feat(learning-harness): declared twins and a fixture-difficulty check

The five byte-identical vibe-py twins now say so in the catalog instead of
only hashing to it, and a declared limit that names one of the unscorable
vocabulary's own reasons keeps that spelling, so `identical_twin` stays one
fact. Leave-one-out over vibe-py consequently runs on 30 rows, not 35.

The difficulty check measures three axes the corpus varies on: binding hops
from the identity source to the constrained use, registration distance, and
guard distance. Measured first, and it failed: the shared obligations
fixture reached (1, 0, 2) where the vibe-py absence rows reach (5, 2, 2).
Every fixture handler carried its own route decorator, so nothing in the
suite exercised a handler registered from another document and no binding
chain was longer than one hop -- the checker was passing on a simpler world
than the one it meets. `from_spec` closes that with the connexion shape
those rows really have. The verdict is committed beside the numbers.

Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG

benchmarks/measurements/2026-09-06-fixture-difficulty.json

@@ -0,0 +1,88 @@
+{
+  "axes": [
+    "binding_hops",
+    "registration_distance",
+    "guard_distance"
+  ],
+  "command": "uv run pytest tests/test_fixture_difficulty.py",
+  "corpus": [
+    {
+      "binding_hops": 5,
+      "function": "get_by_title",
+      "guard_distance": 1,
+      "registration_distance": 2
+    },
+    {
+      "binding_hops": 2,
+      "function": "update_password",
+      "guard_distance": 1,
+      "registration_distance": 2
+    },
+    {
+      "binding_hops": 0,
+      "function": "get",
+      "guard_distance": 2,
+      "registration_distance": 0
+    },
+    {
+      "binding_hops": 0,
+      "function": "delete",
+      "guard_distance": 2,
+      "registration_distance": 0
+    }
+  ],
+  "corpus_reach": [
+    5,
+    2,
+    2
+  ],
+  "corpus_rows": [
+    "vampi-books-get-by-title",
+    "vampi-users-update-password",
+    "threatbyte-api-v1-get",
+    "threatbyte-api-v1-delete"
+  ],
+  "fixture": [
+    {
+      "binding_hops": 0,
+      "function": "guarded",
+      "guard_distance": 0,
+      "registration_distance": 0
+    },
+    {
+      "binding_hops": 1,
+      "function": "constrained",
+      "guard_distance": 0,
+      "registration_distance": 0
+    },
+    {
+      "binding_hops": 1,
+      "function": "constrained_too",
+      "guard_distance": 1,
+      "registration_distance": 0
+    },
+    {
+      "binding_hops": 0,
+      "function": "leaky",
+      "guard_distance": 2,
+      "registration_distance": 0
+    },
+    {
+      "binding_hops": 5,
+      "function": "from_spec",
+      "guard_distance": 1,
+      "registration_distance": 2
+    }
+  ],
+  "fixture_reach": [
+    5,
+    2,
+    2
+  ],
+  "fixture_source": "tests/test_obligation_operations.py::APP",
+  "generated": "2026-09-06",
+  "history": "First measured with the fixture reaching (1, 0, 2) against a corpus reaching (5, 2, 2): every shared obligations handler carried its route decorator, so nothing in the suite exercised a handler registered from another document, and no chain was longer than one binding. `from_spec` was added to the fixture to close that, and it is the connexion shape the vibe-py rows really have.",
+  "note": "learning-harness Req 10.4. Higher is harder on every axis. `binding_hops` counts the assignments between the identity source and the constrained use; `registration_distance` is 0 for a route decorator on the handler, 1 for a statement elsewhere in the same file, 2 for another document entirely; `guard_distance` is 0 for a decorator guard, 1 for a call in the body, 2 for no visible guard. The comparison is per axis over the whole set: a suite covers a bug shape with several handlers between them, but its hardest case on an axis must not fall short of the corpus rows its tests claim to cover.",
+  "strictly_easier": false,
+  "verdict": "fixture_matches_corpus"
+}

benchmarks/pairs/vibe-py/catalog.toml

@@ -2324,6 +2324,7 @@ fix_policy = "silent"
 provenance = "human"
 split = "holdout"
 review_tier = "seeded"
+known_limit = "identical_twin"
 
