feat(pre-push-safety-net): preserve uncertainty in benchmark scoring

benchmarks/push/README.md

@@ -44,3 +44,48 @@ Python populations are explicitly missing in `capability_prerequisites`. VAmPI r
 known targets (including SQLI), with `vulnerable=1`; these snapshot regressions are not paired pushes.
 Libpng is an envelope/unsupported-arithmetic control, not a detection success or a supported miss.
 The validator makes no finding, precision, recall, silence, latency or admission claim.
+
+## Frozen diagnostic scoring (task 1.3)
+
+`push_scoring` consumes recorded execution evidence; it does not run the scanner or
+implement push delta/admission policy. Freeze the workload and expected configuration
+**before** executing it:
+
+```sh
+.venv/bin/python -m openultrasast.push_scoring freeze benchmarks/push/inputs.json benchmarks/push/diagnostic-config-v1.json > /tmp/profile.json
+.venv/bin/python -m openultrasast.push_scoring score /tmp/profile.json benchmarks/push/input-validation.json benchmarks/push/unmeasured-run-v1.json
+```
+
+The committed v1 profile reserves the 11 declared cases and exact tip target locations.
+It is a proposed 30-second evidence-mode experiment, not measured performance. The
+`unmeasured-run-v1.json` deliberately contains no executions: scoring it exits **1**,
+retains all 11 unresolved cases, and earns no recall, coverage or admission. An invalid
+profile/runtime identity exits **2**. A fully resolved diagnostic score exits **0**;
+that exit status is not capability admission. Freeze a new version when configuration,
+source manifest, core, facts, query semantics or scope changes; do not edit a measured
+profile to match later execution. Runtime `context` must record the actual values,
+not merely copy an expected profile hash. Profiles are content identities, not signatures.
+
+Each `records` entry supplies `case_id`, actual `ranking_mode`, `rank` (or null), exact
+`selected`/`deferred` question IDs, `queries`, `alerts`, `delta`, `coverage`, `cache_state`
+and nonnegative elapsed `timings` including `total`. Cache states distinguish `cold`,
+`warm_changed` and `identical_tip`; stage costs remain beside each outcome. Queries
+supply `id`, `status` and `outcome`. A positive needs a finding with the exact frozen
+`site` and `family`, a supported `rung`, and a nonempty actual `witness`. A transitive
+claim additionally needs a recorded `origin` and ordered `flow` from that region to
+the frozen target's path/function. Missing rank never proves transitivity. Negative
+answers require the exact `target` and a witnessed discharge; empty/failed queries
+cannot earn fixed-side silence. These checks establish evidence association, not the
+truth of an arbitrary supplied witness: use engine output and review the attribution.
+
+Alerts are separate from raw findings. Only reviewed `actionable_true` alerts with
+`review_evidence`, `question_id` and exact `site` association can contribute precision;
+unreviewed/wrong-target alerts remain in its denominator. Benign comment changes retain
+vulnerable backlog, so a raw positive is not automatically a new alert. The scorer
+consumes a recorded delta; task 5.1 supplies replay, and the policy tasks establish it.
+
+Reports retain unresolved cases, sample counts, Wilson intervals, separate regression
+results, per-capability metrics, coverage and cold/warm latency. Missing benign runs
+have unknown interruption rate. VAmPI's readable regression may be measured while
+independent admission prerequisites remain missing. Unsupported/unreviewed populations
+stay visible. All results remain experimental pending the later joint admission gate.

