Initial commit: Ten31 Signal Engine (ingest, scoring brain, corpus seeds)

2026-06-15 09:24:29 -05:00
commit a6aec77506
77 changed files with 6263 additions and 0 deletions
@@ -0,0 +1,75 @@
+"""Under-acted-conviction scorer — Job B, the §7.1 backtest target.
+
+score = conviction_weight x exposure_gap x rising_independent_corroboration
+
+Fires when Ten31 believes something (high conviction), has little/no position (exposure gap), and the
+world is beginning to corroborate it or a derivative of it — independently and with acceleration. This
+is the signal that should have flagged "size up power-infra picks-and-shovels" in 2023.
+
+Exposure is joined LOCALLY (never crosses the frontier boundary, §4.6). Corroboration is RETRIEVED
+(stats nominate), then an LLM helper only FILTERS retrieval near-misses (§5.1) — it cannot add claims.
+"""
+from __future__ import annotations
+
+from .llm_helpers import derivative_relevance
+from .windows import windowed_independence
+
+CONVICTION_WEIGHT = {"low": 0.15, "med": 0.4, "med-high": 0.7, "high": 1.0}
+EXPOSURE_GAP = {"none": 1.0, "lt2": 0.8, "2to10": 0.4, "gt10": 0.1, "unset": 0.6}
+
+
+def score_node(conn, sc, backend, *, as_of: str, derivative: str, conviction_id: str,
+               node_id: str | None, conviction_level: str, exposure: str,
+               is_breaker: bool = False, top_k: int = 40, window_days: int = 28) -> dict:
+    cw = CONVICTION_WEIGHT.get(conviction_level, 0.4)
+    eg = EXPOSURE_GAP.get(exposure, 0.6)
+
+    # 1. RETRIEVE (stats nominate): hybrid search over embedded propositions; as-of post-filter.
+    try:
+        res = sc.search(derivative, collection="propositions", top_k=top_k, rerank=True)
+    except Exception as e:  # noqa: BLE001
+        return _result(conviction_id, node_id, 0.0, {"reason": f"search_failed:{str(e)[:60]}"},
+                       cw, eg, exposure, is_breaker)
+    hits = res.get("data", []) if isinstance(res, dict) else []
+    cand = []
+    for h in hits:
+        pl = (h.get("payload") or {}) if isinstance(h, dict) else {}
+        d = pl.get("date")
+        if not pl.get("claim_id") or not d or d[:10] > as_of:   # Qdrant can't date-filter; do it here
+            continue
+        cand.append({"claim_id": pl["claim_id"], "proposition": pl.get("proposition", ""),
+                     "date": d, "source_id": pl.get("source_id")})
+    if not cand:
+        return _result(conviction_id, node_id, 0.0, {"reason": "no_retrieval", "n_retrieved": 0},
+                       cw, eg, exposure, is_breaker)
+
+    # 2. FILTER near-misses with the LLM (affirms-only). Not a nominator — can't add claims.
+    rel = derivative_relevance(backend, derivative,
+                               [{"claim_id": c["claim_id"], "proposition": c["proposition"]} for c in cand])
+    confirmed = [c for c in cand
+                 if rel.get(c["claim_id"], {}).get("corroborates")
+                 and rel[c["claim_id"]].get("direction") == "affirms"]
+    n_src = len({c["source_id"] for c in confirmed})
+
+    # 3. CORROBORATION = independence-weighted acceleration over the confirmed set (treat as a topic).
+    #    window_days matches corpus cadence: ~90d for quarterly filings/earnings, ~28d for weekly podcasts.
+    wi = windowed_independence(conn, [(c["date"], c["source_id"]) for c in confirmed], as_of, days=window_days)
+    a_corrob = wi["acceleration"]
+    eisc_corrob = wi["eisc0"]
+    corroboration = max(0.0, a_corrob) * eisc_corrob
+
+    score = corroboration if is_breaker else cw * eg * corroboration
+    inputs = {
+        "as_of": as_of, "derivative": derivative, "n_retrieved": len(cand), "n_confirmed": len(confirmed),
+        "n_src": n_src, "a_corrob": a_corrob, "eisc_corrob": eisc_corrob, "k_eff0": wi["k_eff0"],
+        "window_counts": wi["counts"], "window_eisc": wi["eisc"], "corroboration": round(corroboration, 3),
+        "confirmed_claim_ids": [c["claim_id"] for c in confirmed][:50],
+    }
+    return _result(conviction_id, node_id, score, inputs, cw, eg, exposure, is_breaker)
+
+
+def _result(conviction_id, node_id, score, inputs, cw, eg, exposure, is_breaker) -> dict:
+    inputs = {**inputs, "conviction_weight": cw, "exposure_gap": eg, "exposure": exposure,
+              "is_breaker": is_breaker}
+    return {"scorer": "under_acted", "conviction_id": conviction_id, "node_id": node_id,
+            "score": round(float(score), 4), "inputs": inputs}