allaun/Research-Stack
1
0
Fork 0
mirror of https://github.com/allaunthefox/Research-Stack.git synced 2026-07-31 03:05:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Research-Stack/6-Documentation/docs/provenance/LANGUAGE_MATH_MODEL_SOURCES.cff
Brandon Schneider de631bf1b7 WIP: accumulated changes
2026-05-25 16:24:21 -05:00

505 lines
21 KiB
Text
Raw Blame History

cff-version: 1.2.0
message: "If you use the language-math model papers or genetic framework probes, cite the appropriate peer-reviewed or arXiv sources below."
type: dataset
title: "Language, Mathematics, Genetics, and Information Theory Paper Sources"
authors:
- name: "Research Stack Contributors"
date-released: 2026-05-22
url: "https://github.com/allaunthefox/Research-Stack"
repository-code: "https://github.com/allaunthefox/Research-Stack"
license: Apache-2.0
# ─────────────────────────────────────────────────────────────────────────────
# Expanded Genetic Alphabet / Synthetic DNA
# ─────────────────────────────────────────────────────────────────────────────
references:
- type: article
title: "Hachimoji DNA and RNA: A genetic system with eight building blocks"
authors:
- family-names: "Hoshika"
given-names: "Shuichi"
- family-names: "Leal"
given-names: "Nicole A."
- family-names: "Kim"
given-names: "Myong-Jung"
- family-names: "Kim"
given-names: "Myong-Sang"
- family-names: "Karalkar"
given-names: "Nilesh B."
- family-names: "Kim"
given-names: "Hyo-Joong"
- family-names: "Bates"
given-names: "Alison M."
- family-names: "Watkins Jr."
given-names: "Norman E."
- family-names: "SantaLucia"
given-names: "Holly A."
- family-names: "Meyer"
given-names: "Adam J."
- family-names: "DasGupta"
given-names: "Saurja"
- family-names: "Piccirilli"
given-names: "Joseph A."
- family-names: "Ellington"
given-names: "Andrew D."
- family-names: "SantaLucia Jr."
given-names: "John"
- family-names: "Georgiadis"
given-names: "Millie M."
- family-names: "Benner"
given-names: "Steven A."
journal: "Science"
volume: "363"
issue: "6429"
pages: "884-887"
date-published: 2019-02-22
doi: "10.1126/science.aat0971"
url: "https://www.science.org/doi/10.1126/science.aat0971"
notes: "Demonstrated 8-base synthetic DNA (hachimoji) with 3 bits/base. Formalized in ExpandedGeneticAlphabetProbe.lean."
- type: article
title: "Enzymatic synthesis and nanopore sequencing of 12-letter supernumerary DNA"
authors:
- family-names: "Kawabe"
given-names: "Hinako"
- family-names: "Thomas"
given-names: "Carter A."
- family-names: "Hoshika"
given-names: "Shuichi"
- family-names: "others"
journal: "Nature Communications"
volume: "14"
pages: "6820"
date-published: 2023-10-26
doi: "10.1038/s41467-023-42406-z"
url: "https://www.nature.com/articles/s41467-023-42406-z"
notes: "Demonstrated 12-letter supernumerary DNA as canonical structural maximum. Formalized in ExpandedGeneticAlphabetProbe.lean."
# ─────────────────────────────────────────────────────────────────────────────
# Genetic Code Optimality
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "The genetic code is one in a million"
authors:
- family-names: "Freeland"
given-names: "Stephen J."
- family-names: "Hurst"
given-names: "Laurence D."
journal: "Journal of Molecular Evolution"
volume: "47"
issue: "3"
pages: "238-248"
date-published: 1998
doi: "10.1007/PL00006381"
url: "https://link.springer.com/article/10.1007/PL00006381"
notes: "Standard genetic code is ~10^6 times better than random at error minimization. Referenced in GenomeGeodesic_PriorResearch.md."
# ─────────────────────────────────────────────────────────────────────────────
# DNA Information Storage
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Next-generation digital information storage in DNA"
authors:
- family-names: "Church"
given-names: "George M."
- family-names: "Gao"
given-names: "Yuan"
- family-names: "Kosuri"
given-names: "Sriram"
journal: "Science"
volume: "337"
issue: "6102"
pages: "1628"
date-published: 2012
doi: "10.1126/science.1226355"
url: "https://www.science.org/doi/10.1126/science.1226355"
notes: "Encoded 5.27-megabit book in DNA. Referenced in GenomeGeodesic_PriorResearch.md."
