Live operational scope, April 2026

The method demonstrated on public and proprietary data.

Every calibrated threshold Invarians uses in the live panel is derivable from public BigQuery datasets or from open collector schemas. Full pipeline published: extraction query, calibration script, expected output.

Invarians captures strictly physical metrics from L1 chains, rollups and native bridges, substrate signals on structure and on demand. Narrative and economic metrics (gas price, token price, TVL) are excluded by design.
A nominal is computed per chain, divergences from that nominal are detected against a published calibration, and the result is exposed as a signed attestation to AI agents. Agents gain structural awareness of the chains they operate on and can schedule execution inside the most nominal windows to secure their transactions. Invarians is focused on RWA and institutional workflows, not daily trading.

View operational scope → How to reproduce

01: The reproducibility problem

A signed attestation is only as trustworthy as the pipeline that produced it.

Any closed signal infrastructure eventually asks for trust on faith. Methodology without runnable pipeline, published numbers without public data source, live service without cross-check path. Evidence replaces all three with a single commitment: anything in the live panel is reproducible end to end by a third party on public data.

Risk 1

Methodology without runnable pipeline

A document that claims thresholds but cannot be executed. A third party has no way to confirm the numbers came from the method described.

Risk 2

Thresholds without public data source

Numbers published on proprietary extractions. The reader is asked to trust the extraction as well as the calibration. No independent falsifiability.

Risk 3

Live panel without cross-check path

Signed attestations are verifiable against the signer, but the parameters embedded in the signer become a black box. Closed stack under HMAC.

The answer

End to end pipeline on public data

Extraction query on a public dataset, open calibration script, published expected output. Anyone can re-run the pipeline and confront the numbers served by the live panel. That is what this page packages.

02: Live operational scope

Two scopes, all fully reproducible.

Exactly what is calibrated, functional today, and backed by a runnable reproduction kit. No overclaim, no roadmap dressed as evidence.

Ethereum L1 regime

● Certified, HIGH confidence

✓ tau structural, M1 = 5.07 ✓ pi demand ✓ Public BigQuery, crypto_ethereum ✓ 34 697 windows, 2020 to 2024 ✓ TPR 100 percent on 4 canonical events ✓ FPR tau + pi = 1.23 percent

Open reproduction kit →

Native bridges, ARB / BASE / OP

● Calibrated, HIGH confidence

✓ BS1 / BS2 state classification ✓ P97 over 30 days per chain ✓ n = 3968 samples per chain ✓ days span = 28.85 to 28.89 ✓ Guard rails pass on all three chains ✓ Thresholds committed 2026-04-22

Open reproduction kit →

Public data only No proprietary extraction Updated 2026-04-22 · M1 = metric stability score. Bridge thresholds committed 2026-04-22 on P97 over 30 days, per chain.

03: Proof

30 days of calibrated operational context, hour by hour.

Invarians has been running a continuous nominal on Ethereum L1, three L2 rollups (Arbitrum, Base, Optimism) and their native bridges since March 2026. Every hour is classified into a regime on substrate metrics alone. The timeline below shows the last 721 hours as Invarians would have exposed them to an autonomous agent operating in this stack. No gas prices, no fee markets, no token prices, substrate only.

Timeline of 30 days, hourly states for ETH L1, three L2 rollups and three native bridges

Three moments from this window, exactly as Invarians surfaced them.

★ 2026-03-29 15:00 UTC

Composite signal on Ethereum and Arbitrum.

Ethereum L1 flipped to S1D2 (demand elevated) the same hour Arbitrum native bridge entered BS2 (degraded). An RWA agent routing through Arbitrum would have seen both signals in one context window.

★ 2026-04-03 02:00 to 07:00 UTC

Optimism bridge degraded five hours over one day.

Invarians exposed BS2 continuously on the OP native bridge. Ethereum L1 stayed S1D1 throughout. A pure L1-aware agent would have missed this window entirely.

★ 2026-04-10 07:00 UTC

Base and Optimism both in S2D1 simultaneously.

