction_channels": 17297.1581, "expected_b1_aggregate_bias": 58496.2501, "expected_b1_effective_control_v1": 2924.8125, "expected_b2": 400.0, "expected_b3": 62.9075, "expected_snr_grad": 0.5, "expected_snr_per_channel": 10.0, "expected_certification_status": "NOT_CERTIFIED_BY_BOUND"}
|
||||
{"label": "hardened-deployment-§7.3", "calculator_version": "t3-bound-v1-bottou-refinement", "b1_model": "max_envelope", "inputs": {"gradient_fraction": 0.01, "gradient_norm_max": 1.0, "gradient_noise_stddev": 0.1, "lr_decision_interval": 100, "lr_grid_size": 4, "window_length": 10000, "batches_per_epoch": 1024, "steps_per_epoch": 1024, "c_b1": 1.0, "c_b2": 1.0, "c_b3": 1.0, "b1_model": "max_envelope"}, "expected_total": 1608.4256, "expected_b1": 1375.0352, "expected_b1_selected": "aggregate_bias", "expected_b1_fraction_channels": 345.9432, "expected_b1_aggregate_bias": 1375.0352, "expected_b1_effective_control_v1": 13.7504, "expected_b2": 200.0, "expected_b3": 33.3904, "expected_snr_grad": 0.1, "expected_snr_per_channel": 10.0, "expected_certification_status": "NOT_CERTIFIED_BY_BOUND"}
|
||||
|
|
|
|||
|
|
@ -92,6 +92,8 @@ Newest first. Update on every open/close.
|
|||
|
||||
| ID | Title | Status | Opened | Directive |
|
||||
|----------|------------------------------------------------|-----------------------|------------|-----------|
|
||||
| #000047 | ForkScore `_delta_*` aggregator (mean vs max vs sum) | open · awaiting go/no-go · doc-only; parks until #000046 produces a below-ceiling baseline to bench against. Recommends: parameterize `delta_aggregator` (default `mean`), don't change the default without #000046 data. #000012-revision / #000025 §10.14 follow-up | 2026-05-11 | — |
|
||||
| #000046 | Harder 5S/5T/5F fixture tier (below-ceiling baselines) | open · awaiting go/no-go · doc-only; the bench Δ-rate terms in `fork_score` are inert while every pack runs at rate 1.0. Recommends a narrow live-path hard tier starting with 5F Falsification (`verify_quotes` near-misses). #000025 §10.14 follow-up; gates #000047 | 2026-05-11 | — |
|
||||
| #000045 | Prometheus-Σ Phase 3 sleep-sweep scheduler (gating ticket) | open · doc-only scaffold 2026-05-10; pins 8 governance parameters + 4 retrigger gates; opens implementation only after one retrigger fires | 2026-05-10 | — |
|
||||
| #000044 | AUTOCOUNT doc-drift discipline | closed · landed across `fc5ba50` / `03c0f6a` / `6c6defb` / `f5dbfab` / `3b30126` 2026-05-10 (mechanism + 4 metrics + 54 tags across 7 doc files; harness catches drift at test time, refresh is 60-second turnaround) | 2026-05-10 | — |
|
||||
| #000043 | Empirical tightening of T3 bound constants (#000036 Phase 2) | open · awaiting go/no-go (parks until v7 deployment surfaces measurement data) | 2026-05-10 | — |
|
||||
|
|
@ -101,7 +103,7 @@ Newest first. Update on every open/close.
