{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33192152", "kind": "science-record", "revision": 3, "content_hash": "sha256:7f0e3cf643ca8f9812ef8505345f9d15d85a6876ab8f47235c1c95fc59d6035d", "created_at": "2026-11-01T15:41:15Z", "updated_at": "2026-11-01T18:53:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Biodiversidata: A novel dataset for the vascular plant species diversity in Uruguay.", "doi": "10.3897/BDJ.8.e56850", "pmid": "33192152", "authors": ["Florencia Grattarola", "Andrés González", "Patricia Mai", "Laura Cappuccio", "César Fagúndez-Pachón", "Florencia Rossi", "Franco Teixeira de Mello", "Lucía Urtado", "Daniel Pincheira-Donoso"], "journal": "Biodiversity data journal", "year": 2020, "abstract": "BACKGROUND: South America hosts some of the world's most prominent biodiversity hotspots. Yet, Uruguay - a country where multiple major ecosystems converge - ranks amongst the countries with the lowest levels of available digital biodiversity data in the continent. Such prevalent data scarcity has significantly undermined our ability to progress towards evidence-based conservation actions - a critical limitation for a country with a strong focus on agricultural industries and only 1.3% of the land surface guarded by protected areas. Under today's rapid biodiversity loss and environmental changes, the need for open-access biodiversity data is more pressing than ever before. To address this national issue, Biodiversidata - Uruguay's first Consortium of Biodiversity Data - has recently emerged with the aim of assembling a constantly growing database for the biodiversity of this country. While the first phase of the project targeted vertebrate biodiversity, the second phase presented in this paper spans the biodiversity of plants.\nNEW INFORMATION: As part of the second phase of the Biodiversidata initiative, we present the first comprehensive open-access species-level database of the vascular plant diversity recorded in Uruguay to date (i.e. all species for which data are currently available and species presence has been confirmed). It contains 12,470 occurrence records from across 1,648 species and 160 families, which roughly represents 60% of the total recorded flora of Uruguay. The primary biodiversity data include extant native and introduced species from the lycophytes, ferns, gymnosperms and angiosperms groups. Records were collated from multiple sources, including data available in peer-reviewed scientific literature, institutional scientific collections and datasets contributed by members of the Biodiversidata initiative. The complete database can be accessed at the Zenodo repository: doi.org/10.5281/zenodo.3954406.", "claims": [{"id": "claim-data-access", "statement": "The complete database can be accessed at the Zenodo repository: doi.org/10.5281/zenodo.3954406", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33192152", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The complete database can be accessed at the Zenodo repository: doi.org/10.5281/zenodo.3954406"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:33192152"], "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:33192152", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3897/BDJ.8.e56850", "sha256": "sha256:9989efb0872917fb3fa41625895f20d2ff836a78026aae9231c18d528bc3e886", "bytes": 49014, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3897/BDJ.8.e56850", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7606476", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33192152:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:06dd03d1191080c29195f233313e1bc06726f3a32eee5b4a4424c552b6151b61", "bytes": 854, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#T5946505", "version": null, "note": "Records collected per group showing number of occurrence records, number of species, records with date of collection, records collected in the last 30 years and records with coordinates, with percentage in parentheses.", "structure": {"pmcid": "PMC7606476", "section_index": 2, "section_title": "The Biodiversidata Initiative", "row_count": 6, "column_count": 6}, "table": {"label": "Table 1.", "caption": "Records collected per group showing number of occurrence records, number of species, records with date of collection, records collected in the last 30 years and records with coordinates, with percentage in parentheses.", "rows": [["Group", "Number of Occurrence Records", "Number of Species", "Records with Date (%)", "Records from the last 30 years (%)", "Records with Coordinates (%)"], ["Lycophytes", "13", "6", "13 (100)", "11 (84.6)", "13 (100)"], ["Ferns", "540", "78", "540 (100)", "508 (94.1)", "540 (100)"], ["Gymnosperms", "48", "5", "41 (85.4)", "39 (81.2)", "48 (100)"], ["Angiosperms", "11,869", "1,559", "10,527 (88.7)", "9,585 (80.8)", "11,869 (100)"], ["Total", "12,470", "1,648", "11,121 (89.2)", "10,143 (81.3)", "12,470 (100)"]], "row_count": 6, "column_count": 6, "numeric_cells": 26, "header_rows": 0, "locator": "section[2]/table-wrap[1]#T5946505"}}, {"id": "asset:table:pmid:33192152:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d1401d214f1eb22c91e56f4f16c6b641b6606b1a9900fa8b4aa634194ee2db12", "bytes": 2987, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T5946506", "version": null, "note": "List of sources used to build the Biodiversidata plant dataset, including the source type, the plant groups included in each source and the number of records extracted from each of the sources.", "structure": {"pmcid": "PMC7606476", "section_index": 4, "section_title": "Sampling description", "row_count": 38, "column_count": 4}, "table": {"label": "Table 2.", "caption": "List of sources used to build the Biodiversidata plant dataset, including the source type, the plant groups included in each source and the number of records extracted from each of the sources.", "rows": [["Source", "Source Type", "Groups", "Records"], ["Alonso Paz and Bassagoda (1999)", "Journal Article", "Ferns, Gymnosperms, Angiosperms", "252"], ["Alonso Paz and Bassagoda (2003)", "Journal Article", "Ferns, Gymnosperms, Angiosperms", "107"], ["Alonso Paz and Bassagoda (2009)", "Journal Article", "Angiosperms", "3"], ["Bartesaghi (2007)", "Thesis", "Gymnosperms, Angiosperms", "34"], ["Berazategui et al. (2009)", "Short Communication", "Angiosperms", "2"], ["Berazategui et al. (2010)", "Short Communication", "Angiosperms", "2"], ["Berazategui et al. (2012)", "Short Communication", "Angiosperms", "3"], ["Brussa (2016)", "Journal Article", "Angiosperms", "8"], ["Cascales et al. (2014)", "Journal Article", "Angiosperms", "6"], ["Delfino and Masciadri (2005)", "Journal Article", "Ferns, Angiosperms", "153"], ["Delfino et al. (2005)", "Journal Article", "Angiosperms", "26"], ["Etchebarne (2014)", "Thesis", "Angiosperms", "71"], ["Fagúndez-Pachón and Grattarola (2020)", "Biodiversidata member", "Lycophytes, Ferns, Gymnosperms, Angiosperms", "340"], ["Gautreau and Lezama (2009)", "Journal Article", "Angiosperms", "52"], ["GBIF (2020)", "Online Database", "Lycophytes, Ferns, Gymnosperms, Angiosperms", "3428"], ["González and Grattarola (2020)", "Biodiversidata member", "Angiosperms", "101"], ["González-Cabezudo (2011)", "Thesis", "Angiosperms", "781"], ["González-Calcagno (2013)", "Thesis", "Angiosperms", "991"], ["Grela (2004)", "Thesis", "Gymnosperms, Angiosperms", "1343"], ["Grela and Brussa (2003)", "Journal Article", "Gymnosperms, Angiosperms", "897"], ["Guido and Mársico (2011)", "Journal Article", "Angiosperms", "17"], ["Guido et al. (2013)", "Journal Article", "Angiosperms", "14"], ["Jolochin (2007)", "Thesis", "Angiosperms", "68"], ["Jolochin (2016)", "Thesis", "Angiosperms", "20"], ["Machado and González-Rosales (2016)", "Thesis", "Lycophytes, Ferns, Angiosperms", "220"], ["Mai et al. (2020)", "Biodiversidata member", "Ferns, Angiosperms", "520"], ["Mai et al. (2016)", "Journal Article", "Angiosperms", "50"], ["Pérez-Sobrino (2016)", "Thesis", "Angiosperms", "9"], ["Ramos (2009)", "Thesis", "Angiosperms", "152"], ["Ríos et al. (2010)", "Report", "Lycophytes, Ferns, Gymnosperms, Angiosperms", "1357"], ["Rivas and Barilani (2004)", "Journal Article", "Angiosperms", "2"], ["Rivas et al. (2014)", "Journal Article", "Ferns, Angiosperms", "53"], ["Rivas et al. (2017)", "Journal Article", "Lycophytes, Ferns, Gymnosperms, Angiosperms", "283"], ["Rodríguez-Mazzini et al. (2001)", "Report", "Lycophytes, Ferns, Gymnosperms, Angiosperms", "710"], ["Rossado et al. (2018)", "Journal Article", "Angiosperms", "20"], ["Trujillo (2012)", "Thesis", "Angiosperms", "9"], ["Urtado et al. (2020)", "Biodiversidata member", "Angiosperms, Ferns", "366"]], "row_count": 38, "column_count": 4, "numeric_cells": 74, "header_rows": 0, "locator": "section[4]/table-wrap[1]#T5946506"}}, {"id": "asset:table:pmid:33192152:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:023f3f3e57b23c8accb15965e6610616b2a3f40ab3a98009649adb2251a24108", "bytes": 8999, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[28]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC7606476", "section_index": 8, "section_title": "Description", "row_count": 62, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the