Claims

Search Type State Status Topic Model Order Counting Over

As of snapshot 27745 under ledger-default@0.3.0.

Claim	Type	Assessment	Score	Review checks	References
Across 26 data- and discovery-focused papers, Paper2Agent’s resource layer achieved 89.0 ± 3.1% accuracy on 100 synthesis questions and was reported as cheaper and faster than a browser-use baseline.	QUANTITATIVE	Leans supported	0.6318	1 of 4	143
Across 42 execution-based tasks from 10 non-biology computational papers, Paper2Agent achieved 98.1 ± 0.8% accuracy across five independent runs.	QUANTITATIVE	Supported	0.8581	1 of 4	129
On 300 tutorial-derived benchmark questions, Paper2Agent with Sonnet 4 achieved 91.2 ± 1.6% accuracy, compared with 80.3 ± 2.3% for direct-repository Claude Code using Sonnet 4.	QUANTITATIVE	Leans supported	0.6128	1 of 4	137
In a corpus of 100 computational-biology papers, Paper2Agent successfully agentified 74 papers and produced 599 proposed tools, of which 593 passed automated validation.	QUANTITATIVE	Leans supported	0.6128	1 of 4	130
Paper2Agent validates each generated tool against reference-code results and figures using example datasets, then locks validated tools to support reproducibility.	OBSERVATIONAL	Leans supported	0.6128	1 of 4	128
Paper2Agent is an automated framework that converts research papers and their associated code, data and workflows into interactive AI agents exposed through MCP servers.	OBSERVATIONAL	Leans supported	0.7146	1 of 4	121