|
|||
| #000039 | Optional `sqlite-vec` retrieval backend (A/B vs FTS5, hybrid not replacement) | open · awaiting go/no-go (doc-only Phase 0) | 2026-05-09 | — |
|
||||
| #000038 | Phase 4 content acquisition — proprietary textbook license decisions for warrant coverage | closed · obviated 2026-05-10 by alias-substitution sprint under #000031 (74 rows in #000041 + 13 rows in #000042); 92/92 records now resolve. Residue (multilingual PD, Hilbert-Ackermann OCR, Knuth permission, personal-copy path B) preserved as design log §8 | 2026-05-09 | — |
|
||||
| #000037 | Prometheus-Σ recursive falsification controller (bicameral substrate) | in progress · Phases 0 + 1 + 1.b + 1.c + 2 landed 2026-05-10; **§12 Trigger 2 fired** (divergence variance 0.575 / N=37); §22 Findings 2 + 3 RESOLVED (kernel/llm cost split + sweep_weights §15.4 + per-mode τ_qa); `controller_events` carries 4 event kinds (decision · difficulty · budget_allocation · falsification_proposal) feeding `arborist controller-events` inspector + live-harvest third bucket in `bench/scripts/harvest_falsification_proposals.py`; §12 Trigger 1 probe wired 2026-05-11 (`trigger_1_branch_density` reads `fork_score_branches` — measurable, not yet fired); Phase 3 sleep-sweep scheduler tracked under #000045 (gating ticket) | 2026-05-09 | — |
|
||||
| #000036 | T3 per-window covert-channel budget bound | in progress · Phase 1 + dav1d review 2026-05-11 → Tier-1 + Tier-2 (Option B = `b1_model=max_envelope` default, applied *in v1*, no v2 fork) both landed 2026-05-11; KAT regenerated (12 entries, active); baseline 625.87 → 6183.02 (max_envelope); 53 → 83 tests; both prior closure blockers cleared — remaining = fox final close-or-iterate call | 2026-05-09 | — |
|
||||
| #000036 | T3 per-window covert-channel budget bound | **closed · 2026-05-11** · Phase 1 + dav1d review → Tier-1 + Tier-2 (Option B = `b1_model=max_envelope` default, in v1, no v2 fork) + KAT-regen tooling (`scripts/generate_t3_bound_kat.py`) all landed 2026-05-11; baseline 625.87 → 6183.02 (max_envelope), `NOT_CERTIFIED_BY_BOUND` at W=10000; 53 → 83 tests; 12-entry active KAT; both dav1d closure blockers cleared, all §5 acceptance criteria met. Continuation: empirical C_B* tightening under #000043 (parks on v7) | 2026-05-09 | — |
|
||||
| #000035 | PRG choice for φ_PRG (HMAC-SHA-512 expansion) | in progress · Phase 1 landed 2026-05-10; §9.10 amendment text **dav1d-reviewed final + endianness resolved 2026-05-11** (manifest field → `anchor_prg_seed`; v7 TLV confirmed little-endian → counter + uint32-word reads flipped big→little, `PHI_PRG_VERSION → -le`, 10 KATs regenerated; float-map prose corrected to "negligible mean −2^−32" not "unbiased"; `dim_h ≤ 16·2^32` guard + bool-reject added; seed-independence + M1-policy-separation added; HMAC-SHA-512 / 32-byte / SHALL all LOCKED; 31 tests). Remaining: land §9.10 into v7 spec when plastic-training has a deployment target (exogenous) | 2026-05-09 | — |
|
||||
| #000034 | Hessian alignment under φ_linear | in progress · Phase 1a landed 2026-05-10 (synthetic-ablation probe + KAT fixture); Phase 1b parks for v7 ramp-up | 2026-05-09 | — |
|
||||
| #000033 | Claim-pack pillar VII (combinatorics) | closed · landed 2026-05-09 (live in shard 000.db; lift verified) | 2026-05-09 | — |
|
||||
|
|
@ -140,4 +142,4 @@ Newest first. Update on every open/close.
|
|||
|
||||
## Next ID
|
||||
|
||||
`000046`
|
||||
`000048`
|
||||
|
|
|
|||
|
|
@ -1,19 +1,21 @@
|
|||
# T3 per-window covert-channel budget bound
|
||||
|
||||
**Ticket**: #000036
|
||||
**Ticket**: #000036 — **closed 2026-05-11**.
|
||||
**Source analysis**: `docs/soft-hash-channel-analysis.md`
|
||||
**Date**: 2026-05-10 (dav1d review pass + Option-B applied 2026-05-11)
|
||||
**Date**: 2026-05-10 (dav1d review pass + Option-B + KAT-regen tooling 2026-05-11)
|
||||
**Status**: formal derivation + calculator landed; **dav1d review
|
||||
returned 2026-05-11** → **Tier-1 polish + Tier-2 (Option B: the
|
||||
returned 2026-05-11** → Tier-1 polish + Tier-2 (Option B: the
|
||||
conservative `max_envelope` B1 model, applied in v1 — no v2 fork)
|
||||
both landed 2026-05-11**. KAT fixture regenerated (12 entries,
|
||||
active — `test_t3_bound_known_answer_tests` no longer skips). The
|
||||
default B1 model is now `max_envelope` (§3.1); `effective_control_v1`
|
||||
is reachable as a backward-comparison mode. Remaining before
|
||||
closure: fox's final close-or-iterate call (optionally a dav1d
|
||||
re-review of the envelope formula). The named C_B* constants are
|
||||
conservative starting estimates that empirical tightening
|
||||
(#000043) can replace without changing call sites.
