PaveFEA-AI replication archive for "From generated scripts to solved models: auditing specification conformance in an LLM-assisted finite-element workflow for pavement structures"

Replication archive for the manuscript "From generated scripts to solved models: auditing specification conformance in an LLM-assisted finite-element workflow for pavement structures" (Y. Luo, D. Huo, J. Wang; Chongqing Jiaotong University). It holds the run ledger of 377 logged generations with per-request seeds and request order; all 377 generated Abaqus scripts; the frozen evaluator and scoring rubric; the prompt templates and the 310 rendered prompts; per-generation retrieval metadata; the frozen test-case specifications; the manual repair chains with per-step diffs and the seven repaired input decks; the repair lineage of the seven executed scripts, classifying every repair step by whether it changed the physical definition of the model; the specification-conformance census of the solved decks under two frozen rule sets, with a cell-by-cell comparison of the two; a positive control of the census — two reference models built and solved from the TC-02 and TC-01 specifications and nine single-defect variants, with the scripts that generate them, their input decks, solver records and read-outs; the synchronisation-timing probe records; the statistical recomputation pipeline and the reproducibility gate; and a snapshot of the submission (manuscript, supplementary material, figures, data tables and verification reports) sealed by RELEASE_SHA256.csv. MANIFEST_SHA256.csv lists the SHA-256 of every file in the archive. What is withheld: the retrieval base derives from a proprietary finite-element function library. In each rendered prompt the retrieved-chunk block, and only that block, is replaced by a manifest of retrieval order, module, function name, similarity score and characters withheld (2,733,580 characters across the 310 prompts). Output databases and solver scratch files (103 files, 1.73 GB) are listed by path, size and SHA-256 in WITHHELD_LARGE_ARTEFACTS.csv and are available from the corresponding author on request; the output databases of the positive control are not archived and are regenerated from its archived input decks. See ARCHIVE_README.md. Version 1.4 (2026-09-30) updates the submission snapshot to the revised manuscript (title unchanged). It adds a second, stricter rule set for the specification census — scoring where a value is applied as well as whether it appears, and declaring value rules for the reinforcement, crack springs and foundation — with its prespecification, extractor, self-tests, reading and a cell-by-cell comparison with the first rule set, which is retained unchanged (submission_pack/data/spec_conformance/); the positive control of the census (submission_pack/data/positive_control/ for the generator scripts, modelling conventions and results; positive_control/ for the eleven input decks and their solver records); and a static constructor check of the raw scripts (Supplementary Note S19). The experimental artefacts carried by versions 1.0–1.3 are unchanged; two internal working documents of the submission package (in Chinese) remain omitted, with their SHA-256 values kept in RELEASE_SHA256.csv. Archive file: pavefea-ai-replication.zip (2,111 entries), SHA-256 cf43d0e5a21da2f02133751e86113739b2c68b32cb8129878285328a8afd84ce.