Automated High-Precision Extraction and Forensic Verification of Data-Bearing Vector Figures

2026-06-30

AI Summary

Scientific and engineering data are frequently disseminated in vector graphics formats such as PDF, SVG, or EPS, yet manual redigitization remains inefficient, error-prone, and lacks verifiable authenticity. This work proposes a fully automated, non-interactive method for high-fidelity numerical recovery by parsing vector graphic structures, modeling renderer behavior, and incorporating floating-point precision analysis. To ensure data integrity, the approach introduces a re-rendering certificate mechanism that provides verifiable and non-repudiable authenticity guarantees. Without requiring ground-truth supervision, the method successfully reproduces the Planck 2018 results with a precision of 10⁻⁹ and the Keeling CO₂ record with an accuracy of 5×10⁻⁴, while also correcting the confidence interval of the Chinchilla scaling law—significantly enhancing the reliability and traceability of scientific data reuse.

Abstract

The quantitative record of science and engineering is increasingly carried by figures rather than text or tables, and a reader who needs the underlying numbers must usually re-digitize them by hand: slowly, imprecisely, and with no way to prove the result is faithful. Yet when a figure is stored as vector graphics, its data are not approximated by the picture but encoded in it: the renderer writes each marker and vertex at a printed precision that, for the dominant scientific toolchain, exceeds the data's own. We turn this into three contributions, one per shortcoming of hand digitization. First, a precision theory bounding how accurately data can be recovered for a given renderer and export format: bit-exact float32 for matplotlib markers, and a calibration-limited three to four significant figures end to end. Second, an automatic extractor that decodes a figure in one pass with no human in the loop, in place of the slow point-by-point tracing a digitizer demands. Third, a verification theory: recovery is injective except on a characterized, vanishingly small interval near zero; accidental agreement between unrelated data is astronomically unlikely; and a re-rendering certificate binds the recovered values to the markers, lines, and ticks the figure draws, not its text, making a result non-repudiable. With no ground truth used during recovery, decoded figures match external archives (Planck 2018 to 10^-9; the Keeling CO2 record to 5*10^-4, and one decoded figure independently reproduces a correction to the Chinchilla scaling-law confidence interval. We map the achievable precision across common renderers and their PDF, SVG, and EPS formats. What we deliver is certified data; the scientific significance of any particular dataset lies outside this paper's scope, and recovered values are candidates for human review, never accusations.

Problem

• vector figures
• data extraction
• forensic verification
• scientific data
• digitization

Innovation

• vector graphics
• data extraction
• forensic verification
• precision theory
• non-repudiable recovery