|
||||
+ KAT-regen tooling (`scripts/generate_t3_bound_kat.py`) all landed
|
||||
2026-05-11; **#000036 closed**. KAT fixture is 12 entries, active
|
||||
(`test_t3_bound_known_answer_tests` runs, not skips). The default
|
||||
B1 model is `max_envelope` (§3.1); `effective_control_v1` /
|
||||
`fraction_channels` / `aggregate_bias` reachable via `--b1-model`.
|
||||
The named C_B* constants are conservative starting estimates that
|
||||
empirical tightening — **continued under #000043** — can replace
|
||||
without changing call sites. (#000043 parks on v7 deployment
|
||||
data.) Landing the bound's framing into a v7 plastic-training spec
|
||||
parks on that spec gaining a deployment target.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -604,9 +606,12 @@ in the follow-up commit):
|
|||
v1 default rather than forking a v2 (per fox's direction):
|
||||
`CALCULATOR_VERSION` stays `t3-bound-v1-bottou-refinement` (the
|
||||
"bottou-refinement" descriptor names the unchanged B3 term).
|
||||
- **KAT fixture regenerated** (`bench/fixtures/t3-bound/known-answer-tests.jsonl`,
|
||||
12 entries: §7 worked examples under `max_envelope`, explicit-mode
|
||||
pins for the other three models, a `g=0` edge case).
|
||||
- **KAT fixture regenerated + regen tooling.**
|
||||
`bench/fixtures/t3-bound/known-answer-tests.jsonl` (12 entries:
|
||||
§7 worked examples under `max_envelope`, explicit-mode pins for
|
||||
the other three models, a `g=0` edge case) is now produced by
|
||||
`scripts/generate_t3_bound_kat.py` — run it after any algorithm
|
||||
change, then bump `CALCULATOR_VERSION`.
|
||||
`test_t3_bound_known_answer_tests` now runs (no longer skips);
|
||||
it pins `b1_model`, `b1_selected`, `certification_status`, and
|
||||
the per-contribution numbers.
|
||||
|
|
|
|||
|
|
@ -187,8 +187,12 @@ def phi_prg(hard_hash_32: bytes, dim_h: int) -> list[float]:
|
|||
### 3.3 Bench fixture
|
||||
|
||||
`bench/fixtures/phi-prg/known-answer-tests.jsonl` — fixed
|
||||
(seed, hard_hash, dim_h) → expected_output_sha256 triples for
|
||||
regression coverage. Generated once, pinned.
|
||||
(seed, hard_hash, dim_h) → expected_output_sha256 triples (10
|
||||
entries) for regression coverage. Regenerated by
|
||||
`scripts/generate_phi_prg_kat.py` (run it after any algorithm
|
||||
change, then bump `PHI_PRG_VERSION` so the fixture's `version`
|
||||
field changes too). `tests/test_anchor_prg.py::test_phi_prg_known_answer_tests`
|
||||
pins these values and asserts the version matches the module.
|
||||
|
||||
### 3.4 Spec amendment
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Ticket #000036 — T3 per-window covert-channel budget bound
|
||||
|
||||
**Status:** in progress · Phase 1 (formal derivation + calculator) landed 2026-05-10; **dav1d review returned 2026-05-11** (`RESPONSE_1` + `RESPONSE_2`) → **Tier-1 + Tier-2 both applied 2026-05-11**. Tier-1: recommendation wording → "CANNOT CERTIFY", structured `certification_status` / `b1_model` / `b1_selected` / `model_assumptions` output fields, bool/NaN/inf validation hardening, `g=0` accepted, hard-coded test cwd removed. **Tier-2 = dav1d Option B applied *in v1* (per fox — no v2 fork)**: default `b1_model` is now `max_envelope` = `max(fraction_channels, aggregate_bias)` (genuinely upper-bounding across both interpretations of `g`); `effective_control_v1` / `fraction_channels` / `aggregate_bias` reachable via `--b1-model`; every output reports all three B1 variants + both SNR readings; `CALCULATOR_VERSION` unchanged (`t3-bound-v1-bottou-refinement` — the descriptor names the unchanged B3 term, and `b1_model` echoed in `inputs` disambiguates KAT replays). **KAT fixture regenerated 2026-05-11** (12 entries; `test_t3_bound_known_answer_tests` now runs, not skips). Baseline I_window: 625.87 (effective_control_v1) → **6183.02 (max_envelope default)**. Test suite 53 → 83. **Both prior closure blockers cleared**; remaining = fox's final close-or-iterate call (optionally a dav1d re-review of the envelope formula). Empirical constant-tightening tracked separately under #000043. R2's architectural integrations (Merkle audit-event commitment, SQD canonicalization, CTI clause-lattice, 5F trigger, ForkScore security-risk) out-of-scope here — separate tickets if wanted.
