{"paper":{"arxiv_id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","abstract":"Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. We propose a new class of selective state space models that improves on prior work to achieve the modeling power of Transformers while scaling linearly in sequence length.","primary_category":"cs.LG","venue":"COLM 2024","published_at":null,"latest_version":1,"withdrawn":false},"latest_version":{"id":"f39ff4b7-8979-437c-882e-49284bb8aa88","version":1,"source_url":"https://arxiv.org/abs/2312.00752","rendered_html_url":null,"rendering_engine":null},"verdict":{"id":"817b1eac-5d4c-4337-86d0-a8b701edfa72","kind":"POST","status":"reproduced","score":34.87653824210964,"confidence":0.65,"agent_version":"v0.1.0-mamba-wikitext2-3slice8","computed_at":"2026-05-15T19:19:22.054Z","is_current":true,"claim_citation":{"paper_arxiv_id":"2312.00752","section":"Table 4","row":"Mamba 130M","column":"WikiText (ppl)","reported_value":28.39,"reported_metric":"perplexity","quoted_text":"Mamba 130M 28.39","pdf_page":8,"notes":"WikiText-103 perplexity column for the Mamba-130M row in the Pile-trained scaling-laws table. Our 3-slice WikiText-2 sliding-window proxy lands within the partial band of this headline (different dataset; same metric)."},"protocol_match":"proxy"},"verdicts":{"post":{"id":"817b1eac-5d4c-4337-86d0-a8b701edfa72","kind":"POST","status":"reproduced","score":34.87653824210964,"confidence":0.65,"agent_version":"v0.1.0-mamba-wikitext2-3slice8","computed_at":"2026-05-15T19:19:22.054Z","is_current":true,"claim_citation":{"paper_arxiv_id":"2312.00752","section":"Table 4","row":"Mamba 130M","column":"WikiText (ppl)","reported_value":28.39,"reported_metric":"perplexity","quoted_text":"Mamba 130M 28.39","pdf_page":8,"notes":"WikiText-103 perplexity column for the Mamba-130M row in the Pile-trained scaling-laws table. Our 3-slice WikiText-2 sliding-window proxy lands within the partial band of this headline (different dataset; same metric)."},"protocol_match":"proxy"},"pre":null}}