Zifeng Yuan

Tingting Chen, Beibei Lin, Zifeng Yuan et al.

As language models are increasingly used in scientific workflows, evaluating their ability to propose sets of explanations-not just a single correct answer-becomes critical. Many scientific problems are underdetermined: multiple, mechanistically distinct hypotheses are consistent with the same observations. We introduce HypoSpace, a diagnostic suite that treats LLMs as samplers of finite hypothesis sets and measures three complementary indicators: Validity (precision of proposals consistent with observations), Uniqueness (non-redundancy among proposals), and Recovery (coverage of the enumerated admissible set). We instantiate HypoSpace in three structured domains with deterministic validators and exactly enumerated hypothesis spaces: (i) causal graphs from perturbations, (ii) gravity-constrained 3D voxel reconstruction from top-down projections, and (iii) Boolean genetic interactions. Across instruction-tuned and reasoning-focused models, Validity often remains high while Uniqueness and Recovery degrade as the admissible space grows, revealing mode collapse that is invisible to correctness-only metrics. HypoSpace offers a controlled probe-rather than a leaderboard-for methods that explicitly explore and cover admissible explanation spaces. Code is available at: https://github.com/CTT-Pavilion/_HypoSpace.

Zifeng Yuan, Huey Eng Chua, Sourav S Bhowmick et al.

Canned patterns (i.e. small subgraph patterns) in visual graph query interfaces (a.k.a GUI) facilitate efficient query formulation by enabling pattern-at-a-time construction mode. However, existing GUIs for querying large networks either do not expose any canned patterns or if they do then they are typically selected manually based on domain knowledge. Unfortunately, manual generation of canned patterns is not only labor intensive but may also lack diversity for supporting efficient visual formulation of a wide range of subgraph queries. In this paper, we present a novel generic and extensible framework called TATTOO that takes a data-driven approach to automatically selecting canned patterns for a GUI from large networks. Specifically, it first decomposes the underlying network into truss-infested and truss-oblivious regions. Then candidate canned patterns capturing different real-world query topologies are generated from these regions. Canned patterns based on a user-specified plug are then selected for the GUI from these candidates by maximizing coverage and diversity, and by minimizing the cognitive load of the pattern set. Experimental studies with real-world datasets demonstrate the benefits of TATTOO. Importantly, this work takes a concrete step towards realizing plug-and-play visual graph query interfaces for large networks.