research: option-volume signals on OPRA bars 2024-03..2026-09 (STOP)

Johnson-So O/S has the opposite sign (Q5-Q1 -11.4%/yr, t -1.63) and
correlates -0.65 with the momentum score; unsigned put/call is flat
(t 0.42). Neither gated signal passes; keep collecting, retest at ~5 years.

The data handling was fixed after a coverage check of the panel, before any
return was computed: stock volume on every day from stock_raw, and a day
without bars counts as 0 contracts only inside a name's bar span (outside it
the options traded under an older ticker or the root's history starts later).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

CLAUDE.md

@@ -113,7 +113,7 @@ PYTHONPATH=. uv run --with numba python -m research.lab.svr_combo     # low_svr2
 PYTHONPATH=. uv run python -m research.lab.fetch_options snapshot|status  # daily S&P 500 option chains after the close: indicative quotes (forward-only from 2026-10-12) + OPRA daily bars + print-vs-quote quality sample; data/options/us/; timer quant-trading-options
 PYTHONPATH=. uv run python -m research.lab.fetch_options backfill        # OPRA daily option bars since 2024-02 for every S&P 500 member since then (resumable, ~2-3 h; pauses 16:10-16:55 NY); then builds volume_panel.csv.gz
 PYTHONPATH=. uv run python -m research.lab.fetch_options volume-panel    # date x underlying option volume (all 0-100 DTE strikes and the 5-100 DTE / 0.7-1.3 band), os_volume, pc_volume
-PYTHONPATH=. uv run --with numba python -m research.lab.option_volume   # Johnson-So O/S and put/call volume on OPRA bars 2024-03..2026-09 (preregistered before the backfill finished; gate |t| >= 3)
+PYTHONPATH=. uv run --with numba python -m research.lab.option_volume   # Johnson-So O/S and put/call volume on OPRA bars 2024-03..2026-09 (preregistered; STOP 2026-10-12: O/S sign reversed, t -1.6, corr -0.65 with momentum; put/call t 0.4)
 uv run python -m research.lab.fetch_us_fundamentals --universe mid      # EDGAR PIT facts for S&P 400 ever-members (name-checked CIKs)
 uv run python -m research.lab.fetch_us_fundamentals --universe small    # the same for S&P 600 (IJR)
 PYTHONPATH=. uv run python -m research.lab.midcap_sleeve [--only h1..h4] [--universe small]  # S&P 400 sleeves vs IJH; S&P 600 replication vs IJR (all REJECT 2026-10-08)

research/lab/fetch_options.py

@@ -106,6 +106,10 @@ OCC = re.compile(r"^[A-Z]{1,5}\d{6,7}[CP]\d{8}$")   # what the bars endpoint acc
 BAR_COLS = ["date", "underlying", "symbol", "type", "expiry", "strike", "o", "h", "l", "c", "v", "n", "vw"]
 
 
+class BackendTimeout(RuntimeError):
+    """HTTP 504 on a request for many symbols: the caller splits the batch."""
+
+
 class Api:
     """Paced GET with retries. ``yield_to_snapshot`` sleeps through 16:10-16:55
     New York on weekdays so a backfill leaves the rate limit to the daily run."""
@@ -140,6 +144,8 @@ class Api:
                 time.sleep(2 ** attempt)
                 continue
             self.n += 1
+            if r.status_code == 504 and params.get("symbols", "").count(",") >= 50:
+                raise BackendTimeout(r.text[:200])   # the same batch times out again (SNDK, 1000 contracts)
             if r.status_code == 429 or r.status_code >= 500:
                 time.sleep(2 ** attempt)
                 continue
@@ -238,14 +244,23 @@ def option_bars(api: Api, symbols: list[str], start: str, end: str, timeframe: s
     e = (dt.datetime.combine(dt.date.fromisoformat(end), dt.time(0), NY) if len(end) == 10
          else dt.datetime.fromisoformat(end))
     end = min(e, dt.datetime.now(NY) - dt.timedelta(minutes=16)).isoformat()
+
+    def fetch(chunk: list[str]) -> list[dict]:
+        params = {"symbols": ",".join(chunk), "timeframe": timeframe, "start": start, "end": end, "limit": 10000}
+        got = []
+        try:
+            for bars in api.pages(f"{DATA}/v1beta1/options/bars", params, "bars"):
+                for sym, bl in bars.items():
+                    got += [{"symbol": sym, "t": b["t"], "o": b["o"], "h": b["h"], "l": b["l"], "c": b["c"],
+                             "v": b["v"], "n": b.get("n"), "vw": b.get("vw")} for b in bl]
+        except BackendTimeout:                       # restart the chunk as two halves
+            h = len(chunk) // 2
+            return fetch(chunk[:h]) + fetch(chunk[h:])
+        return got
+
     rows = []
     for i in range(0, len(symbols), 1000):
-        params = {"symbols": ",".join(symbols[i:i + 1000]), "timeframe": timeframe, "start": start, "end": end,
-                  "limit": 10000}
-        for bars in api.pages(f"{DATA}/v1beta1/options/bars", params, "bars"):
-            for sym, bl in bars.items():
-                rows += [{"symbol": sym, "t": b["t"], "o": b["o"], "h": b["h"], "l": b["l"], "c": b["c"],
-                          "v": b["v"], "n": b.get("n"), "vw": b.get("vw")} for b in bl]
+        rows += fetch(symbols[i:i + 1000])
     return rows
 
 

research/lab/option_volume.py

@@ -32,6 +32,13 @@ Test (PIT S&P 500 research panel, members only, >= 50 names a day):
     the spanning t on it, as in research/lab/factor_census.py.
 Window: 2024-03-01 .. the panel's last date (2026-09-24), about 2.5 years.
 Halves are split at 2025-06-01.
+Data handling (set after a coverage check of the panel, before any return was
+computed): stock volume comes from stock_raw.csv.gz on every day. A day
+without bars counts as 0 contracts inside the name's first..last bar date
+(thin names such as NWS, REG, UDR: 0.6% of stock-days). It is missing
+outside that span, where the options traded under an older ticker or Alpaca's
+history for the root starts later (BNY, XYZ, BRK.B, BF.B ...), and on
+2024-02-02, which has no bars at all.
 
 Gate per gated signal (fixed before the backfill finished; the factor census
 asks |t| >= 3 of a new factor):
@@ -47,6 +54,33 @@ Decision:
 This is the first look at these data. Nothing in the window was used before.
 The rule is written to prereg.json before the run; the script refuses to
 overwrite results.json.
+
+Result (2026-10-12): STOP. low_os_5 fails V1, V2 and V3. low_pc_5 fails V1
+and V3.
+
+  2024-03..2026-09, h=5      IC (t)          Q5-Q1/yr (t)    halves %/yr    top-20 alpha vs EW (t)  corr house
+  low_os_5       (gated)     -0.013 (-1.32)  -11.4% (-1.63)   -1.1 / -21.3   -5.4% (-1.40)           -0.65
+  low_pc_5       (gated)     +0.000 (+0.07)   +1.2% (+0.42)   +1.0 /  +1.4   -5.4% (-1.40)           -0.08
+  low_os_21                  -0.018 (-1.70)  -11.7% (-1.68)   -4.0 / -19.1   -2.7% (-0.71)           -0.65
+  low_os_band_5              -0.013 (-1.36)  -10.1% (-1.52)   -1.2 / -18.6   -5.0% (-1.24)           -0.65
+  low_os_abn                 -0.003 (-0.60)   -3.7% (-1.05)   +2.1 /  -7.7   -6.0% (-1.34)           -0.46
+  call_shift                 -0.009 (-1.73)   -2.5% (-0.87)   -1.0 /  -3.7   -7.0% (-1.95)           -0.19
+  house_overnight_recovery   +0.014 (+1.07)   +8.0% (+0.91)   -2.5 / +18.1  +31.0% (+1.90)           1
+
+  - O/S has the opposite sign to Johnson-So in this window. Names with high
+    option volume relative to stock volume did better, mostly after 2025-06
+    (-21%/yr in the second half). The O/S score correlates -0.65 with the
+    momentum score: high O/S marks recent winners with heavy call trading.
+    Its spanning t on the momentum spread is -1.28, so momentum already holds
+    what O/S carries. It is not a usable signal in either direction (|t| < 2).
+  - Unsigned put/call volume is flat (t 0.42). Without open-buy signing this
+    does not test Pan-Poteshman's result.
+  - One of the 24 reported rows reaches |t| >= 2: call_shift's top-20 alpha at
+    h=21 (-7.8%, t -2.34). That is within what chance gives.
+  - Boundary: 2.5 years in one regime (AI-led momentum). SNDK was fetched after
+    a batch-splitting fix for HTTP 504. CDAY (renamed DAY) and NVR (no listed
+    options) have no bars.
+  - Next: keep collecting the daily bars and retest at ~5 years (2029).
 """
 
 from __future__ import annotations
@@ -66,6 +100,7 @@ from research.lab.us_sweep import run
 
 OUT = os.path.join(RESULTS, "option_volume")
 PANEL = os.path.join("data", "options", "us", "volume_panel.csv.gz")
+STOCK = os.path.join("data", "options", "us", "stock_raw.csv.gz")
 START = "2024-03-01"
 SPLIT = "2025-06-01"
 GATED = ["low_os_5", "low_pc_5"]
@@ -79,6 +114,10 @@ PREREG = {
     "decision": {"CONTINUE": "preregister a combination with overnight_recovery_top10 and add the live signal",
                  "STOP": "keep collecting; retest at ~5 years of history"},
     "data_status": "first look; option bars backfilled 2026-10-12, not inspected before this rule",
+    "data_handling": "fixed after a coverage check of the panel, before any return was computed: stock volume "
+                     "from stock_raw on every day; a day without bars counts as 0 contracts inside the name's "
+                     "first..last bar date, and is missing outside it (older tickers, late root history) and on "
+                     "2024-02-02 (no bars)",
 }
 
 
@@ -89,15 +128,30 @@ def wide(P: pd.DataFrame, col: str, dates, cols) -> pd.DataFrame:
     return w.reindex(index=dates, columns=cols)
 
 
-def signals(p, P: pd.DataFrame) -> dict[str, pd.DataFrame]:
+def coverage(P: pd.DataFrame, dates, cols) -> pd.DataFrame:
+    """True where a missing bar row means no option traded: inside the name's
+    first..last bar date and on a date with any bars. Outside it the volume is
+    unknown (options listed under an older ticker, e.g. XYZ before 2025-01 as SQ;
+    Alpaca's history for the root starts later, e.g. BRK.B 2024-08; 2024-02-02
+    has no bars at all)."""
+    span = P.groupby("underlying")["date"].agg(["min", "max"])
+    span.index = [c.replace(".", "-") for c in span.index]
+    lo = pd.to_datetime(span["min"]).reindex(cols).values[None, :]
+    hi = pd.to_datetime(span["max"]).reindex(cols).values[None, :]
+    d = dates.values[:, None]
+    has_day = np.asarray(dates.isin(pd.to_datetime(P["date"].unique())))[:, None]
+    return pd.DataFrame((d >= lo) & (d <= hi) & has_day, index=dates, columns=cols)
+
+
+def signals(p, P: pd.DataFrame, stock: pd.DataFrame) -> dict[str, pd.DataFrame]:
     dates, cols = p.dates, p.close.columns
-    have = wide(P, "volume", dates, cols)
-    has_options = have.notna()                       # stock-volume row from the options store exists
-    C = wide(P, "v_C", dates, cols).where(has_options).fillna(0).where(has_options)
-    Pv = wide(P, "v_P", dates, cols).where(has_options).fillna(0).where(has_options)
-    Cb = wide(P, "v_band_C", dates, cols).where(has_options).fillna(0).where(has_options)
-    Pb = wide(P, "v_band_P", dates, cols).where(has_options).fillna(0).where(has_options)
-    sv = have.where(have > 0)
+    sv = wide(stock.rename(columns={"symbol": "underlying"}), "volume", dates, cols)
+    sv = sv.where(sv > 0)                            # unadjusted SIP volume on every stock day
+    cover = coverage(P, dates, cols)
+    C = wide(P, "v_C", dates, cols).fillna(0).where(cover)
+    Pv = wide(P, "v_P", dates, cols).fillna(0).where(cover)
+    Cb = wide(P, "v_band_C", dates, cols).fillna(0).where(cover)
+    Pb = wide(P, "v_band_P", dates, cols).fillna(0).where(cover)
     s = lambda x, n: x.rolling(n, min_periods=n).sum()  # noqa: E731
     os5 = s(C + Pv, 5) * 100 / s(sv, 5)
     os21 = s(C + Pv, 21) * 100 / s(sv, 21)
@@ -127,7 +181,7 @@ def main() -> None:
 
     p, _ = load("us")
     P = pd.read_csv(PANEL)
-    S = signals(p, P)
+    S = signals(p, P, pd.read_csv(STOCK))
     end = str(p.dates[-1].date())
     m = p.member
     house = (pct_rank(FACTORS["overnight_mom"](p), m) + pct_rank(FACTORS["rec_126"](p), m)) / 2