From Autonomous Knowledge Generation to Generalizable Property Prediction: A Precision-First Pipeline for Electro-Optic Materials Discovery
Abstract
Electro-optic materials, whose refractive index changes linearly with an applied electric field (the Pockels effect), set the speed and energy of optical modulators and microwave-to-optical links for quantum computing. Designing better materials requires optimizing composition alongside temperature, strain, and bias field. However, general repositories lack electro-optic tensor data. We present a pipeline that builds such a database from literature following the rule: "no value is better than a wrong value." The pipeline has five stages: physics-aware acquisition, layout-aware extraction via LLM and deterministic table parsers, a three-tier verification gate, cross-paper consensus using median and median absolute deviation, and a noise-robust surrogate model audited by leave-one-material-out (LOMO) testing. Physics enters directly: notation is mapped, point-group symmetry-forbidden Pockels components are rejected, equivalent labels are merged, and values carry provenance tags. In a run over 49 publications, the gate processed 816 candidates into 414 accepted, 215 held for review, and 187 rejected. Against a hand-certified gold standard of 303 values from 16 papers, the run achieved a precision of 0.51 and recall of 0.48 for exact record matches. Across four database snapshots, held-out materials where the surrogate model beat a predict-the-mean baseline grew from 1 of 4 to 9 of 13 as the database expanded from 10 to 22 materials. While not a controlled comparison, this trend supports the premise that a precision-oriented, physics-checked database can power forward models beyond its training set and clarifies requirements for inverse material design.
Related
- Stochastic and quantum autonomous information machine: efficiency fluctuations, precision and optimization
- Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI
- Physics-Informed and Knowledge-Driven Generative AI for Autonomous Discovery of Porous Oxide Energy Materials: Opportunities and Challenges
- Editorial: Next-generation radiotherapy for prostate cancer: precision, personalization, and technological advances
- An Arrow of Time in Stable Autonomous Generation
BibTeX
@misc{datta2026from,
title = {{From Autonomous Knowledge Generation to Generalizable Property Prediction: A Precision-First Pipeline for Electro-Optic Materials Discovery}},
author = {Dibakar Datta},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.34628},
eprint = {2610.34628},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.34628},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - From Autonomous Knowledge Generation to Generalizable Property Prediction: A Precision-First Pipeline for Electro-Optic Materials Discovery
AU - Dibakar Datta
PY - 2026
DA - 2026/10/25
PB - arXiv
DO - 10.48550/arxiv.2610.34628
UR - https://arxiv.org/abs/2610.34628
AB - Electro-optic materials, whose refractive index changes linearly with an applied electric field (the Pockels effect), set the speed and energy of optical modulators and microwave-to-optical links for quantum computing. Designing better materials requires optimizing composition alongside temperature, strain, and bias field. However, general repositories lack electro-optic tensor data. We present a pipeline that builds such a database from literature following the rule: "no value is better than a wrong value." The pipeline has five stages: physics-aware acquisition, layout-aware extraction via LLM and deterministic table parsers, a three-tier verification gate, cross-paper consensus using median and median absolute deviation, and a noise-robust surrogate model audited by leave-one-material-out (LOMO) testing. Physics enters directly: notation is mapped, point-group symmetry-forbidden Pockels components are rejected, equivalent labels are merged, and values carry provenance tags. In a run over 49 publications, the gate processed 816 candidates into 414 accepted, 215 held for review, and 187 rejected. Against a hand-certified gold standard of 303 values from 16 papers, the run achieved a precision of 0.51 and recall of 0.48 for exact record matches. Across four database snapshots, held-out materials where the surrogate model beat a predict-the-mean baseline grew from 1 of 4 to 9 of 13 as the database expanded from 10 to 22 materials. While not a controlled comparison, this trend supports the premise that a precision-oriented, physics-checked database can power forward models beyond its training set and clarifies requirements for inverse material design.
ER -