Science Milestones & Research Trader

> This is a template.

> The default signal is keyword-based market discovery combined with conviction-based sizing and science_bias() — remix it with the data sources listed below.

> The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview

Science markets are priced by non-experts following journalist headlines. Journalists systematically amplify the most optimistic interpretation of scientific results. The research community knows the replication rates, timeline track records, and definitional ambiguities behind each claim type. Retail doesn't. This creates large, consistent mispricings — and two of the most exploitable edges anywhere on Polymarket: hype-claim dampening and Nobel calendar timing.

Signal Logic

Default Signal: Conviction-Based Sizing with Science Hype Correction

1. Discover active science and research markets on Polymarket
2. Compute base conviction from distance to threshold (0% at boundary → 100% at p=0/p=1)
3. Apply science_bias() — combines science claim type with Nobel calendar timing
4. Size = max(MIN_TRADE, conviction × bias × MAX_POSITION) — capped at MAX_POSITION
5. Skip markets with spread > MAX_SPREAD or fewer than MIN_DAYS to resolution

Science Bias (built-in, no API required)

Factor 1 — Science Claim Type: Hype Cycle vs Replication Reality

The RT Superconductor Rule — 0.55x is the lowest multiplier in the entire project across all traders. The reason is historical: every significant "room temperature superconductor" claim since 1987 has either failed replication or been retracted. The 2023 LK-99 episode — global excitement, total replication failure within two weeks — is not an outlier. It is the pattern. When a RT superconductor market appears on Polymarket, the YES side is being priced by media excitement, not physics consensus. The NO edge is structural.

The Fusion Rule — "Fusion is always 5 years away" is not a joke; it's a documented pricing pattern. NIF's December 2022 ignition (Q>1) was genuinely historic. But commercial fusion — grid-connected, cost-competitive electricity — requires solving plasma engineering, materials science, and economic problems that are decades away. Every market asking "will fusion power X by Y" where Y is within 10 years is systematically overpriced.

Factor 2 — Nobel Calendar Timing

The Nobel Prize follows a known annual schedule. Two data sources are public every year:

The skill prints nobel=ANNOUNCEMENT / CLARIVATE / off-season on startup.

Clarivate Citation Laureates — Clarivate analyzes citation impact across all scientific literature and publishes annual shortlists of researchers predicted to win Nobel Prizes. Their hit rate is ~40% correct in advance — far above the base rate. The key insight: Nobel committees reward longevity of impact, not recency. The Clarivate list reflects citation networks built over decades; retail chases last year's hottest paper. These systematically diverge.

Keywords Monitored

Nobel Prize, Nobel, physics, fusion energy, ITER, nuclear fusion, dark matter,
quantum computer, quantum computing, breakthrough, nature paper, CERN,
James Webb, room temperature superconductor, AGI, consciousness, cancer cure,
Alzheimer treatment, longevity, aging reversal, CRISPR, gene therapy,
clinical trial, phase 3, replication, preprint, arXiv, peer review,
superconductor, LK-99, qubit, quantum supremacy, drug approval

Remix Signal Ideas

• Clarivate Citation Laureates: September shortlist — use to adjust YES_THRESHOLD per Nobel candidate market; candidates on the shortlist deserve lower YES_THRESHOLD than those off it
• arXiv API: Monitor preprint velocity per keyword topic — spikes 3–7 days before mainstream coverage, before markets reprice
• ClinicalTrials.gov: Gene therapy and Alzheimer drug trial completion dates — feed expected date into days-to-resolution analysis
• Semantic Scholar API: Real-time citation graph — detect breakout papers early before journal publication drives Polymarket question creation

Safety & Execution Mode

The skill defaults to paper trading (venue="sim"). Real trades only with --live flag.

autostart: false and cron: null — nothing runs automatically until you configure it in Simmer UI.

Required Credentials

Tunables (Risk Parameters)

All declared as tunables in clawhub.json and adjustable from the Simmer UI.

Dependency

simmer-sdk by Simmer Markets (SpartanLabsXyz)

• PyPI: https://pypi.org/project/simmer-sdk/
• GitHub: https://github.com/SpartanLabsXyz/simmer-sdk