Oleksiy Penkov, Boyang Shen · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27859 · cited by 0 works (OpenAlex) · open-access PDF
Un numéro de laboratoire publié ne peut être vérifié que lorsque son fichier brut et sa méthode d'extraction sont connus. Ce document présente l'architecture de provenance au niveau de la valeur d'APS ELN, un carnet de laboratoire électronique utilisé par les chercheurs et les agents du modèle de langue. L'architecture a été motivée par un audit de production dans un projet de couverture de laboratoire de matériaux effectué sur près de 5 ans. Le suivi de huit études de base de l'échantillon à la valeur stockée a montré que la structure ELN initiale préservait le lien de l'échantillon au fichier brut. Néanmoins, le lien du fichier brut à la valeur stockée a été perdu, principalement en raison de facteurs humains: les entrées
Machine translation (Meta M2M100); the English original follows.
A published laboratory number can be verified only when its raw file and extraction method are known. This paper presents the value-level provenance architecture of APS ELN, an electronic laboratory notebook used by both researchers and language-model agents. The architecture was motivated by a production audit in a materials laboratory covering projects performed over almost 5 years. Tracing eight baseline studies from sample to stored value showed that the initial ELN structure preserved the link from sample to raw file. Still, the link from raw file to stored value was lost, mainly due to human factors: manual entries carried no file reference or extractor version. To close this gap, the database design and workflow were reworked so that every stored value records its source file, the data file reader/viewer (DFR) plugin and version, any interactive analysis selection, or the server-side formula for derived quantities. An automated drift check re-runs each DFR on the stored files. In two end-to-end validation studies recorded by agents in X-ray reflectivity and tribology, all stored values retained verifiable provenance with zero drift. A comparison with five other platforms shows that none binds individual stored numbers to both their source files and extractor versions.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Workflow, File format, Raw data, Extractor, Computer science, Database
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27859, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange