Leveraging Full Count Census Data through Record Linkage
Bibliographic record
Abstract
Academic researchers in the U.S. and Canada have partnered with genealogical organizations and statistical agencies to create massive new scientific data collections from census enumerations. These data are creating new opportunities for research across the social and health sciences. By linking individuals and families across censuses, analysts can create national longitudinal panels that trace the characteristics of individuals over their lives and families over multiple generations. IPUMS disseminates full count census enumerations for ten U.S. census years from 1850 to 1950. These full count data cover almost 800 million individual records and the IPUMS Multigenerational Longitudinal Panel (MLP) project links individuals' records across censuses. IPUMS data can be combined with data from the U.S. Census Bureau’s data linkage infrastructure to link historical records to numerous recent censuses, surveys and administrative data that measure social, economic and health outcomes. The Canadian Peoples (TCP) is a comprehensive public research database of 40 million coded and georeferenced records found in Canadian censuses from the middle of the nineteenth century until after the First World War. The data include personal, family and household characteristics of every individual enumerated in each census from 1852 to 1921. TCP investigators are exploring record linkage technology to solve challenges presented with these historical records. The workshop included one presentation from each organization, with these objectives: introduce the data collections, explain the challenges and opportunities of census linkage, describe the linking strategies, and provide an overview on how to access the data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.006 | 0.015 |
| Open science | 0.013 | 0.004 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".