Research Lineage Library

Trace original papers without replacing them with AI summaries

This metadata-first library links directly to scholarly records on arXiv—pronounced “archive.” It is intended to help readers locate and revisit original work while keeping authorship, dates, source status, and uncertainty visible.

Verified records8
Provisional reading paths3
Metadata checkedJul 22, 2026

Metadata-first research paths

Follow the papers in time order

Each card preserves the paper title, named authors, first arXiv submission date, identifier, and direct abstract-page link. The connectors show time order only; they are not claims that one paper caused, influenced, validated, or superseded another.

Provisional path 01

Transformer and language-model records

Chronological order only · no importance or influence ranking

arXiv:1706.03762 Preprint repository record

Attention Is All You Need

Show all named authors

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin

arXiv:1810.04805 Preprint repository record

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Show all named authors

Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

arXiv:2005.14165 Preprint repository record

Language Models are Few-Shot Learners

Show all named authors

Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, Dario Amodei

arXiv:2203.15556 Preprint repository record

Training Compute-Optimal Large Language Models

Show all named authors

Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Jack W. Rae, Oriol Vinyals, Laurent Sifre

Provisional path 02

Retrieval and parameter-efficient adaptation

Chronological order only · no importance or influence ranking

arXiv:2005.11401 Preprint repository record

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Show all named authors

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela

arXiv:2106.09685 Preprint repository record

LoRA: Low-Rank Adaptation of Large Language Models

Show all named authors

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen

Provisional path 03

Generative-model records

Chronological order only · no importance or influence ranking

arXiv:1406.2661 Preprint repository record

Generative Adversarial Networks

Show all named authors

Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio

arXiv:2006.11239 Preprint repository record

Denoising Diffusion Probabilistic Models

Show all named authors

Jonathan Ho, Ajay Jain, Pieter Abbeel

How to read this library

Useful navigation with visible limits

Repository status

An arXiv record is a repository record. Presence on arXiv does not by itself establish peer review, acceptance, correctness, or endorsement.

Copyright and reuse

TriWei links to the abstract page and does not reproduce the paper, figures, tables, or abstract. Reuse rights depend on the license shown for the specific arXiv version.

No generated synopsis

TriWei does not reproduce or paraphrase the abstract. Open the linked record to read the authors’ own abstract and paper.

Future relationships

Labels such as “introduces,” “extends,” “tests,” or “replicates” remain unpublished until a human verifies the relationship against the papers and citations. Follow the acceptance gate in the Signal History workbench entry →

This is an independent TriWei research aid and is not affiliated with or endorsed by arXiv.