P4 validated on 2141 vendor GTCs; legacy AutoCall 1.6.2 preset

- vendor comparison (1000 Genomes Omni2.5, AutoCall 1.6.2.2): every
  computed field identical in 2138/2141 samples; the 3 others trace back
  to the single-locus raw-intensity rule (K-009); sex rule 1 matches all
- AutoCall 1.6.2.x leaves GC10/GC50/#calls/#no-calls at 0 in GTC v3:
  new `--preset autocall-1.6.2` (1.1.2 normalization, sex rule 1, GTC v3,
  legacy statistics); the sample summary keeps the real statistics
- NaN sign canonicalised to the x86 pattern (K-014); report P4.md

scripts/validate_p4_large.py

@@ -37,8 +37,8 @@ ALIGN = (
 _W: dict[str, Any] = {}
 
 
-def _init(bpm: str, egt_dir: str, norm: str, sex_version: int) -> None:
-    _W.update(bpm=bpm, egt_dir=egt_dir, norm=norm, sex_version=sex_version, ctx={})
+def _init(bpm: str, egt_dir: str, norm: str, sex_version: int, preset: str) -> None:
+    _W.update(bpm=bpm, egt_dir=egt_dir, norm=norm, sex_version=sex_version, preset=preset, ctx={})
 
 
 def _ctx(cluster_field: str) -> Any:
@@ -69,7 +69,7 @@ def _canon(a: np.ndarray) -> np.ndarray:  # type: ignore[type-arg]
 def check(args: tuple[str, str, str]) -> dict[str, Any]:
     from simurg.formats.gtc import encode_gtc, read_gtc
     from simurg.formats.idat import read_idat
-    from simurg.genotype.sample import GenotypeParams, genotype_sample
+    from simurg.genotype.sample import genotype_sample, params_for_preset
     from simurg.genotype.sex import SexParams
 
     gtc, grn, red = args
@@ -77,8 +77,12 @@ def check(args: tuple[str, str, str]) -> dict[str, Any]:
     try:
         ref = read_gtc(gtc, check_write_complete=False)
         ctx = _ctx(ref.cluster_file)
-        params = GenotypeParams(
-            norm_version=_W["norm"], sex=SexParams(version=_W["sex_version"]), gtc_version=ref.version
+        params = (
+            params_for_preset(_W["preset"], gtc_version=ref.version)
+            if _W["preset"]
+            else params_for_preset(
+                "current", norm_version=_W["norm"], sex=SexParams(version=_W["sex_version"]), gtc_version=ref.version
+            )
         )
         g = genotype_sample(read_idat(grn), read_idat(red), ctx, params)
         res["cluster_file"] = ctx.cluster_file_name
@@ -110,12 +114,13 @@ def check(args: tuple[str, str, str]) -> dict[str, Any]:
             "ploidy",
             "ploidy_type",
             "dx",
-            "slide_identifier",
         ):
             a, b = getattr(g, k), getattr(ref, k)
             same = a == b or (isinstance(a, float) and np.isnan(a) and np.isnan(b))
             if not same:
                 diffs[k] = [repr(a), repr(b)]
+        if ref.version >= 5 and g.slide_identifier != ref.slide_identifier:  # field 1016 exists only in v5
+            diffs["slide_identifier"] = [g.slide_identifier, ref.slide_identifier]
         if "genotype_scores" in diffs:
             d = np.abs(g.genotype_scores.astype(np.float64) - ref.genotype_scores.astype(np.float64))
             res["max_score_abs_diff"] = float(np.nanmax(d))
@@ -155,6 +160,7 @@ def main() -> int:
     ap.add_argument("--out", required=True, type=Path)
     ap.add_argument("--norm-version", default="1.1.2")
     ap.add_argument("--sex-version", type=int, default=1)
+    ap.add_argument("--preset", default="autocall-1.6.2", help="genotype preset; '' = use --norm/--sex-version")
     ap.add_argument("--workers", type=int, default=os.cpu_count() or 1)
     ap.add_argument("--limit", type=int, default=0)
     a = ap.parse_args()
@@ -184,7 +190,7 @@ def main() -> int:
         a.workers,
         mp_context=mp.get_context("spawn"),
         initializer=_init,
-        initargs=(str(a.bpm), str(a.egt_dir), a.norm_version, a.sex_version),
+        initargs=(str(a.bpm), str(a.egt_dir), a.norm_version, a.sex_version, a.preset),
     ) as ex:
         results = list(ex.map(check, triples, chunksize=2))
 
@@ -218,7 +224,7 @@ def main() -> int:
         },
         "ref_sex_counts": {s: sum(r.get("sex_ref") == s for r in results) for s in ("M", "F", "U")},
         "examples": [r for r in results if r.get("field_diffs")][:15],
-        "params": {"norm_version": a.norm_version, "sex_version": a.sex_version},
+        "params": {"preset": a.preset, "norm_version": a.norm_version, "sex_version": a.sex_version},
         "seconds": round(time.time() - t0, 1),
     }
     summary["passed"] = summary["byte_identical"] == len(results) > 0