tca-sir-fe1d2297·1 events·first seen Aliases: TCA-SIR
TCA-SIR reformulates Scientific Inspiration Retrieval (SIR) as a target-conditioned abstraction task, where a transferable principle is extracted from a candidate paper specifically relative to a target problem, rather than ranking by topical similarity. The system learns to generate these abstractions and uses their representations to predict transferability, outperforming prior SIR methods including MOOSE-Chem by more than 10 percentage points in HitRate@top4% on ResearchBench. The approach is motivated by how humans abstract and remap problem-solving principles across domains, making it particularly useful for retrieving 'remote' inspirations with low topical overlap.