The Continuity Layer
Glossary · a term in the AI continuity field

Erasure ladder

thecontinuitylayer.com/glossary/erasure-ladder

The definition

This site's ordering of the twelve operations the word “forget” is used for, from correcting a wrong record to verifying that a deleted one no longer shapes behavior: correct, update, expire, revoke access, delete the record, remove derived memories, purge indexes and embeddings, cryptographic erasure, machine unlearning, verify unrecoverable, verify it stays gone, verify non-influence. No rung implies the ones above it.

The same words the glossary hub and the public data mirror carry; this page is the stable address for the term.

  • Erasure

    Authorized deletion of stored memory: honoring a deletion request, making sure the removed fact stops influencing answers, and being able to show it is gone.…

  • Continuity Framework

    This site's framework (v2.0, November 2026) for judging whether a system has continuity: five obligations a continuity layer owes the people and systems that…

  • Retention policy

    A rule that ends a fact's validity, or removes it, on a schedule or on an event, without anyone asking. Expiry is a policy; the record may still exist until…

  • Deletion receipt

    A signed, checkable statement that a deletion was carried out: what was removed, when, to which rung of the erasure ladder, and under which key or policy.…

  • Ghost vectors

    Embeddings that a vector database marked deleted but kept on disk. In 2026 tests, flagged vectors read from ChromaDB, FAISS and Weaviate storage files were…

  • Cryptographic erasure

    Encrypting each item or subject under its own key and deleting by destroying the key, so retained ciphertext, including backups, cannot be read. The…

  • Access-control erasure

    Withdrawing a record from everyone who could read it while the operator keeps the data and could still decrypt it. The IETF SAIHM draft requires operators to…

  • Machine unlearning

    Removing the influence of specific training data from a model's parameters so the model is approximately what retraining without that data would produce.…

Where it shows up on this site

Keep reading

The working definition of a continuity layer, in full, is at /what-is-a-continuity-layer. Every term, on one page, at /glossary.