|
||||
**Status:** **closed · 2026-05-11.** Phase 1 (formal derivation + calculator) landed 2026-05-10; dav1d review (`RESPONSE_1` + `RESPONSE_2`) returned 2026-05-11 → Tier-1 polish (recommendation wording → "CANNOT CERTIFY"; structured `certification_status` / `b1_model` / `b1_selected` / `model_assumptions` output fields; bool/NaN/inf validation hardening; `g=0` accepted; hard-coded test cwd removed) + Tier-2 (dav1d Option B applied *in v1* per fox — no v2 fork: default `b1_model = max_envelope = max(fraction_channels, aggregate_bias)`, genuinely upper-bounding across both interpretations of `g`; `effective_control_v1` / `fraction_channels` / `aggregate_bias` reachable via `--b1-model`; every output reports all three B1 variants + both SNR readings; `CALCULATOR_VERSION` stays `t3-bound-v1-bottou-refinement`, `b1_model` echoed in `inputs` disambiguates KAT replays) + KAT-regen tooling (`scripts/generate_t3_bound_kat.py`, 12-entry fixture, `test_t3_bound_known_answer_tests` runs not skips) all landed 2026-05-11. Baseline I_window: 625.87 (effective_control_v1) → 6183.02 (max_envelope default), `NOT_CERTIFIED_BY_BOUND` at W=10000. Test suite 53 → 83. **Both dav1d closure blockers cleared** (B1 worst-case model; active KAT fixture). All §5 acceptance criteria met. **Continuation:** empirical C_B1/C_B2/C_B3 tightening tracked under **#000043** (parks on v7 deployment data); R2's architectural integrations (Merkle audit-event commitment, SQD canonicalization, CTI clause-lattice, 5F trigger, ForkScore security-risk) are separate tickets if wanted; landing the bound's framing into a v7 plastic-training spec parks on that spec gaining a deployment target. Reviewer artifacts: `~/Downloads/RESPONSE_1_-_ticket-000036-...txt`, `RESPONSE_2_-_...txt`.
|
||||
**Opened:** 2026-05-09
|
||||
**Scope:** Derive an explicit closed-form upper bound on the covert-
|
||||
channel capacity under threat model T3 (hyperparameter adversary),
|
||||
|
|
|
|||
115
scripts/generate_phi_prg_kat.py
Normal file
115
scripts/generate_phi_prg_kat.py
Normal file
|
|
@ -0,0 +1,115 @@
|
|||
#!/usr/bin/env python3
|
||||
"""Regenerate the φ_PRG anchor-map known-answer-test fixture.
|
||||
|
||||
Writes ``bench/fixtures/phi-prg/known-answer-tests.jsonl`` from the
|
||||
fixed (seed, hard_hash, dim_h) list below. Each entry records the
|
||||
SHA-256 of the raw HMAC-SHA-512 expansion output (before float
|
||||
conversion) — the durable contract; the float layout can change
|
||||
without invalidating the fixture (the byte stream doesn't).
|
||||
|
||||
Run this whenever the φ_PRG algorithm changes — and then bump
|
||||
``PHI_PRG_VERSION`` in ``arborist/substrate/anchor_prg.py`` so the
|
||||
fixture's ``version`` field changes too. The KAT regression test
|
||||
(``tests/test_anchor_prg.py::test_phi_prg_known_answer_tests``)
|
||||
pins these values and asserts the version matches the module.