 [[pair.expected]]
 cwe = "CWE-89"
@@ -3207,6 +3208,7 @@ fix_policy = "silent"
 provenance = "human"
 split = "train"
 review_tier = "seeded"
+known_limit = "identical_twin"
 
 [[pair.expected]]
 cwe = "CWE-1336"
@@ -3236,6 +3238,7 @@ fix_policy = "silent"
 provenance = "human"
 split = "holdout"
 review_tier = "seeded"
+known_limit = "identical_twin"
 
 [[pair.expected]]
 cwe = "CWE-79"
@@ -3354,6 +3357,7 @@ fix_policy = "silent"
 provenance = "human"
 split = "holdout"
 review_tier = "seeded"
+known_limit = "identical_twin"
 
 [[pair.context]]
 relpath = "openapi_specs/openapi3.yml"
@@ -3656,6 +3660,7 @@ fix_policy = "silent"
 provenance = "human"
 split = "train"
 review_tier = "seeded"
+known_limit = "identical_twin"
 
 [[pair.expected]]
 cwe = "CWE-502"

benchmarks/pairs/vibe-py/recipes.toml

@@ -2290,6 +2290,7 @@ trap_id = "dsvw-fp-001"
 acceptable_cwes = ["CWE-89", "CWE-564", "CWE-943"]
 evidence = "SQL injection via id parameter directly concatenated into SELECT query without sanitization"
 commit_url = "https://github.com/stamparm/DSVW/blob/7d40f4b7939c901610ed9b85724552d60e7d63fa/dsvw.py#L30"
+known_limit = "identical_twin"
 split = "holdout"
 
 [[recipe]]
@@ -3167,6 +3168,7 @@ trap_id = "python-insecure-app-fp-001"
 acceptable_cwes = ["CWE-1336", "CWE-94", "CWE-95"]
 evidence = "Server-Side Template Injection via Jinja2. User-controlled 'name' query parameter is interpolated into an f-string on line 38 to build 'content', which is then passed to Template(content).render() on line 41. An attacker can inject Jinja2 t"
 commit_url = "https://github.com/kolega-ai/realvuln-python-insecure-app/blob/80b894a2f754590747a31c92b2088be086421953/app/main.py#L41"
+known_limit = "identical_twin"
 split = "train"
 
 [[recipe]]
@@ -3198,6 +3200,7 @@ trap_id = "python-ssti-fp-001"
 acceptable_cwes = ["CWE-79", "CWE-80"]
 evidence = "The Jinja2 Environment is created with default settings (autoescape=False). User input from the 'username' query parameter is concatenated into the template string and the rendered output is returned as HTMLResponse. An attacker can inject "
 commit_url = "https://github.com/TheWation/PythonSSTI/blob/76339c27d5a870c0a81bad6aee5f9bd516592145/main.py#L14"
+known_limit = "identical_twin"
 split = "holdout"
 
 [[recipe]]
@@ -3328,6 +3331,7 @@ evidence = "Broken Object Level Authorization (BOLA). When vuln=1, get_by_title
 commit_url = "https://github.com/erev0s/VAmPI/blob/1713b54b601ad29582581eeda4b31fceb1319874/api_views/books.py#L51"
 family = "access_control"
 context = ["openapi_specs/openapi3.yml"]
+known_limit = "identical_twin"
 split = "holdout"
 
 [[recipe]]
@@ -3672,6 +3676,7 @@ trap_id = "vulnpy-fp-011"
 acceptable_cwes = ["CWE-502", "CWE-94"]
 evidence = "User input encoded to bytes and passed to pickle.load(), which can execute arbitrary code via crafted pickle payloads"
 commit_url = "https://github.com/Contrast-Security-OSS/vulnpy/blob/d1d0f64c06f038fe59a049e0e6001bfaf9839697/src/vulnpy/trigger/deserialization.py#L8"
+known_limit = "identical_twin"
 split = "train"
 
 [[recipe]]