Unverified50% confidenceBenchmarkExact time
RELAGRAM is trained only on CVRP-100, yet generalizes zero-shot to CVRP-500 (15.6% gap under 256-candidate search) and CVRP-1000 (21.7% gap under 256-candidate search).
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the CVRP-100 benchmark, RELAGRAM's gaps relative to PyVRP are: 13.4% for greedy decoding, 9.8% for eight-fold symmetry augmentation, and 8.3% for 256-candidate search.77% similarUnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.65% similarUnverifiedIn the setting with condition number 100, when the factors are generated before the readout scaling, RC-DS raises the average sparse factor recovery rate from 0.506 to 0.913, against a baseline of centered logit training under the same budget.62% similarUnverifiedWhen using the Prompt-SLAM-ASR-7B model with a 2,000-word bias list, B-WER on the test-clean set was reduced by 23.4% relative to the CTC-Filter baseline.61% similarUnverifiedVCR-Bench's current evaluation is based only on a subset of Kinetics-400, and the datasets and scenarios covered remain limited.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029529API
curl https://kongchang.com/api/v1/knowledge/claims/1029529MCP
get_claim(id=1029529)