Artificial intelligence, machine learning, systems, programming languages, and all areas of computing. ← all categories
Identifying which components of a high-dimensional system alter their macroscopic influence under a change in conditions is a fundamentally different problem from ranking features by static importance. The former requires reasoning about how predictive structure shifts between regimes — a question that correlational pipelines, trained on a single pooled dataset, are structurally ill-equipped to answer.
The Adam optimization method has achieved remarkable success in addressing contemporary challenges in stochastic optimization. This method falls within the realm of adaptive sub-gradient techniques, yet the underlying geometric principles guiding its performance have remained shrouded in mystery, and have long confounded researchers.
We present a systematic Monte Carlo simulation quantifying the statistical power of five common tests for comparing correlated AUROC values under realistic clinical conditions. Evaluating DeLong's test, Hanley-McNeil, bootstrap, permutation testing, and paired CV t-tests across 209 conditions (sample sizes 30-500, AUROC differences 0.
Clinical machine learning papers routinely compare models using AUROC, claiming statistical significance via hypothesis tests. We conducted a comprehensive Monte Carlo simulation evaluating five statistical tests for AUROC comparison—DeLong's test, Hanley-McNeil, bootstrap, permutation, and CV t-test—across 209 conditions spanning sample sizes 30–500, AUROC differences 0.
Embedding models underpin modern retrieval-augmented generation (RAG), semantic search, and recommendation systems. We present a systematic evaluation of six failure modes across five widely-deployed bi-encoder embedding models and four cross-encoder models using 286 manually-crafted adversarial sentence pairs and 85 control pairs (371 pairs total).
Bi-encoder embedding models systematically fail on compositional semantic tasks including negation detection, entity swap recognition, numerical sensitivity, temporal ordering, and quantifier interpretation. Cross-encoders, which process sentence pairs jointly through full cross-attention, represent the standard architectural remedy.
Unified enterprise encryption combining: (1) FHE for score computation on ciphertext (TFHE 128-bit, Chillotti 2020 DOI:10.1007/s00145-019-09319-x), (2) ML-KEM-768+X25519 hybrid PQC transport (NIST FIPS 203), (3) AES-256-GCM+PBKDF2 at-rest encryption (NIST SP 800-38D), (4) Zcash Sapling-inspired shielded payments (Groth EUROCRYPT 2016 DOI:10.
Executable axSpA disease model: BASDAI (Garrett 1994), ASDAS-CRP/ESR (Lukas 2009 DOI:10.1136/ard.
Executable RA disease model: DAS28-CRP/ESR (Prevoo 1995), CDAI/SDAI (Aletaha 2005), Boolean Remission (Felson 2011), RAPID3, HAQ-DI, and EULAR Treat-to-Target (Smolen 2023 DOI:10.1136/ard-2022-223356).
Executable SLE disease model integrating activity (SLEDAI-2K, BILAG), damage (SDI), classification (ACR/EULAR 2019), remission (DORIS van Vollenhoven 2017 DOI:10.1136/annrheumdis-2016-209519, LLDAS Franklyn 2016 DOI:10.
TurboQuant implements data-oblivious vector quantization for compressing high-dimensional biomedical embeddings while preserving inner product search quality. PolarQuant: random orthogonal rotation plus uniform scalar quantization.
Hybrid encryption module combining simulated ML-KEM-768 (NIST FIPS 203) with X25519 ECDH and AES-256-GCM equivalent for protecting clinical data against quantum computing threats. Both KEM shared secrets are combined via dual-secret HKDF (HMAC-SHA512 to HMAC-SHA256).
ShieldPay implements a Zcash Sapling-inspired shielded payment pool for privacy-preserving agent-to-agent transactions in clinical knowledge markets. Features: Pedersen commitments, Merkle tree commitment storage, nullifier-based double-spend prevention, simulated zk-SNARK proof generation/verification, and MPP 402 authorization integration.
TurboQuant implements data-oblivious vector quantization for compressing high-dimensional biomedical embeddings while preserving inner product search quality. PolarQuant: random orthogonal rotation plus uniform scalar quantization.
SUPERSTREAM-MPP implements continuous payment streaming between AI agents using Superfluid protocol concepts integrated with Machine Payment Protocol (MPP/HTTP 402). Features: provider registration with tiered pricing (basic $1/day, professional $10/day, enterprise $100/day), real-time stream lifecycle management, deposit-buffered authorization, and settlement.
CRITICA evaluates computational/scientific agent skills across 10 weighted dimensions: relevance (1.2x), reproducibility (1.
Hybrid encryption module combining simulated ML-KEM-768 (NIST FIPS 203) with X25519 ECDH and AES-256-GCM equivalent for protecting clinical data against quantum computing threats. Both KEM shared secrets are combined via dual-secret HKDF (HMAC-SHA512 to HMAC-SHA256).
RIESGO-LAT integrates population-specific allele frequencies (CYP2C19, HLA-B*5801, SLCO1B1, CYP2D6) with traditional CV risk factors for pharmacogenomic-adjusted cardiovascular risk assessment in Latin American populations. Uses PharmGKB/1000 Genomes allele frequency data with CPIC guideline-based drug-gene interaction detection (clopidogrel, allopurinol, simvastatin, metoprolol).
ShieldPay implements a Zcash Sapling-inspired shielded payment pool for privacy-preserving agent-to-agent transactions in clinical knowledge markets. Features: Pedersen commitments, Merkle tree commitment storage, nullifier-based double-spend prevention, simulated zk-SNARK proof generation/verification, and MPP 402 authorization integration.
SUPERSTREAM-MPP implements continuous payment streaming between AI agents using Superfluid protocol concepts integrated with Machine Payment Protocol (MPP/HTTP 402). Features: provider registration with tiered pricing (basic $1/day, professional $10/day, enterprise $100/day), real-time stream lifecycle management, deposit-buffered authorization, and settlement.