<?xml version="1.0" encoding="UTF-8"?>
<oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:title>Heuristic Index-Based Record Linkage</dc:title>
  <dc:title>R package joinery version 1.0.1</dc:title>
  <dc:description>Links records that refer to the same entity across sources that
    share no common key, such as people, firms, or addresses with spelling
    variation, abbreviations, or reordered words. Linkage is described
    declaratively as a strategy that normalises, tokenises, phonetically
    encodes, weights, and blocks each field; candidate pairs are then scored
    by the rarity-weighted overlap of their tokens and every score is
    attributed back to individual tokens for explainability. Strategies
    compose into staged pipelines of exact, fuzzy, and optional
    embedding-based matching that carry unmatched records forward and resolve
    entities as connected components. The same strategy runs on an in-memory
    'data.table' backend or an out-of-core 'DuckDB' backend, and diagnostic
    and calibration tools help tune a strategy and filter false positives.
    The token-retrieval heuristic follows Doherr (2023)
    &lt;doi:10.2139/ssrn.4326848&gt;.</dc:description>
  <dc:type>Software</dc:type>
  <dc:relation>Depends: R (&gt;= 4.1.0)</dc:relation>
  <dc:relation>Imports: S7, rlang (&gt;= 1.1.0), data.table, igraph, stringi, phonics,
lubridate, cli, glue, tinyplot, graphics</dc:relation>
  <dc:relation>Suggests: duckdb, DBI, dbplyr, dplyr, tidyllm, tibble, stringdist,
generics, parsnip, recipes, workflows, yardstick, probably,
testthat (&gt;= 3.0.0), withr, knitr, rmarkdown</dc:relation>
  <dc:creator>Eduard Brüll &lt;eduard.bruell@zew.de&gt;</dc:creator>
  <dc:publisher>Comprehensive R Archive Network (CRAN)</dc:publisher>
  <dc:contributor>Eduard Brüll [aut, cre]</dc:contributor>
  <dc:rights>MIT + file LICENSE (https://CRAN.R-project.org/package=joinery/LICENSE)</dc:rights>
  <dc:date>2026-07-07</dc:date>
  <dc:format>application/tgz</dc:format>
  <dc:identifier>https://CRAN.R-project.org/package=joinery</dc:identifier>
  <dc:identifier>doi:10.32614/CRAN.package.joinery</dc:identifier>
  <dc:language>en-GB</dc:language>
</oai_dc:dc>
