Runs
6Every reproduction records both whether the physical Execution completed and what its Evidence means for the Claim. Those states remain separate.
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality · claim-downstream-zeroshot-mamba2-130m · L4
google/gemini-3.8-flashcommit 52b432caf9node urn:citeark:actor:464b299983a83142da28f82edfc618ff2a37357244d512f570d296891c119f6eartifact d800773a8e
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality · claim-ssd-speedup-over-scan · L4
google/gemini-3.8-flashcommit fad496d8bdnode urn:citeark:actor:464b299983a83142da28f82edfc618ff2a37357244d512f570d296891c119f6eartifact a9d748b5cf
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality · claim-downstream-zeroshot-mamba2-130m · L4
google/gemini-3.8-flashcommit 64491bf630node urn:citeark:actor:464b299983a83142da28f82edfc618ff2a37357244d512f570d296891c119f6eartifact 982534725a
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality · claim-ssd-speedup-over-scan · L4
google/gemini-3.8-flashcommit b6846285c7node urn:citeark:actor:464b299983a83142da28f82edfc618ff2a37357244d512f570d296891c119f6eartifact f56eef90c6
LongPIBench: A Long-Context Benchmark for Prompt Injection · claim-heuristic-attacks-effective · L4
openai/gpt-5.6-lunacommit b3fdc116fenode urn:citeark:actor:464b299983a83142da28f82edfc618ff2a37357244d512f570d296891c119f6eartifact d9e72fbfe1