- type: article
title: "Towards practical, high-capacity, low-maintenance information storage in synthesized DNA"
authors:
- family-names: "Goldman"
given-names: "Nick"
- family-names: "Bertone"
given-names: "Paul"
- family-names: "Chen"
given-names: "Siyuan"
- family-names: "Dessimoz"
given-names: "Christophe"
- family-names: "Leproust"
given-names: "Emily M."
- family-names: "Sipos"
given-names: "Botond"
- family-names: "Birney"
given-names: "Ewan"
journal: "Nature"
volume: "494"
issue: "7435"
pages: "77-80"
date-published: 2013
doi: "10.1038/nature11875"
url: "https://www.nature.com/articles/nature11875"
notes: "739 KB files encoded in DNA with 100% reconstruction accuracy. Referenced in GenomeGeodesic_PriorResearch.md."
# ─────────────────────────────────────────────────────────────────────────────
# Information Theory & Bottleneck
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Deep Learning and the Information Bottleneck Principle"
authors:
- family-names: "Tishby"
given-names: "Naftali"
- family-names: "Zaslavsky"
given-names: "Noga"
conference:
name: "IEEE Information Theory Workshop (ITW)"
date-published: 2015
doi: "10.1109/ITW.2015.7133169"
url: "https://arxiv.org/abs/1503.02406"
notes: "Information bottleneck principle applied to deep neural networks. Referenced in framework documentation."
- type: article
title: "Algorithmic Information Theory"
authors:
- family-names: "Grunwald"
given-names: "Peter D."
- family-names: "Vitanyi"
given-names: "Paul M. B."
booktitle: "Philosophy of Information"
publisher: "Elsevier North-Holland"
pages: "281-317"
date-published: 2008
doi: "10.1016/B978-0-444-51726-5.50013-3"
url: "https://doi.org/10.1016/B978-0-444-51726-5.50013-3"
notes: "Comprehensive tutorial on Kolmogorov complexity and algorithmic information theory."
# ─────────────────────────────────────────────────────────────────────────────
# Compression & Entropy Coding
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding"
authors:
- family-names: "Duda"
given-names: "Jarek"
journal: "Journal of Universal Computer Science"
volume: "23"
issue: "12"
pages: "1112-1130"
date-published: 2017
doi: "10.48550/arXiv.1311.2540"
url: "https://arxiv.org/abs/1311.2540"
notes: "ANS: single-state entropy coding alternative to AC. Arxiv preprint; later published in J.UCS."
- type: article
title: "Compression Optimality of Asymmetric Numeral Systems"
authors:
- family-names: "Pieprzyk"
given-names: "Josef"
- family-names: "Duda"
given-names: "Jarek"
- family-names: "Pawlowski"
given-names: "Marcin"
- family-names: "Camtepe"
given-names: "Seyit"
- family-names: "Mahboubi"
given-names: "Arash"
- family-names: "Morawiecki"
given-names: "Pawel"
journal: "Entropy"
volume: "25"
issue: "4"
pages: "672"
date-published: 2023
doi: "10.3390/e25040672"
url: "https://doi.org/10.3390/e25040672"
notes: "Proves ANS optimality for distributions described by natural powers of 1/2."
# ─────────────────────────────────────────────────────────────────────────────
# Grammar Induction & Syntax
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Compound Probabilistic Context-Free Grammars for Grammar Induction"
authors:
- family-names: "Kim"
given-names: "Yoon"
- family-names: "Dyer"
given-names: "Chris"
- family-names: "Rush"
given-names: "Alexander M."
conference:
name: "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL)"
pages: "2369-2385"
date-published: 2019
doi: "10.18653/v1/P19-1228"
url: "https://aclanthology.org/P19-1228/"
notes: "Compound PCFG with per-sentence latent variables for grammar induction."
- type: article
title: "Unsupervised Grammar Induction in a Framework of Information Compression by Multiple Alignment, Unification and Search"
authors:
- family-names: "Wolff"
given-names: "J. Gerard"
conference:
name: "ECML/PKDD 2003 Workshop on Learning Context-Free Grammars"
pages: "113-124"
date-published: 2003
doi: "10.48550/arXiv.cs/0311045"
url: "https://arxiv.org/abs/cs/0311045"
notes: "SP70 model of ICMAUS framework for unsupervised grammar learning."
