Search papers, labs, and topics across Lattice.
This study tackles the challenge of consolidating pair-level evidence for essay-scale republication and reuse from fragmented historical texts, specifically focusing on works by David Hume. By comparing a staged rule-based workflow with various baseline methods, the authors achieve a high F1 score of 0.948 through feature aggregation, while the final workflow demonstrates superior precision-recall trade-offs. The findings reveal that while direct LLM approaches can identify many potential reprints, they lack the precision of the developed workflow, which effectively consolidates evidence for historical analysis.
Auditable pair-level evidence consolidation reveals that traditional methods outperform LLMs in precision for identifying historical text reuse.
This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-level evidence consolidation and not fragment retrieval alone. The study focuses on a candidate set centered on essays by eighteenth-century Scottish philosopher David Hume, spanning books from ECCO (Eighteenth Century Collections Online) and historical newspapers. Because the input consists of fragmented reuse hits instead of clean document pairs, and positive coverage is inherently incomplete, we formulate the task as pair-level evidence consolidation into plausible transmission relations and compare three methodological families: a staged rule-based workflow, baselines (a decision tree and two direct LLM settings), and automated rule adaptation. On labeled ECCO--ECCO slices, pair-level feature aggregation alone already reaches 0.948 F1 on the main labeled slice, while the final workflow gives the strongest overall precision-recall trade-off among the tested rule stages. On the full ECCO--ECCO candidate universe, direct LLM baselines flag up to 14,886 pairs as reprints compared to 771 for the final workflow, behaving in this direct-prompt setup as high-recall candidate expanders rather than precision-controlled deployment classifiers. On ECCO--Newspaper, manual audit confirms all 176 predicted positives as genuine cases of republication or reuse, while issue duplication and source-side multiplicity reveal additional provenance structure. Under incomplete ground truth, auditable pair-level evidence consolidation provides a practical way to produce compact candidate spaces for historical inspection.
