Carbon Offset Claim Checker

How Review offset claim text works

Press Load model once: your browser downloads Gemma 3 1B instruction-tuned (web build) (728 MB) from this site and keeps it in its cache. Then add your text and press Check locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 3 1B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction also carries one worked example: the built-in sample with the answer the larger Gemma 4 E2B model gave for it. That example is what lets this smaller model follow the answer format reliably.

The instruction the model gets

You review a company's carbon offset or carbon-neutral claim. Separate what is claimed from the evidence the text actually gives, and list the questions a careful reader would ask: which emissions are covered, which registry or standard verifies the credits, whether reductions come before offsets, and whether the credits are avoidance or removal. Do not say whether the claim is legal or true, and do not name registries, standards or projects that the text does not mention.

What it returns

• What is claimed: Each claim in the text, quoted or closely paraphrased.
• Evidence given: Standards, registries, project types, figures or scopes the text actually mentions.
• Missing evidence: Information a reader would need that the text does not provide.
• Vague wording: Words such as 'neutral', 'net zero', 'offset' or 'verified' used without detail.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Offset claim: Our shipping is 100% carbon neutral because we buy verified rainforest credits equal to estimated annual package emissions.

What is claimed

Shipping is 100% carbon neutral

Evidence given

verified rainforest credits

Missing evidence

Do the reductions come before the offsets?

Vague wording

carbon neutral

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

You can switch models in the tool. Also available: Gemma 4 E2B instruction-tuned (web build) (2.0 GB). The larger language model gives more thorough answers but is a bigger download and needs a stronger device.

Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 4 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage climate and sustainability notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview