data economy and infrastructure for AI forecasting
Solana
Joined April 2026
- Tweets73
- Following62
- Followers40
- Likes122
offdiagonal retweeted
Most AI models try to predict the future.
solana:FMGe8RStdPc1YR59BBuV5Ui12DEe3Q2zVoihrJBbpump does something much harder: it acts as a polygraph for predictions. It audits an entire panel of forecasts and tells you when consensus is an illusion.
Here is what just landed in Zeno v1.05:
1. Unified Architecture: 89.9M parameters across 13 domains, with open weights and @onnxai runtimes for all 13 fields.
2. Hardened Out-of-Sample Edge:
• Weather history: +33.1% edge on chronologically split later weeks (95% CI: +28.5% to +37.6%)
• 24-hour crypto: +13.1% edge on later weeks across 19,200+ cases (surviving 39-comparison corrections)
3. Radical Honesty: If Zeno doesn't beat the baseline on held-out data (e.g., COVID, RSV), it refuses to intervene and routes to the reference forecast. No unearned overconfidence.
4. Lineage-Aware Weighting: 10 models sharing the same base weights only get 1 vote.
Every prediction, outcome, and per-case CSV is open on @huggingface.
Test any panel live or inspect the audit: zenodivergent.dev 🫡
Today we cut v6.42 for offdiagonal.space
Instead of 40 overlapping release folders, the entire corpus now resolves to one unified, content-addressed current pack (current-20261105) with 42 verified files and zero synthetic backfill.
What shipped today:
1. @Research_FRI ForecastBench Full Snapshot: 3,079,921 rows + per-question resolution pairs (55,372 human forecasts across 105 questions, exactly 0 clock violations).
2. Real Crypto Options History: 971,766 BTC and ETH @DeribitOfficial option trades across 64,928 instruments (2024–Nov 2026). Real executed trade prints, not fitted implied volatility curves.
3. @numinous_ai Feed: 1,284,335 forecast points and 597,669 price points across 12,117 live prediction markets.
4. Exact @GitHub Publication Proofs: 1,691 COVID/RSV health model versions pinned strictly to GitHub-stamped landing commits, re-hashed byte-for-byte. Client-dated commits are rejected.
5. Macro Chronology Cleaned: Recovered 40 historical @ECB rounds (2005–2014) dated by first-print Monthly Bulletins; Philly Fed releases pinned to measured upper bounds rather than unverified 8:30 AM assumptions.
6. Access & Audit Security: Hardened panel label audits and round commitment feeds under strict partner-key verification.
403M+ frozen rows across 12 domains.
History is evidenced, never filled.
Explore the live corpus, read our audit logs, or review our agent guides:
🌐 Web: offdiagonal.space
📊 Datasets & API: offdiagonal.space/data
🤖 Agent guide: offdiagonal.space/llms.txt
⚡ Data economy pilot: offdiagonal.space/access
Build on evidence that was witnessed, not filled.
Why a Decentralized Data Economy Layer?
Curating and verifying 400M+ real-world rows across dozens of live sensors, surveys, and prediction markets cannot remain a centralized burden.
It’s time for a proper decentralized data coordination layer:
• On-chain public anchors: Posting SHA-256 release hashes to Solana to cryptographically prove when a dataset was committed.
• Data repair bounties: Community bounties to spot upstream data anomalies, sensor drift, and retro revisions.
• Transparent treasury: On-chain ledger of all data collection grants and verifications.
We package these releases into immutable Parquet bundles on @huggingface.
Between core partner handoffs (including @zenoVision_’s frontier runs) and research downloads, teams are pulling hundreds of millions of clean rows to train multi-domain foundation models without temporal leakage.
Every release is tied to an immutable commit hash, never a moving branch tip.
Why This Data Is Structurally Different?
In forecasting, "filling in missing data" is poisoning your model.
Our three core rules:
1. Zero synthetic zero-fill: If a sensor or market didn't record, it's marked "not measured" — never averaged or smoothed.
2. True first prints: Models are scored against what was knowable at 8:30 AM on release day, not retrospective revisions.
3. Co-failure mapping: Tracking when entire model families fail together across domains.
This isn’t synthetic fluff.
