ReadOnce: I wanted less rereading, so I kept the model's mistake visible

Описание и применение

ReadOnce – веб‑приложение, сравнивающее старые и новые заметки, выявляющее возможные повторения с помощью эмбеддингов и лексических фильтров, сохраняя исходный текст.

Задача

Users need to detect repeated or paraphrased content in new notes without losing the original text or relying on external APIs.

Результат

In 4/4 calibration and 12/12 held‑out synthetic cases, ReadOnce matched expectations, outperforming an exact‑only baseline (0/4 and 10/12). One role‑swap miss was documented and retained for transparency.

Рабочий процесс

• Load current and earlier notes into the two input boxes
• The app tokenizes each note and generates 384‑dimensional vectors via Xenova/all-MiniLM-L6-v2
• Compute cosine similarity between each current note and all earlier notes
• Apply lexical guards (quantity, date, negation, status words, uppercase identifiers) to filter false positives
• Flag notes with cosine ≥0.82, runner‑up gap ≥0.06, and equal protected lexical facts as "possible repeat"
• Render all current notes with reference links and reasons
• Export audit JSON containing original text, references, scores, reasons, settings and timings

Доказательства

ReadOnce takes a smaller job: compare an earlier set of notes with a current one and suggest which lines might repeat earlier meaning. It keeps every current line, its earlier reference, the actual model score and a reason. Nothing is deleted or rewritten.

Источник

The final actual browser-model run matched the authored expectations in 4/4 calibration cases and 12/12 held-out cases.

Источник

The matching rule is deliberately visible: cosine at least 0.82, a best-versus-runner-up gap of at least 0.06, and equal protected lexical facts.

Источник