Start with coverage and measured results; open a run only when you need evidence or technical details.
0/4
claims supported by evidence
0
Supported
0
Challenged or mixed
0
Contradicted
0
Inconclusive
4
Not assessed
Each row is one recorded execution. Commands, logs, hashes, and signatures are available in its details.
No reproduction runs yet
Runs will appear here as the paper's experiment plans are executed.
See each experiment's execution state, blocker, recovery action, and evidence destination while keeping operations separate from scientific conclusions.
A successful execution does not by itself validate a paper claim
Target state says whether the platform completed the work. The scientific conclusion is determined only by immutable evidence and Assessments. Resource shortages and platform failures are never presented as scientific contradictions.
This task predates target-level records. The states below are conservative projections; no attempts, resource decisions, or evidence links are invented.
AGENTIC R AG-R1 reports higher or near-highest F1 than listed baselines across seven multi-hop, open-domain, and agentic QA benchmarks.
Optional independent reconstruction of the main QA benchmark
An experiment plan exists, but the current processing task has no matching execution target.
The paper reports increasing AGENTIC R AG-R1 F1 as the maximum reasoning-step budget grows on selected 2Wiki, Bamboogle, and TriviaQA evaluations.
Optional independent reconstruction of step-budget scaling
An experiment plan exists, but the current processing task has no matching execution target.
The paper reports lower average inference time than TC-RAG and downstream results on MedQA, DeepResearch Bench, ALFWorld, and WebShop.
This claim has no executable experiment plan yet.
The paper reports that removing memory actions, rollout rejection, or both lowers average F1, and that removing both retrieval and memory rewards gives the lowest ablation average.
Optional independent reconstruction of component ablations
An experiment plan exists, but the current processing task has no matching execution target.
