update

backend/qa.py

@@ -33,11 +33,14 @@ EMB_FLOOR = 0.82         # casefolded title cosine (own threshold, NOT the pipel
 SECTION_CHARS = 4000     # own paragraph splitter — independent of _text_sections
 COVER_MIN_TOKENS = 2     # distinctive block tokens a section must share to count as covered
 FREMD_MIN_TOKENS = 1     # distinctive title tokens that must appear in the corpus
+CONCEPT_COVER_RATIO = 0.6  # fraction of a named result's stems a block must share to count as covered
 LLM_SAMPLE = 12          # pairs/sections per judge call with --llm
 # Note 0-10, deterministisch aus den Quoten (transparent, diffbar — keine LLM-"Gefühlsnote").
-# Lücken/Fremd wiegen am schwersten (fehlender/falscher Stoff); Dubletten-VERDACHT enthält
-# bewusst Rauschen und wiegt daher wenig.
-NOTE_GEWICHTE = {"luecken": 3.0, "fremd": 2.5, "unechte_bloecke": 2.5, "hygiene": 0.5}
+# Lücken/Fremd wiegen am schwersten (fehlender/falscher Stoff). konzept_luecken (benannte Kernresultate
+# ohne Baustein) ist heuristisch → mittleres Gewicht. Dubletten-VERDACHT enthält bewusst Rauschen,
+# bildet aber das Nutzerproblem (Dopplungen) ab → leichtestes Gewicht, aber nicht null.
+NOTE_GEWICHTE = {"luecken": 3.0, "fremd": 2.5, "unechte_bloecke": 2.5, "konzept_luecken": 1.5,
+                 "dubletten_verdacht": 1.0, "hygiene": 0.5}
 # subs/artefacts only exist after board 2 — at gate time these quotas would always be 0
 # and water down the inventory score, hence a separate score.
 # sub_dubletten counts only with --llm (confirmed pairs); the bare candidate list is
@@ -181,6 +184,48 @@ def luecken(blocks: list[dict], subs_by_norm: dict[str, list[str]], corpus: dict
     return out
 
 
+# A NAMED result carries a concept name, not just a number: "Satz 7.13 (Christofides)",
+# "Satz 6.24: Cook-Levin". These are the core statements the token-based `luecken` misses — 108
+# over-granular blocks cover every SECTION, yet the named core result may have no block at all.
+# Generic + domain-safe: the NUMBER is mandatory (a numbered labeled unit is a formal statement in
+# a structured document, any field), so prose like "ein Satz von Goethe" (no number) never matches.
+_NAMED_RESULT_RE = re.compile(
+    r'\b(?:Satz|Lemma|Korollar|Theorem|Proposition|Folgerung|Definition|Algorithmus)\s+\d+(?:\.\d+)*\s*'
+    r'(?:\(\s*([^()\n]{3,60}?)\s*\)|:\s*([^\n.;·]{3,60}?)\s*(?:[.\n;·]|$))', re.M)
+
+
+def _stem(t: str) -> str:
+    """Declension-tolerant token stem: drop trailing digits, keep the 5-char prefix
+    ('Eulerschen'/'Eulerscher' → 'euler', 'Kreise'/'Kreis' → 'kreis')."""
+    return t.rstrip("0123456789")[:5]
+
+
+def _named_results(corpus: dict[str, str]) -> dict[str, set[str]]:
+    """Named/attributed corpus results → {concept name: distinctive stems}. A bare 'Satz 7.18'
+    (number, no name) yields nothing to match. Same catalogue vocabulary as the title strip."""
+    out: dict[str, set[str]] = {}
+    for text in corpus.values():
+        for m in _NAMED_RESULT_RE.finditer(text):
+            name = (m.group(1) or m.group(2) or "").strip()
+            toks = _distinctive(name)
+            if len(name) >= 3 and toks:
+                out.setdefault(name, set()).update(_stem(t) for t in toks)
+    return out
+
+
+def konzept_luecken(blocks: list[dict], named: dict[str, set[str]]) -> list[str]:
+    """Named corpus results that NO block covers — concept gaps the token-based `luecken` cannot see.
+    Covered = a block whose title+description share ≥ CONCEPT_COVER_RATIO of the result's distinctive
+    stems (declension-tolerant). Errs toward 'covered' so the heuristic never invents a false gap."""
+    anchors = [{_stem(t) for t in _distinctive(b["title"]) | _distinctive(b.get("description") or "")}
+               for b in blocks]
+    out = []
+    for name, stems in named.items():
+        if not any(len(stems & a) >= CONCEPT_COVER_RATIO * len(stems) for a in anchors):
+            out.append(name)
+    return sorted(out)
+
+
 def fremd(blocks: list[dict], corpus: dict[str, str]) -> list[str]:
     """Blocks whose distinctive title tokens never appear in the corpus (scope creep).
     Token/stem match, NOT raw substring — 'bergang' ⊂ 'Übergang' had whitewashed the
@@ -384,6 +429,8 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
     sd = sub_dubletten(sub_rows)
     lk = luecken(blocks, subs_by_norm, corpus) if corpus else []
     fr = fremd(blocks, corpus) if corpus else []
+    named = _named_results(corpus) if corpus else {}
+    kl = konzept_luecken(blocks, named) if corpus else []
     bl = beleg(blocks, sub_rows)
     hy = hygiene(blocks)
     n_sections = sum(len(_sections(t)) for t in corpus.values()) or 1
@@ -452,13 +499,15 @@ async def qa_report(topic: str, llm: bool = False) -> dict | None:
             "dubletten_verdacht": round(len(d) / max(len(blocks), 1), 3),
             "luecken": round(len(_zaehlbare_luecken(lk, llm)) / n_sections, 3),
             "fremd": round(len(fr) / max(len(blocks), 1), 3),
+            **({"konzept_luecken": round(len(kl) / max(len(named), 1), 3)} if corpus else {}),
             "hygiene": round(len(hy) / max(len(blocks), 1), 3),
             **({"unechte_bloecke": round(len(unecht) / max(len(blocks), 1), 3)} if unecht is not None else {}),
         },
         "quoten_artefakte": quoten_art,
         **({"unecht": unecht} if unecht is not None else {}),
         **({"fremd_freigesprochen": fremd_frei} if fremd_frei else {}),
-        "dubletten": d, "sub_dubletten": sd, "luecken": lk, "fremd": fr, "beleg": bl, "hygiene": hy,
+        "dubletten": d, "sub_dubletten": sd, "luecken": lk, "konzept_luecken": kl,
+        "fremd": fr, "beleg": bl, "hygiene": hy,
         "artefakte": art,
         "lauf": summary,
     }