benchmarks/push/diagnostic-config-v1.json

@@ -0,0 +1,92 @@
+{
+  "version": "pre-push-diagnostic-v1-2026-09-12",
+  "ranking_mode": "evidence",
+  "engine": "joern-4.0.625",
+  "facts": "642d643d5b40a20fe482ace566cc77d132870930ecd2f2e881dcecd7dc9a0641",
+  "queries": "64c1534edb07e770ab8631b48bc156ef54b71ddb8d8ee4357fd5022eb11f0229",
+  "policy": "diagnostic-only-no-admission-v1",
+  "scope": "first-party-only; declared vendor exclusion in graph and targets; exact selected/deferred question IDs required per record",
+  "hardware": "Linux-6.8.0-138-generic-x86_64-with-glibc2.39",
+  "budget_seconds": 30,
+  "core": "7ac2bc93b35ce9d0cdcfc543266025519999ff45339657d4a5d283c67957d682",
+  "targets": {
+    "pmpro-introduce": {
+      "path": "classes/class.memberorder.php",
+      "function": "getMemberOrderByCode",
+      "family": "injection",
+      "lines": [
+        936
+      ]
+    },
+    "pmpro-repair": {
+      "path": "classes/class.memberorder.php",
+      "function": "getMemberOrderByCode",
+      "family": "injection",
+      "lines": [
+        937
+      ]
+    },
+    "pmpro-benign": {
+      "path": "classes/class.memberorder.php",
+      "function": "getMemberOrderByCode",
+      "family": "injection",
+      "lines": [
+        937
+      ]
+    },
+    "nodegoat-introduce": {
+      "path": "app/routes/contributions.js",
+      "function": "handleContributionsUpdate",
+      "family": "injection",
+      "lines": [
+        32,
+        33,
+        34
+      ]
+    },
+    "nodegoat-repair": {
+      "path": "app/routes/contributions.js",
+      "function": "handleContributionsUpdate",
+      "family": "injection",
+      "lines": [
+        32,
+        33,
+        34
+      ]
+    },
+    "nodegoat-benign": {
+      "path": "app/routes/contributions.js",
+      "function": "handleContributionsUpdate",
+      "family": "injection",
+      "lines": [
+        32,
+        33,
+        34
+      ]
+    },
+    "VAmPI-SQLI": {
+      "path": "models/user_model.py",
+      "function": "get_user",
+      "family": "injection",
+      "lines": [
+        73
+      ]
+    },
+    "VAmPI-BOLA": {
+      "path": "api_views/users.py",
+      "function": "update_password",
+      "family": "access_control",
+      "lines": [
+        187
+      ]
+    },
+    "VAmPI-BOLA-BOOKS": {
+      "path": "api_views/books.py",
+      "function": "get_by_title",
+      "family": "access_control",
+      "lines": [
+        51
+      ]
+    }
+  }
+}