# ─────────────────────────────────────────────────────────────────────────────
# Minimum Description Length
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Minimum Description Length Revisited"
authors:
- family-names: "Grunwald"
given-names: "Peter"
- family-names: "Roos"
given-names: "Teemu"
journal: "International Journal of Mathematics for Industry"
volume: "11"
issue: "1"
pages: "1930001"
date-published: 2020
doi: "10.1142/S2661335219300018"
url: "https://doi.org/10.1142/S2661335219300018"
notes: "Updated overview of MDL principle since 2007."
- type: article
title: "A Tutorial Introduction to the Minimum Description Length Principle"
authors:
- family-names: "Grunwald"
given-names: "Peter D."
booktitle: "Advances in Minimum Description Length: Theory and Application"
publisher: "MIT Press"
date-published: 2005
doi: "10.48550/arXiv.math/0406077"
url: "https://arxiv.org/abs/math/0406077"
notes: "Tutorial chapters on MDL. arXiv preprint; published in MIT Press edited volume."
# ─────────────────────────────────────────────────────────────────────────────
# Language Modeling & Compression
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Language Modeling Is Compression"
authors:
- family-names: "Deletang"
given-names: "Gregoire"
- family-names: "Ruoss"
given-names: "Anian"
- family-names: "Duquenne"
given-names: "Paul-Ambroise"
- family-names: "Catt"
given-names: "Elliot"
- family-names: "Genewein"
given-names: "Tim"
- family-names: "Mattern"
given-names: "Christopher"
- family-names: "Grau-Moya"
given-names: "Jordi"
- family-names: "Wenliang"
given-names: "Li Kevin"
- family-names: "Aitchison"
given-names: "Matthew"
- family-names: "Orseau"
given-names: "Laurent"
- family-names: "Hutter"
given-names: "Marcus"
- family-names: "Veness"
given-names: "Joel"
conference:
name: "International Conference on Learning Representations (ICLR)"
date-published: 2024
doi: "10.48550/arXiv.2309.10668"
url: "https://arxiv.org/abs/2309.10668"
notes: "Chinchilla 70B compresses ImageNet to 43.4% and LibriSpeech to 16.4%. ICLR 2024; no proceedings DOI."
- type: article
title: "LLMZip: Lossless Text Compression using Large Language Models"
authors:
- family-names: "Valmeekam"
given-names: "Chandra Shekhara Kaushik"
- family-names: "Narayanan"
given-names: "Krishna R."
- family-names: "Kalathil"
given-names: "Dileep M."
- family-names: "Chamberland"
given-names: "Jean-Francois"
- family-names: "Shakkottai"
given-names: "Srinivas"
date-published: 2023
doi: "10.48550/arXiv.2306.04050"
url: "https://arxiv.org/abs/2306.04050"
notes: "Uses LLaMA-7B for lossless text compression. Arxiv preprint."
# ─────────────────────────────────────────────────────────────────────────────
# Geometry of Embeddings / Manifolds
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Poincare Embeddings for Learning Hierarchical Representations"
authors:
- family-names: "Nickel"
given-names: "Maximillian"
- family-names: "Kiela"
given-names: "Douwe"
conference:
name: "Neural Information Processing Systems (NeurIPS)"
date-published: 2017
pages: "6338-6347"
doi: "10.48550/arXiv.1705.08039"
url: "https://arxiv.org/abs/1705.08039"
notes: "Hyperbolic Poincare ball embeddings. NeurIPS 2017; no proceedings DOI."
# ─────────────────────────────────────────────────────────────────────────────
# Zipf's Law & Statistical Linguistics
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Zipf's word frequency law in natural language: A critical review and future directions"
authors:
- family-names: "Piantadosi"
given-names: "Steven T."
journal: "Psychonomic Bulletin & Review"
volume: "21"
pages: "1112-1130"
date-published: 2014
doi: "10.3758/s13423-014-0585-6"
url: "https://link.springer.com/article/10.3758/s13423-014-0585-6"
notes: "Critical review of Zipf's law theories; argues no single account explains all facts."
