A geocoded dataset of primary health care clinics in Brazil.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41114289", "kind": "science-record", "revision": 2, "content_hash": "sha256:fe3ba5f0e29441efe30474e51204094c8808cc7b8d72551c1fcf093eff85ddc3", "created_at": "2026-11-01T20:31:10Z", "updated_at": "2026-11-01T21:35:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A geocoded dataset of primary health care clinics in Brazil.", "doi": "10.1016/j.dib.2025.112085", "pmid": "41114289", "authors": ["Bruno Wichmann", "Roberta Moreira Wichmann", "Tiago Almeida de Oliveira", "Crysttian Arantes Paixão"], "journal": "Data in brief", "year": 2025, "abstract": "We develop a geocoded dataset of primary health care clinics in Brazil. We merge data from three publicly available sources. The first is the National Registry of Healthcare Facilities (CNES-ST), which collects the location (state, municipality, and 8-digit postal code) of all health care facilities, public or private, operating in Brazil. The second is the National Registry of Addresses for Statistical Purposes (IBGE-CNEFE), which contains the geographic coordinates of all addresses in Brazil (including 8-digit postal codes) and serves as the basis for the Brazilian census. Our approach aggregates individual (address-level) coordinates to the 8-digit postal code, and assigns coordinates to primary care clinics based on each clinics' postal code. Using data from a third source, the IBGE shapefiles, we estimate the area of postal codes to evaluate the precision of our geo-referencing method. The unique facility identification number (cnes number) can be used to merge our georeferenced data with other publicly available databases of the Brazilian Unified Health System. The final dataset is an unbalanced panel with monthly observations about 293,698 primary care clinics' locations (i.e. coordinates), from January 2018 to December 2023, totalling 15,455,219 observations.", "claims": [{"id": "claim-method", "statement": "Specifically, for every 8-digit postal code, we compute the (frequency weighted) average latitude and longitude.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41114289", "locator": "sections[7] \"Postal codes coordinates data (IBGE-CNEFE)\" paragraph 4", "quote": "Specifically, for every 8-digit postal code, we compute the (frequency weighted) average latitude and longitude."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Mendeley DataData and codes to produce a geocoded dataset of primary health care clinics in Brazil (Reference data)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41114289", "locator": "sections[13] \"Data Availability\" paragraph 2", "quote": "Mendeley DataData and codes to produce a geocoded dataset of primary health care clinics in Brazil (Reference data)"}], "state": "complete"}, {"id": "claim-target-result", "statement": "The final dataset is an unbalanced panel with monthly observations about 293,698 primary care clinics’ locations (i.e. coordinates), from January 2018 to December 2023, totalling 15,455,219 observations.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41114289", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The final dataset is an unbalanced panel with monthly observations about 293,698 primary care clinics’ locations (i.e. coordinates), from January 2018 to December 2023, totalling 15,455,219 observations."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The final dataset is an unbalanced panel with monthly observations about 293,698 primary care clinics’ locations (i.e. coordinates), from January 2018 to December 2023, totalling 15,455,219 observations.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41114289"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41114289", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2025.112085", "sha256": "sha256:d0625b6d326ec8f18891b0527629ad0826b1031a7e570acbc66da64e9cbfc340", "bytes": 28811, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2025.112085", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12528921", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "frequency-weighted average latitude and longitude aggregation", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Specifically, for every 8-digit postal code, we compute the (frequency weighted) average latitude and longitude."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (frequency-weighted average latitude and longitude aggregation), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Mendeley DataData and codes to produce a geocoded dataset of primary health care clinics in Brazil (Reference data)"], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41114289"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:03:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8346, "completion_tokens": 2002, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41114289", "type": "paper", "label": "pmid:41114289"}, {"id": "source:pmid:41114289", "type": "manuscript", "label": "PMID 41114289 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41114289", "type": "paper", "label": "pmid:41114289"}, {"id": "source:pmid:41114289", "type": "manuscript", "label": "PMID 41114289 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41114289", "type": "extraction", "used": ["source:pmid:41114289"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41114289", "parent_hash": "sha256:6902234a8001bf36d3eecfd0e74eda3cb656ee9b7a7907e5e002b49777e8cce9", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}