Skip to content
View hiroki-tamba-research's full-sized avatar
1 follower · 13 following

Achievements

Achievement: Pair Extraordinaire

Achievements

Achievement: Pair Extraordinaire

Block or report hiroki-tamba-research

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hiroki-tamba-research/README.md

Hiroki Tamba | 丹波大樹

Independent researcher — AI evaluation infrastructure, narrative intelligence, LLM grader reliability.

Recent contributions

ORCID: 0009-0004-7635-0741 · OSF

arXiv endorsement

Seeking endorsement for a cs.AI submission on LLM-as-judge grader non-determinism. Code: V6FVHF

How arXiv endorsement works

Popular repositories Loading

  1. japan-cannabis-act-its japan-cannabis-act-its Public

    Pre-registered interrupted time series analysis of drug enforcement patterns following Japan's December 2023 Cannabis Control Act amendment. OSF Registration: https://doi.org/10.17605/OSF.IO/S5JAQ

    R

  2. saluscope saluscope Public

    Multi-source health & development data explorer via open APIs. Extensible to any indicator.

    HTML

  3. strategic-narrative-terminal strategic-narrative-terminal Public

    Realtime geopolitical narrative monitoring interface.

  4. llm-judge-nondeterminism llm-judge-nondeterminism Public

    Empirical reproducibility note: non-determinism in LLM-as-judge graders (generalized from Japan-AISI/aisev #25)

    Python

  5. inspect_ai inspect_ai Public

    Forked from UKGovernmentBEIS/inspect_ai

    Inspect: A framework for large language model evaluations

    Python

  6. tlim-signet tlim-signet Public

    Creator-held defensive provenance — a proof of concept (TLIM research program). Open-core.

    Python