# ─────────────────────────────────────────────────────────────────────────────
# Recent Arxiv Preprints (No Peer-Reviewed DOI Yet)
# ─────────────────────────────────────────────────────────────────────────────
- type: article
title: "Attention and Compression is all you need for Controllably Efficient Language Models"
authors:
- family-names: "Prakash"
given-names: "Jatin"
- family-names: "Puli"
given-names: "Aahlad"
- family-names: "Ranganath"
given-names: "Rajesh"
date-published: 2025
doi: "10.48550/arXiv.2511.05313"
url: "https://arxiv.org/abs/2511.05313"
notes: "Compress & Attend Transformer (CAT). Submitted to ICLR 2026."
- type: article
title: "On the compressiveness of the Burrows-Wheeler transform"
authors:
- family-names: "Bannai"
given-names: "Hideo"
- family-names: "I"
given-names: "Tomohiro"
- family-names: "Nakashima"
given-names: "Yuto"
date-published: 2024
doi: "10.48550/arXiv.2411.11298"
url: "https://arxiv.org/abs/2411.11298"
notes: "BWT and bijective BWT compressiveness analysis. Arxiv preprint."
- type: article
title: "Harnessing the Universal Geometry of Embeddings"
authors:
- family-names: "Jha"
given-names: "Rishi"
- family-names: "Zhang"
given-names: "Collin"
- family-names: "Shmatikov"
given-names: "Vitaly"
- family-names: "Morris"
given-names: "John X."
date-published: 2025
doi: "10.48550/arXiv.2505.12540"
url: "https://arxiv.org/abs/2505.12540"
notes: "Universal latent representation translation across embedding spaces. Arxiv preprint."
- type: article
title: "Hyperbolic Large Language Models"
authors:
- family-names: "Patil"
given-names: "Sarang"
- family-names: "Zhang"
given-names: "Zeyong"
- family-names: "Huang"
given-names: "Yiran"
- family-names: "Ma"
given-names: "Tengfei"
- family-names: "Xu"
given-names: "Mengjia"
date-published: 2025
doi: "10.48550/arXiv.2509.05757"
url: "https://arxiv.org/abs/2509.05757"
notes: "Comprehensive survey of hyperbolic geometry in LLMs. Arxiv preprint."
- type: article
title: "Entropy Estimation Methods"
authors:
- name: "Authors pending"
date-published: 2025
doi: "10.48550/arXiv.2511.10618"
url: "https://arxiv.org/abs/2511.10618"
notes: "Recent preprint on entropy estimation."
- type: article
title: "Rethinking LLM Information Geometry"
authors:
- name: "Authors pending"
date-published: 2025
doi: "10.48550/arXiv.2506.15830"
url: "https://arxiv.org/abs/2506.15830"
notes: "Recent preprint on LLM information geometry."
- type: article
title: "Token Embeddings Manifold Analysis"
authors:
- name: "Authors pending"
date-published: 2025
doi: "10.48550/arXiv.2504.01002"
url: "https://arxiv.org/abs/2504.01002"
notes: "Recent preprint on token embedding manifolds."
- type: article
title: "Topological Language Analysis"
authors:
- name: "Authors pending"
date-published: 2024
doi: "10.48550/arXiv.2411.10298"
url: "https://arxiv.org/abs/2411.10298"
notes: "Recent preprint on topological approaches to language."
- type: article
title: "Unraveling Syntax with Neural Methods"
authors:
- name: "Authors pending"
date-published: 2025
doi: "10.48550/arXiv.2510.02524"
url: "https://arxiv.org/abs/2510.02524"
notes: "Recent preprint on syntax analysis."
- type: article
title: "Latent Semantic Manifolds"
authors:
- name: "Authors pending"
date-published: 2026
doi: "10.48550/arXiv.2603.22301"
url: "https://arxiv.org/abs/2603.22301"
notes: "Recent preprint on latent semantic manifolds."
- type: article
title: "Kolmogorov Complexity Legacy Survey"
authors:
- name: "Authors pending"
date-published: 2020
doi: "10.48550/arXiv.2006.11842"
url: "https://arxiv.org/abs/2006.11842"
notes: "Survey of Kolmogorov complexity developments."
- type: article
title: "Information Bottleneck in Modern Deep Learning"
authors:
- name: "Authors pending"
date-published: 2025
doi: "10.48550/arXiv.2509.26327"
url: "https://arxiv.org/abs/2509.26327"
notes: "Recent preprint extending information bottleneck theory."
Reference in a new issue View git blame Copy permalink