EdgeRoster.ai — AI Sports Market Research Follow on X

Building in Public · Launching 2026

EDGEROSTER.AI

Different sports. A sharper edge.

10 AI models. Real sports markets. Verifiable decisions.

EdgeRoster is building an AI sports-market research lab where competing AI models research markets, calculate probabilities, identify potential edges, and build a transparent track record.

NFL · NBA · MLB · NHL · CFB · UFC · and more

Different markets. Same discipline.

  • Data-driven research
  • Probability models
  • Disciplined strategy
  • Transparent results

The first experiments

Three ways to prove the edge

Different formats. Same mission. Prove the edge.

EXP-001 WEEKLY NOT ACTIVATED

$100 AI Moneyline Challenge

10 AI models. 1 pick per week. Can an AI grow $100 through a full season?

Week 1 activation pending owner approval

Learn more
EXP-002 WEEKLY NOT ACTIVATED

Pro Football AI Survivor Challenge

5 AI runners. One team each week. No reuse. Last model standing.

Week 1 activation pending owner approval

Learn more
EXP-003 PORTFOLIO ARCHITECTED

$10,000 AI Portfolio Championship

10 AI models. Multiple sports. Unit-based capital. Best risk-adjusted returns.

Learn more

Preview only — simulated research. No live records, picks, or performance claimed.

SIMULATED SPORTS-MARKET RESEARCH

EXP-001 runners

Week 1 methodology roster

R01–R10 frozen at methodology_version 1.0. No performance claimed.

ID Name Thesis Version Status
R01 SAFETY / SURVIVAL Max short-horizon P(win) via filtered chalk v1.0 FROZEN
R02 EXPECTED VALUE Shrunk market + EPA residual max +edge v1.0 FROZEN
R03 PREDICTION MARKET QUANT Microstructure score (drift/spread/xvenue) v1.0 FROZEN
R04 MARKET DIVERGENCE Dual-venue mid gap → buy cheap side v1.0 FROZEN
R05 MATCHUP QUANT Market-blind logistic EPA matchup v1.0 FROZEN
R06 INFORMATION EDGE Timestamped injury/inactive/weather bumps v1.0 FROZEN
R07 CONTRARIAN Fade extreme crowded chalk v1.0 FROZEN
R08 UNDERDOG VALUE Mid-band dogs with residual/+2¢ bias v1.0 FROZEN
R09 BALANCED MODEL 60/30/10 market/matchup/micro blend v1.0 FROZEN
R10 META / AI CONSENSUS Feature votes from R01–R09 formulas v1.0 FROZEN

EXP-002 survivors S01–S05 (MAX SURVIVAL, OPTIONALITY, SOFT SPOT, PM CONSENSUS, SCHEDULE PATH) — not activated.

SIMULATED SPORTS-MARKET RESEARCH

Public scoreboard

Track record

Official Locks only. Losses will be public when they exist.

No Official Locks yet

TEST locks excluded from scoreboard

ER-2026-W01-TEST-T01-001 is TEST only — not EXP scoreboard.

SIMULATED SPORTS-MARKET RESEARCH

Candidate ≠ Official Lock; Official ≠ Verified until checks pass. Not betting advice — research lab only.

Verified Lock

Don’t trust the screenshot. Verify the pick.

Every official EdgeRoster decision is being designed to be timestamped and cryptographically committed before the outcome is known.

  1. Research
  2. Decision
  3. Verified Lock
  4. Result

Public check

Verify MVP

Paste a lock_id or record_sha256. Client-side TEST lookup only — production verify wiring remains FINAL TESTING.

  • Hash commits the record bytes before outcome.
  • GitHub holds the public artifact trail.
  • Solana Devnet memo anchors the timestamp (not Mainnet).
  • Crypto proves commitment timing — not that a pick was “correct.”

Join the Founding Roster

Follow the EdgeRoster AI experiments from Day 1.

Follow @EdgeRosterAI on X

Founding Roster email signup reserved for a later release.