Delete Names Five Operations: Erasure Semantics for Derived Agent Memory, and Why a State-Level Definition Cannot Be the Auditable One
Abstract
Life of Research
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0.
Persistent memory has become a standard component of language-model agents, and with it a standard assumption: that where a fact lives in a retrievable store rather than in weights, erasing it is a solved problem, because a store supports deletion and weights do not. Agent memory does not hold the records that assumption presumes. It holds derivations - extracted facts, consolidated summaries, reflections, learned procedures, and edits made to earlier entries because a later one arrived - and deleting a source does not remove what was derived from it. This paper separates the operations that the single word delete is used for in this literature: removing the stored item, withdrawing everything derived from it, barring it from supporting an outgoing claim, making the fact non-inferable from what remains, and restoring the store to the state that would have obtained had the item never been written. Three systems published in 2026 supply a semantics for one of these each, and they are not the same semantics. The paper argues that the second is the database view-deletion problem, which has a known structure - no unique source update, and two inequivalent minimality objectives - that the agent-memory literature is rediscovering without the vocabulary; that the fourth is not a property of a record at all, and that deletion is itself an inference signal; and that the fifth is not defined for LLM-mediated consolidation, because the same trajectories are reported to yield different memories under different update schedules. The parametric unlearning literature reached the parallel conclusion in 2021, that only an algorithmic-level definition is auditable. What is not known is stated flatly: no work located for this paper reports what fraction of a production memory store's entries carry a recoverable derivation link to their sources. Six measurements are specified.
Questions about this paper
Who wrote "Delete Names Five Operations"?
Pranay Mahendrakar wrote "Delete Names Five Operations: Erasure Semantics for Derived Agent Memory, and Why a State-Level Definition Cannot Be the Auditable One", published 6 Sep 2026. Pranay Mahendrakar is an Indian AI specialist and LLM engineer based in Bengaluru, India. He is the Managing Director of SonyTech, Nodal Coordinator at IIRS-ISRO, and an instructor at Tutorials Point. His work covers large language models, natural language processing, computer vision and retrieval-augmented generation. He publishes open-access research papers and is the author of three books: Just AI With Pranay, Multiverse of AI and It's Me LLM.
Is "Delete Names Five Operations" free to read?
Yes. "Delete Names Five Operations" by Pranay Mahendrakar is open access under a Creative Commons Attribution 4.0 licence, with the full PDF available from Zenodo at https://doi.org/10.5281/zenodo.23022338. There is no paywall and no account required.
How do I cite "Delete Names Five Operations"?
Cite the DOI: Mahendrakar, P. (2026). Delete Names Five Operations: Erasure Semantics for Derived Agent Memory, and Why a State-Level Definition Cannot Be the Auditable One. Zenodo. https://doi.org/10.5281/zenodo.23022338 A BibTeX entry is provided on this page.