It’s physical and economic ground truth:
• 403.4M total database records across 327 tables
• 762,014 CDC FluSight forecasts (114 models) paired with first official prints via exact commit blobs
• 76,271 Philly Fed predictions across 146 survey rounds paired with ALFRED first-release dates
• 198 consecutive weeks of UK grid demand (NESO vs Elexon)
• 368 crowd probability vectors replayed strictly at decision time across 193 questions
Most AI forecasting models are trained on benchmarks filled with hidden time travel — evaluating predictions against revised data published months later, or pulling market odds from resolution time.
We built offdiagonal.space to fix this: 403M+ frozen, immutable rows across 12 real-world domains.
Pinned by SHA-256, zero imputation, zero lookahead leakage. 🧵👇
Most AI forecasting models are evaluated on synthetic benchmarks or backfilled data with hidden lookahead leakage.
We just shipped v6.41.1 for solana:FMGe8RStdPc1YR59BBuV5Ui12DEe3Q2zVoihrJBbpump next training run — 260M+ frozen, append-only rows across 12 domains:
• 762,014 CDC @FluSight forecasts (114 models) paired with first official prints, dated by exact @GitHub commit blob
• 76,271 Philadelphia Fed predictions across 146 survey rounds verified against ALFRED first-release dates
• 368 crowd probability vectors replayed from Manifold bet-by-bet history strictly at decision time
• 20,284 immutable event links sealed before target resolution
• 198 consecutive weeks of continuous UK grid demand, 139 weeks of weather, 105 weeks of sea buoys
Zero imputation. Zero synthetic zero-fills. Every single record pinned by SHA-256.
Live verification & specs: offdiagonal.space 👀
offdiagonal retweeted
Three parts, one research loop:
@offdiagonal_ → dated forecasts, outcomes and traceable evidence.
Zeno → forecast combination and failure-risk learning.
Zeno30 → live forecasting and prospective tests.
solana:FMGe8RStdPc1YR59BBuV5Ui12DEe3Q2zVoihrJBbpump → economic and community layer
The aim: let resolved outcomes improve the next decision.
RFC 8785 parity & zero leakage
• 100% byte-for-byte fingerprint parity between Python (scripts/content_hash.py) and TypeScript via RFC 8785 canonical JSON.
• 3 failure labels separated: individuay miss, within-family collapse, and multi-family failure.
Inspect the inventory, audit receipts, and verification manifests: offdiagonal.space 💽
Macro & Energy: 857,536 paired records
• 857,536 national grid demand pairs (NESO UK & CAISO), with 325,058 provably pre-target.
• @ECB Survey of Professional Forecasters vintage captures locked with full v2 timestamp identities.
• 3,104 public health hub files (1,406 COVID, 1,372 @FluSight, 326 RSV) now bound to commit-level public availability timestamps.
Crypto Forecasters: @DeribitOfficial & @Kalshi ladders
• 247,944 crypto forecasts + 83,056 settlement observations across append-only quotes.
• History derived strictly from venue-stored candles at or before decision_at.
• Independent settlement indices per family: no cross-venue price smoothing, no synthetic zero-fills during illiquid ticks.
Prediction Markets: 674,741 bets & 13,151 question clocks
• 674,741 @Polymarket bets re-indexed with strictly prior timestamps to eliminate lookahead bias.
• Refactored wallet metrics into raw observable properties: bet size vs. prior traded volume, signed distance from tape price, and 1h post-fill impact (quarantined strictly as influence outcome, never input).
• 1,113 resolved multiple-choice questions audited: 639 pass single-winner eligibility; 410 multi-winner and 48 cancelled markets isolated.
Hard-Numbers
8,786 downloads on @huggingface and 260.9M audited forecast-outcome records.
We just froze v6.39 (commit 66b41c14).
Here are the exact numbers on what changed across crypto, prediction markets, and macro data: 🧵
Clean predictive data isn't about scraping everything. It's about cryptographic clocks, immutable SHA-256 manifests, & primary truth.
• 260M+ verified points
• 10.5M+ wallet trades
• Live pulse & audit log: offdiagonal.space
• Frozen v6.37 dataset on @huggingface
AI datasets brag about raw gigabytes. We brag about what we refuse to train on.
We’re holding out river flow cases & provisional flood models because their 3–7 day confidence intervals are too narrow for real calibration.
If data isn't independent, it doesn’t touch Zeno model.
In the live agent tournament:
• We locked down 1,101 real predictions
• 65 verified against primary source docs (Nobel Prize committee, FAA certifications, SEC filings—never web scrapes)
• 7 forecasts submitted afterthe answer was publicly known were instantly caught.