Self-evolving AI harness records higher root-cause accuracy
Preprint testing found higher scores on two public benchmarks and one company dataset, while a verification gate rejected 37% of proposed changes.
Search
2,230 results
1141–1160
AI Emotion Scores Differ Across Views of the Same Simulated Scene
Preprint: A simulated benchmark reports higher recognition scores under a privileged reference trajectory than under a stationary initial view, while an active policy recovered only part of the gap.
Robot Study Reports Wider Feasible Sampling in One Diagnostic
Preprint: PRISM reports broader feasible sampling in a single-joint test, task-specific success rates under manual and Bayesian tuning, and reported transfer to physical UR5e robots.
AI models face a harder problem: citing the data they use
A preprint argues that useful citations must trace training data, retrieved datasets and individual knowledge-graph facts.
Small preprint reports top stated response rate for spear-phishing and greed
Preprint: In a study of 12 adults, spear-phishing paired with greed had the highest reported yes-rate among 25 simulated scenarios, at 75%.
New theorem sets conditional curvature bounds for geometric equations
Preprint: A mathematical study reports conditional curvature and Hessian estimates alongside a new concavity inequality.
Molecular benchmark finds a gap between ionization methods
An arXiv preprint compares Dyson, non-Dyson and screened calculations against selected-CI reference values.
Preprint warns fluent AI security reports can lack proof
A review proposes testing the code behind vulnerability claims before human triage, but its proposed safeguards have not yet been validated.
Galaxy growth model better matches low-mass buildup to redshift 8
Preprint: COSMOS-Web observations find star formation rising slightly faster than stellar mass at low masses before flattening, a pattern that better matches the evolving galaxy mass distribution.
Mathematical model maps three possible paths for radial spread
Preprint: a theorem-driven analysis finds expansion, boundedness or collapse as the boundary-density parameter changes.
Higher QLoRA Rank Linked to Stronger Fact Learning, Lower Retention
An arXiv preprint reports an acquisition-retention trade-off in Qwen3 tests, while a smaller mathematics experiment showed a much weaker pattern.
Study finds clues that some spirals may grow around old cores
Preprint analysis of 5,124 massive central galaxies supports a possible early-type-to-spiral pathway, but does not directly observe the transformation.
Self-supervised GNSS model scores best in harsh urban tests
Preprint: The Transformer-based route led in the study’s Heavy OOD category, while supervised-only training performed better in Slight OOD.
Math preprint finds a diagram-based bound for colored link homology
Preprint: A formal result sets a grading window from crossings, local maxima and writhe, with an application to Legendrian links.
Survey finds PhD researchers draw different lines around AI use
Preprint: A survey of 3,785 PhD students found four comfort profiles, with literature tasks more comfortable than writing, data work or experiment design in the largest group.
Preprint Builds a Half-Signature Extension for 3D Bordism
The arXiv version 1 document gives an explicit construction and classifies its linear representations, while a key proof remains forthcoming.
New theorem gives Goodwillie derivatives a product rule
Preprint: A theorem by Max Blans and Thomas Blom shows how Goodwillie derivatives preserve products and related structures under stated assumptions.
Model predicts electric control of chiral phonons in dielectrics
Preprint calculations model a ferroelectric–dielectric bilayer that could pump angular momentum into lattice vibrations and reverse their handedness electrically.
CloSeR scores higher in clustering tests across six benchmarks
Preprint: CloSeR first learns from labelled known categories, then groups known and novel categories.
New numerical schemes keep stochastic simulations inside bounds
Preprint: Two explicit methods are designed to keep numerical solutions inside a prescribed hypercube for any timestep under stated assumptions.