existence of a particular organism at a particular place at a particular time | dwc:occurrenceID"], ["otherCatalogNumbers", "A list (concatenated and separated) of previous or alternate fully qualified catalogue numbers or other human-used identifiers for the same particular organism, whether in the current or any other dataset or collection | dwc:otherCatalogNumbers"], ["basisOfRecord", "The specific nature of the data record (e.g. PreservedSpecimen, HumanObservation, unknown) | dwc:basisOfRecord"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original existence of a particular organism at a particular place at a particular time | dwc:recordedBy"], ["establishmentMeans", "The process by which the biological individual(s) represented in the record established at the spatial region or named place (e.g. native (= nativa), introduced (= introducida), unknown (= desconocido)) | dwc:establishmentMeans"], ["previousIdentifications", "A list (concatenated and separated) of previous assignments of names to the recorded organism | dwc:previousIdentifications"], ["eventDate", "The date during which the recording event occurred (format YYYY-MM-DD) | dwc:eventDate"], ["year", "The four-digit year in which the recording event occurred, according to the Common Era Calendar | dwc:year"], ["month", "The ordinal month in which the recording event occurred | dwc:month"], ["day", "The integer day of the month on which the recording event occurred | dwc:day"], ["higherGeography", "A list (concatenated and separated) of geographic names less specific than the information captured in the locality term | dwc:higherGeography"], ["continent", "The name of the continent in which the spatial region or named place occurs | dwc:continent"], ["country", "The name of the country or major administrative unit in which the spatial region or named place occurs | dwc:country"], ["countryCode", "The standard code for the country in which the spatial region or named place occurs | dwc:countryCode"], ["stateProvince", "The name of the next smaller administrative region than country (state, province, canton, department, region etc.) in which the location occurs | dwc:stateProvince"], ["locality", "The standardised description of the spatial region or named place of an event | dwc:locality"], ["decimalLatitude", "The geographic latitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLatitude"], ["decimalLongitude", "The geographic longitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLongitude"], ["geodeticDatum", "The ellipsoid, geodetic datum, or spatial reference system (SRS) upon which the geographic coordinates given in decimalLatitude and decimalLongitude as based | dwc:geodeticDatum"], ["coordinateUncertaintyInMeters", "The horizontal distance (in metres) from the given decimalLatitude and decimalLongitude describing the smallest circle containing the whole of the spatial region or named place | dwc:coordinateUncertaintyInMeters"], ["coordinatePrecision", "A decimal representation of the precision of the coordinates given in the decimalLatitude and decimalLongitude | dwc:coordinatePrecision"], ["georeferencedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the georeference (spatial representation) for the spatial region or named place | dwc:georeferencedBy"], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the taxon to the subject | dwc:identifiedBy"], ["taxonID", "An global unique identifier for the set of taxon information | dwc:taxonID"], ["scientificName", "The full scientific name, with authorship and date information if known | dwc:scientificName"], ["nameAccordingTo", "The reference to the source in which the specific taxon concept circumscription is defined or implied | dwc:nameAccordingTo"], ["higherClassification", "A list (concatenated and separated) of taxa names terminating at the rank immediately superior to the taxon referenced in the taxon record | dwc:higherClassification"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified | dwc:kingdom"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified | dwc:phylum"], ["class", "The full scientific name of the class in which the taxon is classified | dwc:class"], ["order", "The full scientific name of the order in which the taxon is classified | dwc:order"], ["family", "The full scientific name of the family in which the taxon is classified | dwc:family"], ["genus", "The full scientific name of the genus in which the taxon is classified | dwc:genus"], ["specificEpithet", "The name of the first or species epithet of the scientificName | dwc:specificEpithet"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation | dwc:infraspecificEpithet"], ["taxonRank", "The taxonomic rank of the most specific name in the scientificName | dwc:taxonRank"], ["scientificNameAuthorship", "The authorship information for the scientificName | dwc:scientificNameAuthorship"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record | dwc:institutionCode"], ["collectionCode", "The name, acronym, coden or initialism identifying the collection or dataset from which the record was derived | dwc:collectionCode"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection | dwc:catalogNumber"], ["recordNumber", "An identifier given to the occurrence at the time it was recorded | dwc:recordNumber"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, URI) of literature associated with the existence of a particular organism at a particular place at a particular time | dwc:associatedReferences"], ["verbatimLocality", "The original textual description of the spatial region or named place of the record event | dwc:verbatimLocality"], ["georeferenceRemarks", "Notes or comments about the spatial description determination, explaining assumptions made | dwc:georeferenceRemarks"], ["vernacularName", "A list (concatenated and separated) of common or vernacular names | dwc:vernacularName"], ["locationAccordingTo", "Information about the source of the location information | dwc:locationAccordingTo"], ["georeferencedDate", "The date on which the location was georeferenced | dwc:georeferencedDate"], ["georeferenceSources", "A list (concatenated and separated) of maps, gazetteers or other resources used to georeference the Location, described specifically enough to allow anyone in the future to use the same resources | dwc:georeferenceSources"], ["georeferenceVerificationStatus", "A categorical description of the extent to which the georeference has been verified to represent the best possible spatial description (e.g. requires verification) | dwc:georeferenceVerificationStatus"], ["georeferenceProtocol", "A description or reference to the methods used to determine the spatial coordinates and uncertainties | dwc:georeferenceProtocol"], ["verbatimLatitude", "The verbatim original latitude of the location (spatial region or named place) | dwc:verbatimLatitude"], ["verbatimLongitude", "The verbatim original longitude of the location (spatial region or named place) | dwc:verbatimLongitude"], ["verbatimCoordinateSystem", "The spatial coordinate system for the verbatimLatitude and verbatimLongitude of the location | dwc:verbatimCoordinateSystem"], ["locationRemarks", "Comments or notes about the location (spatial region or named place) | dwc:locationRemarks"], ["measurementType", "The nature of the measurement, fact, characteristic or assertion | dwc:measurementType"], ["measurementValue", "The value of the measurement, fact, characteristic or assertion | dwc:measurementValue"], ["measurementDeterminedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the value of the measurement, fact, characteristic or assertion | dwc:measurementDeterminedBy"], ["measurementRemarks", "Comments or notes accompanying the measurement, fact, characteristic or assertion | dwc:measurementRemarks"], ["organismRemarks", "Comments or notes about the particular organism recorded | dwc:organismRemarks"], ["language", "Language of the resource | dcterms:language"], ["license", "A legal document giving official permission to do something with the resource | dcterms:license"]], "row_count": 62, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[28]/table-wrap[1]#DS1"}}, {"id": "asset:table:pmid:33192152:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:023f3f3e57b23c8accb15965e6610616b2a3f40ab3a98009649adb2251a24108", "bytes": 8999, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[28]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC7606476", "section_index": 11, "section_title": "Description", "row_count": 62, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the existence of a particular organism at a particular place at a particular time | dwc:occurrenceID"], ["otherCatalogNumbers", "A list (concatenated and separated) of previous or alternate fully qualified catalogue numbers or other human-used identifiers for the same particular organism, whether in the current or any other dataset or collection | dwc:otherCatalogNumbers"], ["basisOfRecord", "The specific nature of the data record (e.g. PreservedSpecimen, HumanObservation, unknown) | dwc:basisOfRecord"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original