|
||||
|
||||
Usage::
|
||||
|
||||
python -m scripts.generate_phi_prg_kat # from repo root
|
||||
# or: python scripts/generate_phi_prg_kat.py
|
||||
|
||||
Config list (10 entries): the placeholder seed against zero / all-
|
||||
ones hashes at several dim_h; a random (seed, hash) pair with two
|
||||
one-bit-flip variants (avalanche cross-check); block-boundary cases
|
||||
(dim_h=16 = exactly one HMAC block; dim_h=17 = two blocks with
|
||||
truncation); a 4096-element counter-rollover stress sample. Note:
|
||||
at counter=0 the bytes are identical regardless of endianness, so
|
||||
the single-block (dim_h ≤ 16) entries are endianness-invariant; the
|
||||
multi-block entries pin the little-endian counter encoding.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import pathlib
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1]))
|
||||
|
||||
from arborist.substrate.anchor_prg import _expand, PHI_PRG_VERSION # noqa: E402
|
||||
|
||||
_FIXTURE = (
|
||||
pathlib.Path(__file__).resolve().parents[1]
|
||||
/ "bench" / "fixtures" / "phi-prg" / "known-answer-tests.jsonl"
|
||||
)
|
||||
|
||||
# (label, seed_hex, hard_hash_hex, dim_h)
|
||||
_ENTRIES: list[tuple[str, str, str, int]] = [
|
||||
("placeholder-seed/zero-hash/dim_h=1",
|
||||
"ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3",
|
||||
"0000000000000000000000000000000000000000000000000000000000000000", 1),
|
||||
("placeholder-seed/zero-hash/dim_h=8",
|
||||
"ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3",
|
||||
"0000000000000000000000000000000000000000000000000000000000000000", 8),
|
||||
("placeholder-seed/zero-hash/dim_h=32",
|
||||
"ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3",
|
||||
"0000000000000000000000000000000000000000000000000000000000000000", 32),
|
||||
("placeholder-seed/all-ones-hash/dim_h=16",
|
||||
"ef532720a49159beb6816d98e13a162bac63c531b631bd1adb0fcca96b467ff3",
|
||||
"ffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffff", 16),
|
||||
("seed=A/hash=B/dim_h=64",
|
||||
"14ab2dab0d3cddeaa58ec70632d3ff4f5de2c514004a92144e260dfe384d912e",
|
||||
"a23cb10b94660f062b467f313a9dc9d84f2dc2748c3627c661082dda7f55e3bb", 64),
|
||||
("seed=A/hash=B'/dim_h=64 (one-bit-flip from prior)",
|
||||
"14ab2dab0d3cddeaa58ec70632d3ff4f5de2c514004a92144e260dfe384d912e",
|
||||
"223cb10b94660f062b467f313a9dc9d84f2dc2748c3627c661082dda7f55e3bb", 64),
|
||||
("seed=A'/hash=B/dim_h=64 (one-bit-flip seed)",
|
||||
"94ab2dab0d3cddeaa58ec70632d3ff4f5de2c514004a92144e260dfe384d912e",
|
||||
"a23cb10b94660f062b467f313a9dc9d84f2dc2748c3627c661082dda7f55e3bb", 64),
|
||||
("block-boundary/dim_h=16",
|
||||
"cfd60c2bda64ebcefbb23a5b28d98269c9c4f8b8ac77f6f9ca7a0f4865b10f58",
|
||||
"724cd966a7bfe78ba802877510ffb90c67f385a1d3135e4e1b8a1b38f744c6da", 16),
|
||||
("block-boundary/dim_h=17",
|
||||
"cfd60c2bda64ebcefbb23a5b28d98269c9c4f8b8ac77f6f9ca7a0f4865b10f58",
|
||||
"724cd966a7bfe78ba802877510ffb90c67f385a1d3135e4e1b8a1b38f744c6da", 17),
|
||||
("stress/dim_h=4096",
|
||||
"0ddd62c311f88ebe2d4f6cd5d9d1374474dfd645e012043648dd966a71785c95",
|
||||
"e605ede3d9d0d13c6d7d32c5c424b998677eef0689a0d9f0fa4ebd1bb4307cb9", 4096),
|
||||
]
|
||||
|
||||
|
||||
def build_lines() -> list[str]:
|
||||
lines = [
|
||||
f"# arborist v7 phi_prg known-answer tests — version {PHI_PRG_VERSION}",
|
||||
"# Regenerated by scripts/generate_phi_prg_kat.py. Records SHA-256 of",
