An Ontological Spectral Recognition Engine for Breast Microwave Imaging: Density-Adaptive Multi-Operator Fusion with Lazebnik-Calibrated Baselines
Bibliographic record
Abstract
We present EtherLang v2.1, a spectral recognition engine grounded in an ontological framework that achieves perfect tissue discrimination (AUC = 1.000) in breast microwave imaging across all ACR breast density categories. Unlike traditional approaches that rely on dielectric contrast—which collapses from 12.1× infatty tissue to 1.1× in dense breast tissue—EtherLang employs density-adaptive multi-operator fusion to access structural dimensions orthogonal to permittivity. The system fuses six spectral operators (PERMITTIVITY+, FROBENIUS_IMAGE+,SECOND_LAW+, TRANSPORT+, BOLTZMANN+, WAVE+) with weights dynamically adjusted by tissue density. Key innovations include: (1) empirically-derived baselines from the Lazebnik Wisconsin-Calgary Cole-Cole parameters, (2) density-specific EDEN threshold calibration (τ = 0.70 → 0.45 across ACR I–IV), (3) a J-operator with density conditioned consistency rules, and (4) BOLTZMANN+ for Warburg-effect metabolicfingerprinting in ACR-IV dense tissue. Benchmark comparison against gprMax FDTDelectromagnetic simulation demonstrates that while single-modality EM approaches achieve AUC = 0.454 in dense tissue (worse than random), EtherLang v2.1 maintains AUC = 1.000 by accessing the ontologically distinct Spec manifolds of benign and malignant tissue. The framework achieves 1640× faster inference (0.11 ms vs. 180 ms) while using 6 complementary modalities versus gprMax’s single EM modality.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".