paper_id	claim	claim_status	evidence_status	source_depth	source_quote	page_or_section	taxonomy_fit	audit_status
2604.24938v2	The abstract reports: Depth pruning improves the inference efficiency of large language models by removing Transformer blocks.	preliminary-linked	has evidence row	abstract	Depth pruning improves the inference efficiency of large language models by removing Transformer blocks.	abstract	in-scope: taxonomy category match	needs work; preliminary / abstract-derived; report=audit_report.md
2411.03513v1	The abstract reports: This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT.	preliminary-linked	has evidence row	abstract	This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT.	abstract	in-scope: taxonomy category match	needs work; preliminary / abstract-derived; report=audit_report.md
2510.22228v1	The abstract reports: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).	preliminary-linked	has evidence row	abstract	Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).	abstract	in-scope: taxonomy category match	needs work; preliminary / abstract-derived; report=audit_report.md
2406.07929v1	The abstract reports: With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for signal classification.	preliminary-linked	has evidence row	abstract	With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for signal classification.	abstract	in-scope: taxonomy category match	needs work; preliminary / abstract-derived; report=audit_report.md
2602.14649v1	The abstract reports: Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment.	preliminary-linked	has evidence row	abstract	Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment.	abstract	in-scope: taxonomy category match	needs work; preliminary / abstract-derived; report=audit_report.md