|
||||
"# the raw HMAC-SHA-512 (little-endian counter-mode) expansion output,",
|
||||
"# before float conversion. Algorithm change MUST bump PHI_PRG_VERSION",
|
||||
"# and re-run this script; old runs replay against the old fixture.",
|
||||
]
|
||||
for label, seed_hex, hh_hex, dim_h in _ENTRIES:
|
||||
seed = bytes.fromhex(seed_hex)
|
||||
hh = bytes.fromhex(hh_hex)
|
||||
raw = _expand(seed, hh, dim_h * 4)
|
||||
lines.append(json.dumps({
|
||||
"label": label,
|
||||
"version": PHI_PRG_VERSION,
|
||||
"seed_hex": seed_hex,
|
||||
"hard_hash_hex": hh_hex,
|
||||
"dim_h": dim_h,
|
||||
"output_sha256": hashlib.sha256(raw).hexdigest(),
|
||||
"output_bytes": dim_h * 4,
|
||||
}, ensure_ascii=False))
|
||||
return lines
|
||||
|
||||
|
||||
def main() -> int:
|
||||
lines = build_lines()
|
||||
_FIXTURE.parent.mkdir(parents=True, exist_ok=True)
|
||||
_FIXTURE.write_text("\n".join(lines) + "\n", encoding="utf-8")
|
||||
print(f"wrote {len(_ENTRIES)} KAT entries to {_FIXTURE} (version {PHI_PRG_VERSION})")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
145
scripts/generate_t3_bound_kat.py
Normal file
145
scripts/generate_t3_bound_kat.py
Normal file
|
|
@ -0,0 +1,145 @@
|
|||
#!/usr/bin/env python3
|
||||
"""Regenerate the T3-bound calculator known-answer-test fixture.
|
||||
|
||||
Writes ``bench/fixtures/t3-bound/known-answer-tests.jsonl`` from the
|
||||
fixed config list below by running ``t3_bound_bits`` on each and
|
||||
recording the full output. Run this whenever the calculator's
|
||||
algorithm changes — and then bump ``CALCULATOR_VERSION`` in
|
||||
``bench/scripts/t3_bound_calculator.py`` so the fixture's
|
||||
``calculator_version`` field changes too. The KAT regression test
|
||||
(``tests/test_t3_bound_calculator.py::test_t3_bound_known_answer_tests``)
|
||||
pins these values.
|
||||
|
||||
Usage::
|
||||
|
||||
python -m scripts.generate_t3_bound_kat # from repo root
|
||||
# or: python scripts/generate_t3_bound_kat.py
|
||||
|
||||
Config list rationale (12 entries):
|
||||
|
||||
- ``small-deployment-§7.1`` / ``medium-deployment-§7.2`` /
|
||||
``hardened-deployment-§7.3`` — the worked examples in
|
||||
``docs/soft-hash-channel-t3-bound.md`` §7, under the default
|
||||
``b1_model=max_envelope``.
|
||||
- ``extreme-low-g`` / ``tight-window-W=100`` — corner regimes.
|
||||
- ``tightened-c-b1`` / ``all-constants-tight`` — non-default
|
||||
C_B* overrides (replay-completeness for the constants path).
|
||||
- ``b3-floor-regime`` — exercises the B3 floor-at-zero branch.
|
||||
- ``gradient-fraction-zero`` — the g=0 component-isolation case
|
||||
(B1=0; B2+B3 still fire).
|
||||
- ``b1-effective-control-v1-mode`` / ``b1-fraction-channels-mode``
|
||||
/ ``b1-aggregate-bias-mode`` — explicit ``b1_model`` pins so the
|
||||
non-default models are regression-guarded.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import pathlib
|
||||
import sys
|
||||
|
||||
# Allow ``python scripts/generate_t3_bound_kat.py`` from repo root.
|
||||
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parents[1]))
|
||||
|
||||
from bench.scripts.t3_bound_calculator import ( # noqa: E402
|
||||
CALCULATOR_VERSION,
|
||||
t3_bound_bits,
|
||||
)
|
||||
|
||||
_FIXTURE = (
|
||||
pathlib.Path(__file__).resolve().parents[1]
|
||||
/ "bench" / "fixtures" / "t3-bound" / "known-answer-tests.jsonl"
|
||||
)
