○MODEL CARD — CLEAN · NO TAMPERING DETECTED
Bellatrix-Tiny-1B-v3
A known-clean model, correctly not flagged — it reads below the detection boundary. The detector fires on the safety-removal class, not on “something changed.”
Nothing to disclose, nothing to detect — the abstain is the entry.
No safety behavior to strip — so no finding is manufactured. The honest blank is what makes every catch on the record mean something.
No refusal rate to read — the subject is a base model.
○THE FULL RECORD
The record behind the read.
Everything the read is built on — the provenance, the claims, the evidence, the signed attestation. Depth, not a second telling: pick a tab.
○ HONEST SCOPE
What this card does not claim.
The misses are part of the card, not an appendix. Every catch above sits next to what could not be proven — and it never renders folded away.
COVERAGE — 3 architecture families (Qwen2, Llama, Gemma-2) · 6 vendors · public safetensors releases 0.5B–9B · mechanism-proven with benign + adversarial controls · 40 models graded (15 caught, 25 clean), 0 false positives · full-tier restore certified to the reference safety floor at the smaller sizes, reversible fp32-exact weight round-trip at the largest · CURATED-SET record, not a wild-population precision/recall estimate · live-scale batteries staged.
Excise starts from a proven finding. No finding, no patch. Fail closed.
On-ramps: the deepest read, signed OPEN NOW, the full atlas, how this read scores against the open-source scanners, and why it’s called Protora.
◐SEEN WHOLE
One model, two lenses.
The same public model, read from both ends. Protora answers what was done to it — its integrity. Ardora, a sibling Vulcora tool, reads what it is — its disposition. Two questions, one artifact, joined on the public HuggingFace id.
CLEAN · NO TAMPERING DETECTED
Correctly not flagged — reads below the detection boundary.
the full finding ↓- instruction-following / assistant registermedium confidencepresent — an instruction-tuned register on top of the Llama instruct base
- refusal registerhigh confidencepermissive — complies with the majority of the harmful probe battery — and over-refuses a minority of benign controls (a somewhat over-broad refusal disposition; described, not judged)
- instruction-following registerhigh confidencelargely ignores explicit format instructions
- verbositymedium confidencemoderate verbosity
- coherencehigh confidencecoherent — sustained, non-repetitive text
- code-shaped-output dispositionhigh confidencecompletes code prompts with code-shaped output
What a finetune changed · clearAn instruction-tuned register relative to the Llama instruct base; the change reads clearly and the refusal disposition reads retained.
Ardora — what is this? →Two tools, two questions about one public model — never merged into a single verdict. The disposition read is the sibling tool’s; the integrity finding is Protora’s.
Run it on the model
you can’t vouch for.
This card started as a model someone downloaded and trusted. Bring yours — Protora will tell you what it did, prove it with a replayable witness, and tell you plainly what it couldn’t prove.
Every engagement is scoped per case and quoted per offer — tell us what you need, and we’ll scope it and send you an offer.