{"entity":{"id":"provenance-fields","kind":"term","name":"Provenance fields for research data","aka":["provenance fields","data provenance","data lineage","pipeline version","source accession","checksum","sha256 manifest","content-addressed storage"],"tldr":"Provenance fields record where each data file came from and how it was processed (source, accession, pipeline version, genome build, date, checksum), so a result can be traced and reproduced.","summary":"Data lineage is the tracking of how data is generated, transformed and used across systems, documenting its origins and movements so errors can be traced (Wikipedia). For genomic data the minimum fields are the source dataset and accession, the pipeline and its version, the genome build and annotation release, the download date and a checksum. Content-addressable storage takes the last step further by keying each raw file on the hash of its contents, so the same bytes are stored once and any change is detected (Wikipedia).","asOf":"2026-09-24","wikipedia":"https://en.wikipedia.org/wiki/Data_lineage","links":[{"label":"Wikipedia: content-addressable storage","url":"https://en.wikipedia.org/wiki/Content-addressable_storage"},{"label":"Wikipedia","url":"https://en.wikipedia.org/wiki/Data_lineage"}],"tags":["cansim-terms"],"related":["cancer-ai-vocabulary"],"cancers":[],"sections":[],"technologies":[],"targets":[],"drugs":[],"companies":[],"institutions":[],"pathways":[],"terms":["genome-builds","ensembl-gene-id","tcga-barcode","reproducibility"],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":["Listed in the CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme; CanSim page path /terms/provenance-fields."],"provenance":{"editedBy":"OnCo CanSim terms wave (Wikipedia summaries, standards and project pages, GDC and FDA pages, Europe PMC)","editedOn":"2026-09-24","note":"CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme"},"category":"Genomics & genetics"},"route":"/terms/provenance-fields/","neighbours":{"term":[{"id":"duckdb-catalog","kind":"term","name":"Analytical databases as a data catalogue (DuckDB, PostgreSQL)","route":"/terms/duckdb-catalog/"},{"id":"cancer-ai-vocabulary","kind":"term","name":"Cancer AI vocabulary (CanSim terms map)","route":"/terms/cancer-ai-vocabulary/"},{"id":"ensembl-gene-id","kind":"term","name":"Ensembl gene ID","route":"/terms/ensembl-gene-id/"},{"id":"genome-builds","kind":"term","name":"Genome builds: GRCh38 versus hg19 (GRCh37)","route":"/terms/genome-builds/"},{"id":"reproducibility","kind":"term","name":"Reproducibility and negative results","route":"/terms/reproducibility/"},{"id":"tcga-barcode","kind":"term","name":"TCGA barcode","route":"/terms/tcga-barcode/"},{"id":"units-ontology","kind":"term","name":"Units of measurement ontology (UO)","route":"/terms/units-ontology/"},{"id":"zenodo-doi","kind":"term","name":"Zenodo DOIs for data and code","route":"/terms/zenodo-doi/"}]}}