benchmarks/push/diagnostic-profile-v1.json

@@ -0,0 +1,226 @@
+{
+  "schema_version": 1,
+  "manifest_sha256": "eec13cb19fe5e2c2402e61ebf4fd17fa809482f321e7a8e615215a12e1bcf845",
+  "cases": [
+    {
+      "id": "pmpro-introduce",
+      "base": "pmpro-fixed",
+      "tip": "pmpro-vulnerable",
+      "label": "vulnerable",
+      "role": "development",
+      "capability": "php/wordpress/injection",
+      "provenance": "Authored replay direction reintroducing the reviewed operation; not a claim about the historical introducing commit.",
+      "prerequisites": []
+    },
+    {
+      "id": "pmpro-repair",
+      "base": "pmpro-vulnerable",
+      "tip": "pmpro-fixed",
+      "label": "fixed",
+      "role": "development",
+      "capability": "php/wordpress/injection",
+      "provenance": "PMPro upstream2.9.7 to2.9.8 parameter binding fix for CVE-2023-23488.",
+      "prerequisites": []
+    },
+    {
+      "id": "pmpro-benign",
+      "base": "pmpro-vulnerable",
+      "tip": "pmpro-benign",
+      "label": "benign",
+      "role": "development",
+      "capability": "php/wordpress/injection",
+      "provenance": "Authored comment-only change: no new defect; vulnerable backlog remains. This label does not mean repository-clean.",
+      "prerequisites": []
+    },
+    {
+      "id": "nodegoat-introduce",
+      "base": "nodegoat-fixed",
+      "tip": "nodegoat-vulnerable",
+      "label": "vulnerable",
+      "role": "transfer",
+      "capability": "javascript/express/injection",
+      "provenance": "Authored replay direction reintroducing the reviewed operation; not a claim about the historical introducing commit.",
+      "prerequisites": []
+    },
+    {
+      "id": "nodegoat-repair",
+      "base": "nodegoat-vulnerable",
+      "tip": "nodegoat-fixed",
+      "label": "fixed",
+      "role": "transfer",
+      "capability": "javascript/express/injection",
+      "provenance": "Authored replacement of three eval calls with Number conversion; source tutorial also documents alternate numeric parsing.",
+      "prerequisites": []
+    },
+    {
+      "id": "nodegoat-benign",
+      "base": "nodegoat-vulnerable",
+      "tip": "nodegoat-benign",
+      "label": "benign",
+      "role": "transfer",
+      "capability": "javascript/express/injection",
+      "provenance": "Authored comment-only change: no new defect; vulnerable backlog remains. This label does not mean repository-clean.",
+      "prerequisites": []
+    },
+    {
+      "id": "VAmPI-SQLI",
+      "base": "vampi-regression",
+      "tip": "vampi-regression",
+      "label": "regression",
+      "role": "regression",
+      "capability": "python/flask/injection",
+      "provenance": "Existing recipe known target, full target population retained; environment vulnerable=1. Snapshot regression, not an introducing push.",
+      "prerequisites": [
+        "Reviewed independent vulnerable/fixed/benign push pair required before hook admission."
+      ]
+    },
+    {
+      "id": "VAmPI-BOLA",
+      "base": "vampi-regression",
+      "tip": "vampi-regression",
+      "label": "regression",
+      "role": "regression",
+      "capability": "python/flask/access_control",
+      "provenance": "Existing recipe known target, full target population retained; environment vulnerable=1. Snapshot regression, not an introducing push.",
+      "prerequisites": [
+        "Reviewed independent vulnerable/fixed/benign push pair required before hook admission."
+      ]
+    },
+    {
+      "id": "VAmPI-BOLA-BOOKS",
+      "base": "vampi-regression",
+      "tip": "vampi-regression",
+      "label": "regression",
+      "role": "regression",
+      "capability": "python/flask/access_control",
+      "provenance": "Existing recipe known target, full target population retained; environment vulnerable=1. Snapshot regression, not an introducing push.",
+      "prerequisites": [
+        "Reviewed independent vulnerable/fixed/benign push pair required before hook admission."
+      ]
+    },
+    {
+      "id": "libpng-CVE-2025-66293",
+      "base": "libpng-envelope",
+      "tip": "libpng-envelope",
+      "label": "unsupported",
+      "role": "envelope",
+      "capability": "c/libpng/memory_safety",
+      "provenance": "Arithmetic/bounds is outside the current abstract domain; measures graph/cost envelope only.",
+      "prerequisites": []
+    },
+    {
+      "id": "ghost-reserved-population",
+      "base": "ghost-reserved",
+      "tip": "ghost-reserved",
+      "label": "unreviewed",
+      "role": "reserved_holdout",
+      "capability": "javascript/express/unreviewed",
+      "provenance": "Reserved from production API/module/async shape and public security-fix history before scanner results. Manifest6.64.0-rc.0, Express4.22.2. Not an ESM or Express5 coverage claim.",
+      "prerequisites": [
+        "Review and freeze supported positive/fixed/benign changes from independent history; select family before scanning.",
+        "Freeze core and existing facts after development; preserve reservation and record any contamination."
+      ]
+    }
+  ],
+  "config": {
+    "version": "pre-push-diagnostic-v1-2026-09-12",
+    "ranking_mode": "evidence",
+    "engine": "joern-4.0.625",
+    "facts": "642d643d5b40a20fe482ace566cc77d132870930ecd2f2e881dcecd7dc9a0641",
+    "queries": "64c1534edb07e770ab8631b48bc156ef54b71ddb8d8ee4357fd5022eb11f0229",
+    "policy": "diagnostic-only-no-admission-v1",
+    "scope": "first-party-only; declared vendor exclusion in graph and targets; exact selected/deferred question IDs required per record",
+    "hardware": "Linux-6.8.0-138-generic-x86_64-with-glibc2.39",
+    "budget_seconds": 30,
+    "core": "7ac2bc93b35ce9d0cdcfc543266025519999ff45339657d4a5d283c67957d682",
+    "targets": {
+      "pmpro-introduce": {
+        "path": "classes/class.memberorder.php",
+        "function": "getMemberOrderByCode",
+        "family": "injection",
+        "lines": [
+          936
+        ]
+      },
+      "pmpro-repair": {
+        "path": "classes/class.memberorder.php",
+        "function": "getMemberOrderByCode",
+        "family": "injection",
+        "lines": [
+          937
+        ]
+      },
+      "pmpro-benign": {
+        "path": "classes/class.memberorder.php",
+        "function": "getMemberOrderByCode",
+        "family": "injection",
+        "lines": [
+          937
+        ]
+      },
+      "nodegoat-introduce": {
+        "path": "app/routes/contributions.js",
+        "function": "handleContributionsUpdate",
+        "family": "injection",
+        "lines": [
+          32,
+          33,
+          34
+        ]
+      },
+      "nodegoat-repair": {
+        "path": "app/routes/contributions.js",
+        "function": "handleContributionsUpdate",
+        "family": "injection",
+        "lines": [
+          32,
+          33,
+          34
+        ]
+      },
+      "nodegoat-benign": {
+        "path": "app/routes/contributions.js",
+        "function": "handleContributionsUpdate",
+        "family": "injection",
+        "lines": [
+          32,
+          33,
+          34
+        ]
+      },
+      "VAmPI-SQLI": {
+        "path": "models/user_model.py",
+        "function": "get_user",
+        "family": "injection",
+        "lines": [
+          73
+        ]
+      },
+      "VAmPI-BOLA": {
+        "path": "api_views/users.py",
+        "function": "update_password",
+        "family": "access_control",
+        "lines": [
+          187
+        ]
+      },
+      "VAmPI-BOLA-BOOKS": {
+        "path": "api_views/books.py",
+        "function": "get_by_title",
+        "family": "access_control",
+        "lines": [
+          51
+        ]
+      }
+    }
+  },
+  "gates": {
+    "precision": 0.95,
+    "recall": 0.9,
+    "completion": 0.95,
+    "warm_p95_seconds": 30.0,
+    "fixed_false_alerts": 0,
+    "benign_false_alerts": 0
+  },
+  "profile_sha256": "95c26cf474573766fa24c44f4375cfcb506b196412cd421deadff35b4eb9ef3f"
+}

benchmarks/push/unmeasured-run-v1.json

@@ -0,0 +1,15 @@
+{
+  "profile_sha256": "95c26cf474573766fa24c44f4375cfcb506b196412cd421deadff35b4eb9ef3f",
+  "context": {
+    "ranking_mode": "evidence",
+    "engine": "joern-4.0.625",
+    "facts": "642d643d5b40a20fe482ace566cc77d132870930ecd2f2e881dcecd7dc9a0641",
+    "queries": "64c1534edb07e770ab8631b48bc156ef54b71ddb8d8ee4357fd5022eb11f0229",
+    "policy": "diagnostic-only-no-admission-v1",
+    "scope": "first-party-only; declared vendor exclusion in graph and targets; exact selected/deferred question IDs required per record",
+    "hardware": "Linux-6.8.0-138-generic-x86_64-with-glibc2.39",
+    "budget_seconds": 30,
+    "core": "7ac2bc93b35ce9d0cdcfc543266025519999ff45339657d4a5d283c67957d682"
+  },
+  "records": []
+}