Turrii verification record
The simple answer is that it must have been typed by a human on a keyboard. That sounds straight forward, but there are quite a few uncertain cases. How does copy pasting work? How do quotes, and editing work? What about text typed on different websites, and then signed? What about spelling and grammar help? It is a complex process, but we've attempted to standardize the rules. 1) All properly quote text is not considered. Quotations are the original way to show you didn't write something. By using them the author is communicating to the reader that the did not write this text. We follow the same conventions. 2) Copy pasting outside text is not allowed. Turrii is unable to verify the authenticity of pasted text, and therefore considers it to be Not Human. The only exception is for editing within the current text. Copying or moving text around the document is legitimate, and we'll pull the evidence along with the text. 3) Text can contain some portion of auto-correct, grammar, and spelling fixes. We know that writing by hand is a lot harder (but I'd say a lot more rewarding), then using AI. I know I still personally need considerable grammar, and spelling help. As long as about 80% or more is human typing evidence it will be labeled as human. Pay attention to the indicator at the bottom to see what your current text is labeled as. The indicator uses the same algorithm as signing. 4) Text written across multiple time periods and different websites can be used in verification of a single text. We know the writing process isn't linear. Some people take hours, others take days. Some people stick with one website/app, others use multiple. As long as you are typing with the Turrii extension turned on, we can use that evidence. All the evidence is stored on your browser until it's needed. The only exception is text typed straight into our website in the Write tab. That is considered a single writing session, and does not pull in additional evidence. 5) We do not allow editing of text after signing. Every text signing ID always maps to the same piece of text. The author is never allowed to edit the text once signed. This increases trust, and stops any rug pulls. The only way to change text is to create a new signed text continuing from the previous one, and that will generate a new ID. 6) The indicator always indicates the up to date verification status. As you're typing on the Write page, or in the sidebar we are continuously running your evidence through our algorithm. If you notice your text gets marked as Not Human while editing, that's okay, you can still fix it. Use the notes to see which sections have been flagged and you can work to update them. Or if you needed to paste in some content, you can keep adding human text to get back above that 80% line. Once less than 20% of your text is Not Human, it'll flip back over to Human. Think we missed something? Please reach out and let us know. We're always looking to improve our algorithm.
Ready to get started?
Download the free plugin, verify your own writing and help rebuild a feed where real thought wins.
02 / How it works
Levels of evidence
Higher levels of app integration increase our technology's confidence that a human wrote the text.
Keystroke timing was captured by the Chrome extension as the author typed, then analyzed against human capability thresholds to verify a natural writing rhythm.
- Chrome extension keystroke capture
- In-platform composition verified
- Human-like typing analysis
Why this score
- The number
- 75 out of 100. Each level has its own band: this text is at the chrome extension level, which runs 63 to 79.
- Where the typing came from
- Captured in the browser, keystroke by keystroke, as the text was typed.
- What held it here
- Typing was recorded in the browser. Browser-only evidence tops out at 79; higher scores need the desktop app's hardware keystroke check.
- What would raise it
- Running the desktop app while typing adds a hardware keystroke check and can lift a text to the desktop app level (80 to 89).
Confidence
How confident is this verification?
The confidence score is derived from analyzing keystroke timing, rhythm, and cadence as you type. Our algorithm compares your typing patterns against known human and machine behaviors to score how likely the text was created by a human at a keyboard.
75/ 100
Notes
- Pasted content was detected. Pasted text cannot be verified as human-typed and lowers the overall confidence.
- Typing rhythm is consistent with human input.
The “Typing evidence” view on the letter above marks each part of the text by how it was written, and the play button replays the typing as it happened. Here is the same thing as totals.
- Typed 100% Typed key by key with a human rhythm.
The typing engine scores the timing of every recorded keystroke. It looks at the signals below together; no single one decides the verdict. The exact measurements stay private so the check is hard to game.
- Typing speed
- How fast the text was typed, overall and in short bursts. People speed up and slow down; a script tends not to.
- Gaps between keys
- The pauses from one key to the next. Fingers have a floor; replayed or injected text often does not.
- Rhythm
- How uneven and unpredictable the rhythm is. Real typing is bumpy; machine typing is suspiciously even.
- Key presses
- How long keys stay pressed and how the fingers travel between them, when the recorder sees both key down and key up.
- Thinking pauses
- The longer pauses people take to think between phrases.
- Edits and fixes
- Deleting and rewriting. People revise as they write; pasted or generated text usually arrives finished.
Taken together, these signals read as a person typing at a keyboard.
The server signed a hash of this exact text together with its tier and author. Anyone can check the signature against the public key below. If a single character of the text changed, the content hash would not match.
Record ID
2f17b8e1-1b2b-4e2e-8bfe-f9be191617e1
Author ID
204b7374-2d81-4563-a037-9dbd8fe6fd1b
Content hash
ouVid5pA8BAqJAm-NMaZ2PDLD0KQsXROCp_zCMzFPUI
Signature
gK7uz_awRdtSv5xW19E4-5wP6vIXItmMDJNqdlITCIlY-1Bg-7dR3mCW_cWJsvZqCO0t0FW4UKXz8VZX4vkkCg
Key ID
prod-ed25519-001
Algorithm
ed25519
Public key
jJa5XbW6SEMK-N98a2ikV_gEuV0xrJJUoSgw8e-h6ls
Version
3
Signed at
Nov 16, 2026, 12:19 AM UTC
Canonical payload
{"version":3,"id":"2f17b8e1-1b2b-4e2e-8bfe-f9be191617e1","author_id":"204b7374-2d81-4563-a037-9dbd8fe6fd1b","tier":1,"verify_code":"SG6PLQDK","content_hash":"ouVid5pA8BAqJAm-NMaZ2PDLD0KQsXROCp_zCMzFPUI","key_id":"prod-ed25519-001","algorithm":"ed25519","created_at":"2026-11-16T00:19:23.924621Z","tier_code":"V1","author_identity_verified":true,"author_identity_verified_at":"2026-06-01T00:05:46.686927Z"}Start your own
Ready to get started?
Download the free plugin, verify your own writing and help rebuild a feed where real thought wins.
Start now