|
||||
|
||||
# (label, inputs-dict). inputs may include c_b1/c_b2/c_b3/b1_model.
|
||||
_CONFIGS: list[tuple[str, dict]] = [
|
||||
("small-deployment-§7.1", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024)),
|
||||
("medium-deployment-§7.2", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=1000, lr_grid_size=16, window_length=100000,
|
||||
batches_per_epoch=8192, steps_per_epoch=8192)),
|
||||
("hardened-deployment-§7.3", dict(
|
||||
gradient_fraction=0.01, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=4, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024)),
|
||||
("extreme-low-g", dict(
|
||||
gradient_fraction=0.001, gradient_norm_max=1.0, gradient_noise_stddev=0.5,
|
||||
lr_decision_interval=500, lr_grid_size=2, window_length=5000,
|
||||
batches_per_epoch=256, steps_per_epoch=256)),
|
||||
("tight-window-W=100", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=2.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=50, lr_grid_size=4, window_length=100,
|
||||
batches_per_epoch=64, steps_per_epoch=64)),
|
||||
("tightened-c-b1", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024, c_b1=0.5)),
|
||||
("all-constants-tight", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024, c_b1=0.1, c_b2=0.1, c_b3=0.1)),
|
||||
("b3-floor-regime", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=100.0, gradient_noise_stddev=0.001,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=4, steps_per_epoch=4)),
|
||||
("gradient-fraction-zero", dict(
|
||||
gradient_fraction=0.0, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024)),
|
||||
("b1-effective-control-v1-mode", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024, b1_model="effective_control_v1")),
|
||||
("b1-fraction-channels-mode", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024, b1_model="fraction_channels")),
|
||||
("b1-aggregate-bias-mode", dict(
|
||||
gradient_fraction=0.05, gradient_norm_max=1.0, gradient_noise_stddev=0.1,
|
||||
lr_decision_interval=100, lr_grid_size=8, window_length=10000,
|
||||
batches_per_epoch=1024, steps_per_epoch=1024, b1_model="aggregate_bias")),
|
||||
]
|
||||
|
||||
|
||||
def build_lines() -> list[str]:
|
||||
lines = [
|
||||
f"# T3 bound calculator known-answer tests — version {CALCULATOR_VERSION}",
|
||||
"# Regenerated by scripts/generate_t3_bound_kat.py. Algorithm change",
|
||||
"# MUST bump CALCULATOR_VERSION and re-run this script; old runs",
|
||||
"# replay against the old fixture (do not delete history).",
|
||||
]
|
||||
for label, inp in _CONFIGS:
|
||||
r = t3_bound_bits(**inp)
|
||||
lines.append(json.dumps({
|
||||
"label": label,
|
||||
"calculator_version": r["calculator_version"],
|
||||
"b1_model": r["b1_model"],
|
||||
"inputs": r["inputs"],
|
||||
"expected_total": r["I_window_bits_upper_bound"],
|
||||
"expected_b1": r["B1_contribution"],
|
||||
"expected_b1_selected": r["b1_selected"],
|
||||
"expected_b1_fraction_channels": r["B1_fraction_channels"],
|
||||
"expected_b1_aggregate_bias": r["B1_aggregate_bias"],
|
||||
"expected_b1_effective_control_v1": r["B1_effective_control_v1"],
|
||||
"expected_b2": r["B2_contribution"],
|
||||
"expected_b3": r["B3_contribution"],
|
||||
"expected_snr_grad": r["snr_grad"],
|
||||
"expected_snr_per_channel": r["snr_per_channel"],
|
||||
"expected_certification_status": r["certification_status"],
|
||||
}, ensure_ascii=False))
|
||||
return lines
|
||||
|
||||
|
||||
def main() -> int:
|
||||
lines = build_lines()
|
||||
_FIXTURE.parent.mkdir(parents=True, exist_ok=True)
|
||||
_FIXTURE.write_text("\n".join(lines) + "\n", encoding="utf-8")
|
||||
print(f"wrote {len(_CONFIGS)} KAT entries to {_FIXTURE} (version {CALCULATOR_VERSION})")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
|
@ -572,7 +572,7 @@ KAT_FIXTURE = (
|
|||
|
||||
@pytest.mark.skipif(
|
||||
not KAT_FIXTURE.exists(),
|
||||
reason="KAT fixture not yet generated",
|
||||
reason="KAT fixture not yet generated; run scripts/generate_t3_bound_kat.py",
|
||||
)
|
||||
def test_t3_bound_known_answer_tests():
|
||||
"""Replay the pinned t3-bound/known-answer-tests.jsonl fixture;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue