LucentLucent Intel

Lucent Composite Fair Value Methodology

Per-market composite fair-value probability served under /api/pm/fair-value. The COMP360 year-end filing market uses a Kalshi-only reference with explicit book-quality and expiry checks. Other markets use a weighted geometric mean of odds over three provider legs: Kalshi (when a public-API anchor exists), Polymarket (when a Gamma-API anchor exists), and a Lucent internal literature-priors model leg with structured CHMP + FAERS adjustments. Every published probability is reproducible from the response envelope's breakdown field.

Registered markets

V1 admits only registry-listed marketKey values. Requests for any other key return 404 (never available: false — that’s reserved for known markets with insufficient substrate). Registry source of truth: data/pm-market-registry/*.json.

CMPS-slate parity (6)

marketKeyTickerResolution axisKalshi anchorPolymarket anchor
cmps:adcom-yesCMPSprocedure——
cmps:controversy-blindingCMPSprocedure——
cmps:controversy-remsCMPSsafety——
cmps:controversy-voucherCMPSprocedure——
cmps:nda-by-dec-31-2026CMPStimingKXNEWDRUGAPPLICATIONCMPS-360-27…—
cmps:review-priorityCMPSprocedure——

Extended Lucent-owned (6)

marketKeyTickerResolution axisKalshi anchorPolymarket anchor
cmps:approval-by-jan-2027CMPSapprovalKXFDAAPPROVALDATECMPS-360-27JAN…—
cmps:approval-by-jan-2028CMPSapprovalKXFDAAPPROVALDATECMPS-360-28JAN…—
cmps:approval-by-jul-2027CMPSapprovalKXFDAAPPROVALDATECMPS-360-27JUL…—
cmps:approval-by-mar-2027CMPSapprovalKXFDAAPPROVALDATECMPS-360-27MAR…—
cmps:approval-by-oct-2027CMPSapprovalKXFDAAPPROVALDATECMPS-360-27OCT…—
psych:any-by-jan-2027—approvalKXFDAAPPROVALPSYCHEDELIC-27-ANY…—

Lucent Composite Fair Value Methodology

This page documents how Lucent computes fair-value probabilities for prediction-market contracts served under /api/pm/fair-value. Most markets use a weighted geometric mean of odds (logit pool) over three provider legs. The COMP360 year-end filing market uses the scoped Kalshi reference policy below. Published probabilities are decision-support inputs, not investment advice.

COMP360 complete-submission reference

Only cmps:nda-by-dec-31-2026 uses comp360-nda-2026-kalshi-v1: 100% Kalshi KXNEWDRUGAPPLICATIONCMPS-360-27JAN01, which concerns NDA submission before January 1, 2027, not FDA approval. Kalshi's NEWDRUGAPPLICATION terms count a rolling submission upon receipt of the complete package; FDA acceptance or approval is not required. This policy does not price an approval event or infer a filing probability from an approval curve.

One uncached market-detail response supplies active status, exact ticker, primary/secondary rules, close time, early-close capability, and the best YES bid/ask with their sizes. Changed contract fields fail closed. The probability is the exact bid/ask midpoint, with no last-trade fallback, open-interest weighting, internal prior, or Polymarket leg. The spread must be positive and at most 5 cents. Resting notional at each best YES and NO bid must be at least $50; NO bid is 1 minus YES ask. These are pilot operational gates, not empirical confidence estimates or a guarantee against manipulation. Liquidity limits must be revisited before increasing maker exposure beyond the approximately $50 pilot budget.

Reference snapshots cache uniformly for 10 seconds on both availability arms. expiresAt is derived from the start of observation plus 10 seconds and capped at 2027-01-01T00:00:00.000Z. The API forbids shared caching for this market. This timestamp is a conservative quoting cutoff, five hours before Lucent's year-end Eastern resolution cutoff; it does not change market settlement rules. Exact cross-venue timezone/source equivalence remains a rollout check, not a guaranteed hedge. A successful GET records when we observed the book, not when its orders last changed. News can still move the reference within this window and execution adds latency.

Ordinary reference failures and the quoting cutoff return no_provider_legs_fresh, so the maker cancels and retries without a prior fallback. An actual contract-content mismatch returns reference_contract_mismatch and requires operator investigation. Breakdown provenance and failure detail survive caching. The consumer requires this policy identifier, anchor, and expiry for this market, rejecting old blended responses after rollback.

Provider set

Three provider legs compose the fair value:

  • **Kalshi** — public trade-api v2 price on markets where the registry entry carries a Kalshi anchor. Mid-price from bid/ask when a valid book exists, falling back to last trade. Non-active status maps to freshness 0.
  • **Polymarket** — public Gamma API price on markets where the registry entry carries a Polymarket anchor. Preferred price is lastTradePrice; falls back to the YES token in outcomePrices[0]. Closed markets map to freshness 0.
  • **Lucent internal model** — literature-derived base rate per (eventType, eventSubtype, therapeuticArea) tuple, plus structured adjustments (CHMP precedent, FAERS safety-signal count). Zero use of biopharma-intel's Hit Rate substrate — that measures alert-capture timeliness, not approval probability.

The composite is a pure logit pool at V1 — EXTREMIZATION_FACTOR = 1.0. Satopää et al. (2014) show extremized logit pool outperforms non-extremized on resolved-outcome corpora with d ∈ [1.16, 3.92], but V1 has zero resolved substrate for these markets; any factor choice would be unjustifiable. V2 revisits once N ≥ 30 resolved markets accumulate.

Weight formula

Each provider leg's raw weight is a product of four factors, all in [0, 1]:

w_i = provider_base_i × freshness_score_i × liquidity_score_i × resolution_match_score_i

Provider base weights: Kalshi 0.4, Polymarket 0.4, internal model 0.2. Raw weights normalize to sum to 1.0 (SPEC D4 Step 1); the model leg is then capped at MODEL_LEG_CAP_WITH_EXTERNAL = 0.4 of the FINAL NORMALIZED weight whenever any external leg is present (SPEC D4 Step 2). Cap redistribution is proportional to external legs' RAW weights:

Given raw per-leg weights w_kalshi, w_poly, w_model:

      // Step 1 — provisional normalize
      total_raw = w_kalshi + w_poly + w_model
      n_i = w_i / total_raw   for each i
      // Step 2 — model-leg cap if any external leg is present
      if (n_kalshi + n_poly > 0) and n_model > MODEL_LEG_CAP_WITH_EXTERNAL:
        excess = n_model - MODEL_LEG_CAP_WITH_EXTERNAL
        n_model = MODEL_LEG_CAP_WITH_EXTERNAL
        external_raw_sum = w_kalshi + w_poly
        n_kalshi += excess × (w_kalshi / external_raw_sum)
        n_poly   += excess × (w_poly   / external_raw_sum)

Worked example 1 (both externals full-quality): raw {kalshi: 0.4, poly: 0.4, model: 0.2}. Provisional n = {0.4, 0.4, 0.2}. Model at 0.2 < 0.4 cap. Final {0.4, 0.4, 0.2}.

Worked example 2 (kalshi unreachable, poly stale + thin): raw {kalshi: 0, poly: 0.16, model: 0.2}. Provisional n = {0, 0.444, 0.556}. Cap fires; excess = 0.156 goes fully to poly (kalshi raw = 0). Final {0, 0.6, 0.4}.

Worked example 3 (both externals absent): raw {kalshi: 0, poly: 0, model: 0.2}. Cap does NOT apply (no external leg present). Final {0, 0, 1.0}. Model leg is *the* answer, not a shrinkage.

Model leg composition

The internal-model leg is a literature-derived base rate plus two structured adjustments. The base rate lives in data/fair-value-model-priors/base-rates.json — one row per unique (eventType, eventSubtype, therapeuticArea) tuple, each carrying {rate, citation, capturedAt, notes}. Sources: FDA approval statistics, BIO/MIT/Tufts CSDD industry meta-analyses, PDUFA priority-review base rates, FDA AdCom calendar reviews, FDA PRV disclosure register, FDA REMS document register. Every prior is version-pinned per SPEC D18: the priors JSON is canonicalized into the methodology-hash sha input, so any edit → sha changes → forces FAIR_VALUE_METHODOLOGY_VERSION bump.

Two adjustments apply on the log-odds axis:

1. **CHMP precedent** — applies when regulator ∈ {fda, both} AND a CHMP opinion exists at event_date ≤ asOf. Positive → +CHMP_POSITIVE_LOGODDS_DELTA (+0.05). Negative → CHMP_NEGATIVE_LOGODDS_DELTA (−0.05). Withdrawn / none → 0. EMA-only markets excluded (would double-count). 2. **FAERS safety-signal count** — applies ONLY when resolutionAxis === "safety" AND count > 0 in the 12 months preceding asOf. Delta = FAERS_PER_SIGNAL_LOGODDS_DELTA × min(count, FAERS_COUNT_CAP) = −0.03 × min(count, 3). Ceiling: 3+ signals saturate at −0.09.

All four coefficient constants (CHMP_POSITIVE_LOGODDS_DELTA, CHMP_NEGATIVE_LOGODDS_DELTA, FAERS_PER_SIGNAL_LOGODDS_DELTA, FAERS_COUNT_CAP) plus FAIR_VALUE_METHODOLOGY_VERSION live in src/fair-value/methodology.ts alongside the weight formula. Editing any of them requires version bump per SPEC D12/D18.

Freshness gate

Per-provider freshness maps quote age to a multiplicative factor (SPEC D6):

  • Age < 10 minutes → 1.0
  • Age < 1 hour → 0.5
  • Age < 24 hours → 0.1
  • Older than 24 hours OR unreachable → 0 (leg dropped)

Internal-model leg is always freshness 1.0 (computed at request time). Kalshi + Polymarket endpoints don't expose per-quote timestamps cleanly at the V1 wire shape; a live 200 with a valid active/open market maps to 1.0 and any failure maps to 0.

Availability discipline

The response envelope is a discriminated union on available. Silent-omission over caveated inclusion is the load-bearing prior (Phase 26c.3 canonical).

- available: true — composite computed. Carries fairValue, breakdown, computedAt, methodologyHash, methodologyVersion. - available: false — one of two named reasons: - no_provider_legs_fresh — every provider leg dropped at the freshness gate. - internal_model_missing_prior — the registry entry references a tuple absent from the priors JSON, and no external leg is present to carry the composite.

Unknown marketKey values return 404 at the route layer — NOT available: false. That distinction is load-bearing: available: false is for known markets with insufficient substrate.

Cap on internal model

When any external leg contributes, the internal-model leg caps at 40% of the FINAL NORMALIZED weight (MODEL_LEG_CAP_WITH_EXTERNAL = 0.4). Defers to external liquidity by design; on markets where Kalshi/Polymarket carry real anchors, the model leg is a shrinkage prior. When BOTH externals are absent, no cap fires and the model leg becomes the whole composite. V1 accepts the risk of drowning out genuine model-leg edge; V2 revisits if evidence accumulates.

Snapshot cache

Composite results are persisted append-only to pm_fair_value_snapshots keyed on (market_key, computed_at). Cached rows must match the current methodology version AND hash. Composite markets use a uniform 10-minute TTL across statuses (D19); the scoped COMP360 reference uses 10 seconds across statuses. Expired snapshots trigger fresh compute under a per-market advisory lock. Snapshot rows are never updated in place.

Version + drift

The methodology hash is sha256(METHODOLOGY_BODY + "::" + FAIR_VALUE_METHODOLOGY_VERSION + "::" + canonicalize(base-rates.json)). Three inputs, one sha:

  • METHODOLOGY_BODY — this prose, byte-exact.
  • FAIR_VALUE_METHODOLOGY_VERSION — the version string.
  • data/fair-value-model-priors/base-rates.json — read at hash-computation time, canonicalized via the shared sorted-key JSON serializer.

Editing any of the three changes the sha. The methodology-hash regression test pins the current sha. A body edit without a version bump leaves the sha stable — silent-drift risk mitigated only by PR discipline. A priors JSON edit forces the sha to change (D18 closes the priors silent-drift arm). Version-bump discipline mirrors HIT_RATE_COMPUTE_VERSION + BACKTEST_METHODOLOGY_VERSION.

Disclaimer

These composite fair-value probabilities are decision-support inputs, not investment advice. External-provider legs (Kalshi, Polymarket) depend on third-party public APIs whose availability is not part of Lucent's uptime SLA. The internal-model leg is anchored on literature-derived base rates with named citations and structured adjustments — it carries the same known-unknown as any prior-driven estimate on a market with limited resolved-outcome history. Nothing on this page or in the associated API responses constitutes a solicitation, offer, or recommendation to buy or sell any security or take any trading position.

Composite-market provider weights

ProviderBase weightNotes
kalshi0.40Public trade-api v2 mid.
polymarket0.40Public Gamma API price.
internal_model0.20Literature priors + CHMP/FAERS adjustments; capped at 40% of the final normalized weight when any external leg is present (SPEC D4).

Extremization factor: 1.00 — pure logit pool at V1. Bumping this constant requires FAIR_VALUE_METHODOLOGY_VERSION co-bumped per SPEC D12.

Model-leg adjustment constants

ConstantValueFires when
CHMP_POSITIVE_LOGODDS_DELTA+0.05Positive CHMP opinion at event_date ≤ asOf; regulator ∈ {fda, both}.
CHMP_NEGATIVE_LOGODDS_DELTA-0.05Negative CHMP opinion at event_date ≤ asOf.
FAERS_PER_SIGNAL_LOGODDS_DELTA-0.03Per FAERS safety signal in prior 12mo when resolutionAxis === "safety".
FAERS_COUNT_CAP3Signals cap; 10 signals still saturate at -0.09 on log-odds.

Freshness gate

Age bucketScore
< 10 min1.00
< 1 h0.50
< 24 h0.10
Older / unreachable0

Internal-model leg always freshness 1.0 (computed at request time). Providers with freshness 0 are dropped from composition (weight × 0 = 0).

Methodology version sha: a17f72a9

Methodology version: 1.1.0

Priors captured as of (latest across data/fair-value-model-priors/base-rates.json).

Compute cadence: per-request; snapshot cached for 10 min regardless of available status (SPEC D19).

See also the methodology index for Lucent’s other published methodologies (Hit Rate, Strategy Primitive).

Not investment advice. Composite fair-value probabilities are decision-support inputs anchored on third-party public APIs (Kalshi, Polymarket) whose availability is not part of Lucent’s uptime SLA. The internal-model leg is anchored on literature-derived base rates with named citations in data/fair-value-model-priors/base-rates.json (source-viewable in the repo); it carries the same known-unknown as any prior-driven estimate on a market with limited resolved-outcome history. Nothing on this page or in the associated API responses constitutes a solicitation, offer, or recommendation to buy or sell any security or take any trading position.