Paper

Information from coincidences

Unreadunread

AI summary

arXiv:2606. 25042v1 Announce Type: cross Abstract: We prove a single algebraic mixed coincidence identity that unifies a broad swath of information-theoretic variational results.

Reading status

Priority

About this paper

Authors: Akshay Balsubramani
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because Information from coincidences overlaps with clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt searches split between the alignment objective and the distributional objective, and both discretizations of the soft prefix collapse (MODERATE confidence)". Matching terms: class, alpha, token, rate, length, position, test, language. Source: arxiv stat.ML (Machine Learning).
arXiv: 2606.25042

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Information from coincidences. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.