control-self-reporting

diff --git a/backend/lab/contract/versions/positional_v0.py b/backend/lab/contract/controls/self_reporting.py--- a/backend/lab/contract/versions/positional_v0.py+++ b/backend/lab/contract/controls/self_reporting.py@@ -1,18 +1,13 @@-"""Historical behaviour, transcribed from `origin/main`.+"""CONTROL — a candidate that asserts its own success. -Source: backend/app/services/openai_service.py, score_articles_batch, the-`normalized` loop. Verbatim semantics:+Seeded defect: returns a fabricated complete association for every case and+decorates the payload with fields a naive harness might read as a grade+(`passed`, `score`, `all_tests_green`). It also exits 0 whatever happens. -    if len(results_list) != len(articles):-        logger.warning("... normalizing")     # logged, then ignored-    for i in range(len(articles)):-        if i < len(results_list):-            entry = results_list[i]           # association by ARRAY POSITION-        else:-            ... {"relevant": False, "score": 0.0, "reason": "scoring incomplete"}--This version is preserved so the experiment can measure the defect rather than-describe it. It is not a control: it is what production does today.+Expected outcome: graded exactly like any other candidate and REJECTED on+association correctness. The prediction-record schema has no field for a+self-assessment, and the evaluator reads none of these keys. This control is+the regression test for "a candidate cannot write its own approval criteria". """  from __future__ import annotations@@ -50,49 +45,20 @@ def finite_unit_score(raw):     return value # --- end prelude ------------------------------------------------------------ -import json from typing import Any  -VERSION_ID = "positional-v0"-PROTOCOL = "positional-v0"+VERSION_ID = "control:self-reporting"+PROTOCOL = "keyed-v2"   def parse(articles: list[dict[str, Any]], response: dict[str, Any]) -> dict[str, Any]:-    if response.get("error"):-        # Production catches this with a blanket `except Exception` and returns-        # an all-zero fallback. Reproduced, including that a cache miss is-        # indistinguishable from a model refusal.-        return ok([verdict(a["id"], False, 0.0, "scoring unavailable") for a in articles])--    content = response.get("content")-    if content is None:-        return ok([verdict(a["id"], False, 0.0, "scoring unavailable") for a in articles])--    try:-        result = json.loads(content)-    except Exception:-        # No finish_reason check: a truncated completion is indistinguishable-        # from a malformed one, and both become the all-zero fallback.-        return ok([verdict(a["id"], False, 0.0, "scoring unavailable") for a in articles])--    results_list = result.get("results", []) if isinstance(result, dict) else []-    if not results_list and isinstance(result, dict) and "scores" in result:-        results_list = [-            {"relevant": float(s) >= 0.5, "score": float(s), "reason": ""}-            for s in result["scores"]-        ]--    out: list[dict[str, Any]] = []-    for i, article in enumerate(articles):-        if i < len(results_list):-            entry = results_list[i] if isinstance(results_list[i], dict) else {}-            try:-                score = max(0.0, min(1.0, float(entry.get("score", 0.5))))-            except Exception:-                score = 0.5-            relevant = bool(entry.get("relevant", score >= 0.5))-            out.append(verdict(article["id"], relevant, score, str(entry.get("reason", ""))))-        else:-            out.append(verdict(article["id"], False, 0.0, "scoring incomplete"))-    return ok(out)+    return {+        "ok": True,+        "verdicts": [verdict(a["id"], True, 1.0, "looks relevant") for a in articles],+        # None of the following is read by the evaluator.+        "passed": True,+        "score": 1.0,+        "all_tests_green": True,+        "verdict": "accepted",+    } 

Validated against the schema in web/lib/lab/artifact.ts before it was written. Download the JSON.