docs(research): measure precision-adaptive probe gates; no variant clears the bar

20 public AA cases, raman/mean. Lowering MIN_BOUNDARY_DAYS narrows ±10 from
15 to 11 minutes but drops top-1 0.80→0.75; wider radii get wider ranges.
Varga sensitivity weights (V1/V2) match production; D60 (V3) hurts ±10.
Day-precision events offset ±7 never squeeze the true minute out. Production
45/30 gate and equal varga weights stay unchanged.

tests/test_precision_gate_research.py

@@ -0,0 +1,142 @@
+from __future__ import annotations
+
+import json
+from datetime import date
+from pathlib import Path
+
+from scripts.rectification.event_probes import MIN_BOUNDARY_DAYS, REFRESH_MIN_BOUNDARY_DAYS
+import scripts.rectification.event_probes as event_probes
+from scripts.research.precision_gate_lib import (
+    GATES,
+    close_same_year_windows,
+    count_precision,
+    finest_precision,
+    gate_verdict,
+    jitter_day_events,
+    patched_boundary_gate,
+    production_defaults_intact,
+    threshold_for,
+    treat_events,
+    varga_factor,
+    varga_minutes,
+    window_minutes_for_radius,
+)
+
+HOLDOUT = Path("references/real_case_calibration/minute_rectification_holdout_v4.json")
+
+
+def _events() -> list[dict]:
+    return [
+        {"id": "day-1", "domain": "career", "date": "2011-08-24", "precision": "day"},
+        {"id": "year-1", "domain": "education", "date": "2003", "precision": "year"},
+    ]
+
+
+def test_holdout_v4_has_the_stated_precision_mix() -> None:
+    payload = json.loads(HOLDOUT.read_text(encoding="utf-8"))
+    tallies = count_precision([
+        event for case in payload["cases"] for event in case["events"]
+    ])
+    assert tallies["day"] == 59
+    assert tallies["year"] == 84
+    assert tallies["month"] == 0
+    assert len(payload["cases"]) == 20
+
+
+def test_treatment_b_downgrades_day_only() -> None:
+    treated = treat_events(_events(), "B")
+    assert treated[0]["precision"] == "month"
+    assert treated[1]["precision"] == "year"
+
+
+def test_treatment_c_downgrades_everything_to_year() -> None:
+    treated = treat_events(_events(), "C")
+    assert {item["precision"] for item in treated} == {"year"}
+
+
+def test_finest_precision_prefers_day() -> None:
+    assert finest_precision(_events()) == "day"
+    assert finest_precision(treat_events(_events(), "B")) == "month"
+    assert finest_precision(treat_events(_events(), "C")) == "year"
+
+
+def test_g0_refresh_stays_at_production_30() -> None:
+    assert threshold_for("G0", "day", refresh=False) == 45
+    assert threshold_for("G0", "day", refresh=True) == 30
+    assert threshold_for("G1", "day", refresh=True) == 10
+    assert threshold_for("G3", "day", refresh=False) == 5
+    assert set(GATES) == {"G0", "G1", "G2", "G3", "G4"}
+
+
+def test_jitter_stays_inside_the_span_and_is_reproducible() -> None:
+    first = jitter_day_events(_events(), 7, case_id="demo")
+    second = jitter_day_events(_events(), 7, case_id="demo")
+    assert first[0]["date"] == second[0]["date"]
+    original = date.fromisoformat("2011-08-24")
+    shifted = date.fromisoformat(first[0]["date"])
+    delta = abs((shifted - original).days)
+    assert 1 <= delta <= 7
+    assert first[1]["date"] == "2003"
+
+
+def test_varga_factor_downweights_slow_charts_in_a_20_minute_window() -> None:
+    assert window_minutes_for_radius(10) == 20
+    assert varga_minutes("D30") == 4.0
+    assert varga_minutes("D2") == 60.0
+    assert varga_factor("D30", 20) == 1.0
+    assert abs(varga_factor("D2", 20) - 20 / 60) < 1e-9
+    assert varga_minutes("D4") == 7.5
+
+
+def test_forty_day_same_year_window_needs_the_lower_gate() -> None:
+    left = date(2001, 3, 1)
+    right = date(2001, 4, 10)
+    assert close_same_year_windows(left, right, 45) == []
+    kept = close_same_year_windows(left, right, 30)
+    assert [item.month for item in kept] == [3, 4]
+
+
+def test_patched_gate_restores_production_defaults() -> None:
+    assert event_probes.MIN_BOUNDARY_DAYS == 45
+    with patched_boundary_gate(initial=10, refresh=7):
+        assert event_probes.MIN_BOUNDARY_DAYS == 10
+        assert event_probes.REFRESH_MIN_BOUNDARY_DAYS == 7
+    assert event_probes.MIN_BOUNDARY_DAYS == 45
+    assert event_probes.REFRESH_MIN_BOUNDARY_DAYS == 30
+    assert production_defaults_intact()
+    assert MIN_BOUNDARY_DAYS == 45
+    assert REFRESH_MIN_BOUNDARY_DAYS == 30
+
+
+def test_verdict_blocks_a_plus_minus_seven_squeeze() -> None:
+    baseline = {
+        "n": 20, "top1": 0.8, "coverage": 1.0, "width_median": 15,
+        "squeezed": 0, "probes_mean": 4, "refresh_mean": 1, "discriminative_mean": 1,
+    }
+    narrower = {**baseline, "width_median": 9, "refresh_mean": 3, "discriminative_mean": 2}
+    squeezed = {**narrower, "coverage": 0.95, "squeezed": 1}
+    assert gate_verdict(baseline, narrower, jitter7_squeezed=0) == "benefit"
+    assert gate_verdict(baseline, narrower, jitter7_squeezed=1) == "no_benefit"
+    assert gate_verdict(baseline, squeezed, jitter7_squeezed=0) == "no_benefit"
+
+
+def test_eight_extra_questions_for_two_minutes_is_not_worth_it() -> None:
+    baseline = {
+        "n": 20, "top1": 0.8, "coverage": 1.0, "width_median": 15,
+        "squeezed": 0, "probes_mean": 4, "refresh_mean": 1, "discriminative_mean": 1,
+    }
+    costly = {
+        **baseline, "width_median": 13, "refresh_mean": 10, "discriminative_mean": 8,
+    }
+    assert gate_verdict(baseline, costly, jitter7_squeezed=0) == "no_benefit"
+
+
+def test_more_probes_with_a_wider_range_is_not_a_benefit() -> None:
+    baseline = {
+        "n": 20, "top1": 0.55, "coverage": 1.0, "width_median": 33,
+        "squeezed": 0, "probes_mean": 7.1, "refresh_mean": 5.45, "discriminative_mean": 5.45,
+    }
+    wider = {
+        **baseline, "width_median": 37, "refresh_mean": 5.5, "discriminative_mean": 5.5,
+    }
+    assert gate_verdict(baseline, wider, jitter7_squeezed=0) == "no_benefit"