Gemma added a generation that never lived. My code turned it into a ghost.

说明与用途

该系统使用Gemma 4 12B从录音中提取家谱关系，并通过对原始音频的逐句验证，防止出现虚构亲属。

问题

A family tree built from recorded oral histories can contain invented relatives if the model’s output is not verified against the source audio.

结果

On 60 test families, Gemma 4 12B produced 85.5 % correct links before verification; the verification step caught all 118 wrong links, yielding 100 % correct verified links.

工作流

• Record audio of a family story
• Transcribe with faster‑whisper
• Run Gemma 4 via Ollama on the transcript to generate JSON claims
• Verify each claim with shezhire/verify.py: check name presence, quote match, person naming, kinship word, and additional rules
• Draw verified links in ink, ghost links dashed in red, and output a single HTML page
• Optionally test on synthetic families to tune rules

证据

Gemma 4 12B read it and answered, confidently, with a quote: "Сәкен is the grandfather of Данияр."

来源

On 60 test families, Gemma 4 12B got 85.5% of its links right. Every one of the 118 wrong links was caught, so 100% of what reached the page was right.

来源

The check asks four questions: Is this person in the recording at all? Is the quote really there? Are both people in that sentence? Is there a kinship word of the right kind?

来源