Skip to content
View Aurantium-47's full-sized avatar

Block or report Aurantium-47

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
Aurantium-47/README.md

Aurantium — an animated ASCII orange in warm amber light

Aurantium🍊

English · 简体中文

NLP · AI for Math · Crypto

Mathematics · Contributions

Python PyTorch Transformers Lean 4 / mathlib SymPy C++ TypeScript

Open source made new things possible for more people.

Mathematical research

Research index · Proofs, counterexamples & extensions

Two negative answers from the AIM problem list · 2004 / 2007 · Polynomial zeros

Questions dating back two decades ask whether polynomial transformations preserve properties of their zeros. AIM 23: a counterexample increases nonreal zeros from 4 to 6. AIM 34: from asking whether sufficiently large integer parameters work to ruling out every positive real parameter. Both include Lean sources, historical replay records and independent AI review. Background: Craven–Csordas · Chasse's dissertation

BRW graph polynomials: progress on a 1994 question · Canadian Journal of Mathematics · 1994 · Graph theory

When graphs are assembled, which polynomial-zero properties survive? A uniform result extends particular cycle lengths to every cycle length: replacing one cycle vertex with a graph satisfying the stated condition preserves the relevant real-rootedness property and permits further attachment along an edge. This covers a whole construction family, as a partial result toward the general conjecture.

Stack-sorting: a uniform proof draft for permutation counts · 2026 · Combinatorics

A proof draft explaining a stronger form of log-concavity in counts of permutations sharing a sorting output. This draft's Git commit: November 4. The proof and a comparison with related work by Colin Defant* are public.

* Colin Defant, Harvard postdoctoral fellow; Theorem 1.1 of his November 10 arXiv preprint gives the corresponding conclusion.

More mathematical work · Full index & verification materials

NLP & information retrieval

Dense & Hybrid Retrieval · Knowledge Graphs · Retrieval-Augmented QA

Research interests in retrieval and question answering over text–graph knowledge bases, focusing on complementary retrieval channels, relation-aware entity disambiguation, and coordination between retrieval and reranking.

Current work uses STaRK-MAG to explore how entity text, attributes and graph relations can jointly guide candidate selection under both semantic and relational constraints.

Research tools

Research-to-Decision — an agent workflow that turns research into a choice. Built on BMad Deep Recon and OpenInquire’s cross-platform reading, it clarifies requirements, compares evidence and trade-offs, and explains when to choose an alternative.

Contributions

Draft engineering · Sentence Transformers: synchronized per-dataset batches #4317

Align tasks across ranks while allowing task-specific per-rank batch sizes; preserve the training schedule across checkpoint resume. 18 real two-rank CPU/Gloo Trainer runs (6 configurations × full / prefix / resume) matched native-objective checks and continuous-versus-resumed trajectories in deterministic fixtures.

Not merged: its dependency Accelerate #4491 is currently closed and unmerged; upstream CI awaits maintainer approval.

Scheduling diagram, fixed evidence & limits

Synchronized task scheduling: group same-task rank slots before sharding, retaining task-specific per-rank batch sizes

Fixed reproduction evidence · 2 November 2026 includes rank traces, source hashes and JSON-only oracle replay. The 18 jobs were run in an independent validation environment, not upstream CI. The diagram illustrates scheduling, not measured throughput. Scope: fixed two-rank CPU/Gloo, ordinary map-style sampling and deterministic resume fixtures; no GPU/NCCL, arbitrary stochastic-resume or performance claim. AI-assisted implementation, tests and evidence review.

Selected merged contributions:

huggingface/tokenizers starsHugging Face Tokenizers · #2567 · merged
Rust · Tokenization
Fixed Kimi-K2 tokenization of special Han characters, restoring encoding consistency. The maintainer-reported regression was reviewed and merged.

HKUDS/LightRAG starsLightRAG · #4368 · merged
Python · PostgreSQL · pgvector
Fixed missing data after interrupted vector migrations. The maintainer extended the fix and verified duplicate-free migration of 30,000 vectors across two instances. Regression tests also earned maintainer credit and informed their merged fix for data-safe shutdown retries.

huggingface/sentence-transformers starsSentence Transformers · #4251 · #4262 · #4264 · #4284
Python · PyTorch · Semantic retrieval
4 merged fixes: corrected retrieval rankings and training negatives, restored reranker scoring, and kept empty results from aborting evaluation.

morluto/rea starsREA · #2422 · #2448 · #2429
TypeScript · Node.js · Reverse engineering
3 merged contributions: cross-platform path matching, binary diagnostics and installation guidance. The diagnostic fix was independently verified on Linux.

github/spec-kit starsSpec Kit · #4956
PowerShell · Python · Spec-driven development
Prevented plan files from being overwritten on Windows paths containing special characters. Verified on two PowerShell generations and merged.

More merged contributions

All projects · Merged contributions

Pinned Loading

  1. morluto/rea morluto/rea Public

    Reverse engineer anything with agents, from app behavior down to native binaries.

    TypeScript 466k 114k

  2. anomalyco/opencode anomalyco/opencode Public

    The open source coding agent.

    TypeScript 228k 30.9k

  3. ollama/ollama ollama/ollama Public

    Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    Go 187k 19.1k

  4. Comfy-Org/ComfyUI Comfy-Org/ComfyUI Public

    The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

    Python 147k 17.6k