Substrate anomaly on Base and Optimism at the same hour while Ethereum L1 stayed nominal. An L1-only execution context would not have surfaced this at all.

These are the windows an RWA agent cares about. Invarians surfaced them at the hour they happened, signed under HMAC, and served through a single call: get_execution_context(from, to, bridge).

04: How to reproduce

Five steps, same pipeline Invarians runs internally.

The reproduction path is identical across the two scopes, only the source differs. For Ethereum L1, the source is BigQuery public data. For the native bridges, the source is live RPC captured by an open collector.

Pick a scope

Ethereum L1 regime, or native bridges Arbitrum, Base, Optimism. Each has its own folder under Data with a self-contained README.

Pull the data

For Ethereum, open BigQuery console, paste the extract SQL (extract_eth.sql), run, export CSV. For bridges, either run the open collector for at least 25 days against the three L2 RPCs or load a provided sample into Postgres.

Run the calibration

For Ethereum, run python backtest_eth.py. The script lives in the calibration repository and takes the exported CSV as input. For bridges, execute calibrate_native_p97_30d.sql as a transaction on the Postgres instance holding the signals.

Read the output

Ethereum produces a backtest_results CSV with per-window classification S1D1 to S2D2 and aggregate TPR / FPR. Bridges produce a BEFORE / COMPUTED / AFTER audit showing the P97 thresholds applied per chain.

Confront to expected_thresholds.md

Each scope folder holds an expected_thresholds.md listing the exact numbers the live panel uses. Match within numerical noise confirms the pipeline. Divergence beyond noise is a published falsification, which is the intended use of this kit.

Every Invarians attestation carries calibration: { version, methodology_hash } in its payload. The methodology hash points to the published method that produced the thresholds. Evidence is the path to re-derive those thresholds independently, with no credentials required for the Ethereum scope.

05: Out of scope, in archive

What is not on this page, and where to find it.

Invarians' methodology work is broader than the current live panel. To keep evidence strictly aligned with the operational scope, chains and bridges not yet served in the live panel are not shown here. They remain public in the calibration archive.

This page

Live operational evidence

Ethereum L1 regime and native bridges Arbitrum, Base, Optimism. Calibrated, functional, and reproducible end to end on public data. Anything claimed here is runnable against the live service.

Reintegrating 2026-05-16

Polygon L1 regime

Chain backtest certified MEDIUM (M1 tau = 12.60, M1 pi = 3.59, TPR 100 percent on 4 events at Phi = 720, FPR documented 14.57 percent). Polygon PoS Bridge collector started 2026-04-23 on Ethereum L1 RootChainProxy, requires 25 days of continuous samples before P97 / 30d calibration. Evidence card returns to the scope grid once polygon_pos-ethereum/native commits calibrated:true.

In archive

Methodology validation

Solana backtest (proxy v1 for sigma, tx_count unavailable, partial). Avalanche calibration pending (M1 insufficient). CCIP lanes and CCTP routes captured raw with calibrated:false, classifications earliest 2026-05-20. All documented at the calibration repository.

Archive reference : github.com/agentnorthstar/calibration. Methodology section 4.4 lists the per-chain parameters, section 12 (signal taxonomy) documents what is strictly excluded by design (narrative and economic metrics).

The method demonstrated on public and proprietary data.

A signed attestation is only as trustworthy as the pipeline that produced it.

Two scopes, all fully reproducible.

30 days of calibrated operational context, hour by hour.

Five steps, same pipeline Invarians runs internally.

What is not on this page, and where to find it.

Three documents, all canonical sources.

Run the pipeline.
Publish falsifications.

The method demonstrated on public and proprietary data.

A signed attestation is only as trustworthy as the pipeline that produced it.

Two scopes, all fully reproducible.

30 days of calibrated operational context, hour by hour.

Five steps, same pipeline Invarians runs internally.

What is not on this page, and where to find it.

Three documents, all canonical sources.

Run the pipeline.Publish falsifications.

Run the pipeline.
Publish falsifications.