Pith. sign in

Attribot: A bag of tricks for efficiently approximating leave-one-out context attribution

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.GT 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

In-Context Credit Assignment via the Core

cs.GT · 2026-05-07 · unverdicted · novelty 7.0

Algorithms based on the least core approximate stable credit assignments for AI-generated content using orders of magnitude fewer LLM calls than alternatives.

citing papers explorer

Showing 2 of 2 citing papers.

  • In-Context Credit Assignment via the Core cs.GT · 2026-05-07 · unverdicted · none · ref 24

    Algorithms based on the least core approximate stable credit assignments for AI-generated content using orders of magnitude fewer LLM calls than alternatives.

  • RREDCoT: Segment-Level Reward Redistribution for Reasoning Models cs.LG · 2026-06-04 · unverdicted · none · ref 139

    RREDCoT approximates segment-level reward redistribution for CoT traces by querying the model itself, offering a lower-cost alternative to Monte Carlo credit assignment in reasoning-model RL.