Citable, permanent evidence

The dataset, archived off-network

The live chain is the real evidence -- this page exists so it can also be cited. Every confirmed block, the exact hit it triaged, and the exact classifier model that scored it, deposited periodically on Zenodo with a permanent DOI. Once published, a snapshot can never be silently altered -- that's a feature for citation, not a limitation.

Latest snapshot

Pulled live from Zenodo's own record for this deposit -- never hand-typed here, so it can't go stale.

Loading the latest deposit record from Zenodo…

How to independently verify a row

No step here requires trusting Galaxy SIGNAL -- each one is checkable against a source this project doesn't control.

  1. Re-score it. Load rfi_classifier.joblib from the deposit with scikit-learn, feed it a row's own frequency/drift-rate/SNR (and whether the frequency falls in a known-crowded band), and confirm it reproduces that row's verification_score.
  2. Check the block. block_hash is independently verifiable against the live network's own /chain endpoint, or any full node's own copy -- see the whitepaper for the block-hash construction.
  3. Check the hit is real. hit_file_pos is the hit's exact row position in the original, public Breakthrough Listen survey CSV -- anyone with a copy of that source dataset can confirm the row genuinely exists, not fabricated.

What this is not

Not a discovery claim. This archives the network's actual, checkable output -- which hits the classifier accepted, when, and under which exact model -- as an immutable, timestamped record. It is not a claim that any of these detections is a technosignature; see the whitepaper's own "what this is not" section for why.