pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier

[2608.14658] pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14658 (cs) [Submitted on 31 Jul 2026] Title: pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier Authors: Gautam Kishore View a PDF of the paper titled pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier, by Gautam Kishore View PDF HTML (experimental) Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.5 million parameters that simultaneously predicts seven content properties from raw UTF-8 bytes in a single forward pass. Operating directly at the byte level -- no tokenizer, no subword vocabulary, no pretrained embeddings -- pico-type classifies coarse type (12 classes), modality (8), subtype (24), code language (62), text language (30), file MIME type (90), and risk flags (6-label multi-label: API keys, JWTs, passwords, emails, phone numbers, SSH keys). The architecture combines a learned byte embedding, three convolutional blocks with growing receptive fields, two bidirectional attention layers with rotary position encodings, and a statistical pooling layer feeding seven Matryoshka-style classification heads. Four tiered variants (tiny/small/base/pro) share the same trunk with sliced representations from 16 to 576 dimensions, yielding ONNX exports under 210 KB and CPU inference under 10 ms. Trained on a mixture of synthetic templates and real-world data (8709 GitHub code samples, 5000 Wikipedia articles), pico-type achieves 60.3 percent code language accuracy on The Heap benchmark (24 languages) and 98.2 percent text language accuracy on Wikipedia (30 languages) -- improvements of +57 and +79 percentage points respectively over the synthetic-only baseline. Format-based heads (coarse, modality, subtype, file_mime, risk) maintain 100 percent accuracy on synthetic benchmarks. The model, code, and pretrained weights are released under Apache 2.0. Comments: 14 pages, 1 figure, 8 tables Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) Cite as: arXiv:2608.14658 [cs.LG] (or arXiv:2608.14658v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14658 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Gautam Kishore [ view email ] [v1] Fri, 31 Jul 2026 12:20:03 UTC (45 KB) Full-text links: Access Paper: View a PDF of the paper titled pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier, by Gautam Kishore View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.CL cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Certified Split Windows for Parallel Lexing: Recovering Boundaries Where No Byte Certifies#441740
• Binary Neural Networks: A Survey#19807
• Gene Machine#286253
• EDGE: a closed-form directed test for the calibration of probabilistic binary classifiers#659077
• EDGE: a closed-form directed test for the calibration of probabilistic binary classifiers#656941