existence of a particular organism at a particular place at a particular time | dwc:recordedBy"], ["establishmentMeans", "The process by which the biological individual(s) represented in the record established at the spatial region or named place (e.g. native (= nativa), introduced (= introducida), unknown (= desconocido)) | dwc:establishmentMeans"], ["previousIdentifications", "A list (concatenated and separated) of previous assignments of names to the recorded organism | dwc:previousIdentifications"], ["eventDate", "The date during which the recording event occurred (format YYYY-MM-DD) | dwc:eventDate"], ["year", "The four-digit year in which the recording event occurred, according to the Common Era Calendar | dwc:year"], ["month", "The ordinal month in which the recording event occurred | dwc:month"], ["day", "The integer day of the month on which the recording event occurred | dwc:day"], ["higherGeography", "A list (concatenated and separated) of geographic names less specific than the information captured in the locality term | dwc:higherGeography"], ["continent", "The name of the continent in which the spatial region or named place occurs | dwc:continent"], ["country", "The name of the country or major administrative unit in which the spatial region or named place occurs | dwc:country"], ["countryCode", "The standard code for the country in which the spatial region or named place occurs | dwc:countryCode"], ["stateProvince", "The name of the next smaller administrative region than country (state, province, canton, department, region etc.) in which the location occurs | dwc:stateProvince"], ["locality", "The standardised description of the spatial region or named place of an event | dwc:locality"], ["decimalLatitude", "The geographic latitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLatitude"], ["decimalLongitude", "The geographic longitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLongitude"], ["geodeticDatum", "The ellipsoid, geodetic datum, or spatial reference system (SRS) upon which the geographic coordinates given in decimalLatitude and decimalLongitude as based | dwc:geodeticDatum"], ["coordinateUncertaintyInMeters", "The horizontal distance (in metres) from the given decimalLatitude and decimalLongitude describing the smallest circle containing the whole of the spatial region or named place | dwc:coordinateUncertaintyInMeters"], ["coordinatePrecision", "A decimal representation of the precision of the coordinates given in the decimalLatitude and decimalLongitude | dwc:coordinatePrecision"], ["georeferencedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the georeference (spatial representation) for the spatial region or named place | dwc:georeferencedBy"], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the taxon to the subject | dwc:identifiedBy"], ["taxonID", "An global unique identifier for the set of taxon information | dwc:taxonID"], ["scientificName", "The full scientific name, with authorship and date information if known | dwc:scientificName"], ["nameAccordingTo", "The reference to the source in which the specific taxon concept circumscription is defined or implied | dwc:nameAccordingTo"], ["higherClassification", "A list (concatenated and separated) of taxa names terminating at the rank immediately superior to the taxon referenced in the taxon record | dwc:higherClassification"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified | dwc:kingdom"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified | dwc:phylum"], ["class", "The full scientific name of the class in which the taxon is classified | dwc:class"], ["order", "The full scientific name of the order in which the taxon is classified | dwc:order"], ["family", "The full scientific name of the family in which the taxon is classified | dwc:family"], ["genus", "The full scientific name of the genus in which the taxon is classified | dwc:genus"], ["specificEpithet", "The name of the first or species epithet of the scientificName | dwc:specificEpithet"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation | dwc:infraspecificEpithet"], ["taxonRank", "The taxonomic rank of the most specific name in the scientificName | dwc:taxonRank"], ["scientificNameAuthorship", "The authorship information for the scientificName | dwc:scientificNameAuthorship"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record | dwc:institutionCode"], ["collectionCode", "The name, acronym, coden or initialism identifying the collection or dataset from which the record was derived | dwc:collectionCode"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection | dwc:catalogNumber"], ["recordNumber", "An identifier given to the occurrence at the time it was recorded | dwc:recordNumber"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, URI) of literature associated with the existence of a particular organism at a particular place at a particular time | dwc:associatedReferences"], ["verbatimLocality", "The original textual description of the spatial region or named place of the record event | dwc:verbatimLocality"], ["georeferenceRemarks", "Notes or comments about the spatial description determination, explaining assumptions made | dwc:georeferenceRemarks"], ["vernacularName", "A list (concatenated and separated) of common or vernacular names | dwc:vernacularName"], ["locationAccordingTo", "Information about the source of the location information | dwc:locationAccordingTo"], ["georeferencedDate", "The date on which the location was georeferenced | dwc:georeferencedDate"], ["georeferenceSources", "A list (concatenated and separated) of maps, gazetteers or other resources used to georeference the Location, described specifically enough to allow anyone in the future to use the same resources | dwc:georeferenceSources"], ["georeferenceVerificationStatus", "A categorical description of the extent to which the georeference has been verified to represent the best possible spatial description (e.g. requires verification) | dwc:georeferenceVerificationStatus"], ["georeferenceProtocol", "A description or reference to the methods used to determine the spatial coordinates and uncertainties | dwc:georeferenceProtocol"], ["verbatimLatitude", "The verbatim original latitude of the location (spatial region or named place) | dwc:verbatimLatitude"], ["verbatimLongitude", "The verbatim original longitude of the location (spatial region or named place) | dwc:verbatimLongitude"], ["verbatimCoordinateSystem", "The spatial coordinate system for the verbatimLatitude and verbatimLongitude of the location | dwc:verbatimCoordinateSystem"], ["locationRemarks", "Comments or notes about the location (spatial region or named place) | dwc:locationRemarks"], ["measurementType", "The nature of the measurement, fact, characteristic or assertion | dwc:measurementType"], ["measurementValue", "The value of the measurement, fact, characteristic or assertion | dwc:measurementValue"], ["measurementDeterminedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the value of the measurement, fact, characteristic or assertion | dwc:measurementDeterminedBy"], ["measurementRemarks", "Comments or notes accompanying the measurement, fact, characteristic or assertion | dwc:measurementRemarks"], ["organismRemarks", "Comments or notes about the particular organism recorded | dwc:organismRemarks"], ["language", "Language of the resource | dcterms:language"], ["license", "A legal document giving official permission to do something with the resource | dcterms:license"]], "row_count": 62, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[28]/table-wrap[1]#DS1"}}, {"id": "asset:table:pmid:33192152:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c15ed90ab8de604f0079238d4f44b15b3e881108eb9c8f51af65e5cf3edce65", "bytes": 276, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#taxonomic_coverage", "version": null, "note": null, "structure": {"pmcid": "PMC7606476", "section_index": 12, "section_title": "Taxa included", "row_count": 3, "column_count": 3}, "table": {"label": null, "caption": null, "rows": [["Rank", "Scientific Name", "Common Name"], ["kingdom", "Plantae", "Plants"], ["phylum", "Tracheophyta", "Vascular Plants"]], "row_count": 3, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[12]/table-wrap[1]#taxonomic_coverage"}}, {"id": "asset:table:pmid:33192152:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:023f3f3e57b23c8accb15965e6610616b2a3f40ab3a98009649adb2251a24108", "bytes": 8999, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[28]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC7606476", "section_index": 28, "section_title": "Description", "row_count": 62, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the existence of a particular organism at a particular place at a particular time | dwc:occurrenceID"], ["otherCatalogNumbers", "A list (concatenated and separated) of previous or alternate fully qualified catalogue numbers or other human-used identifiers for the same particular organism, whether in the current or any other dataset or collection | dwc:otherCatalogNumbers"], ["basisOfRecord", "The specific nature of the data record (e.g. PreservedSpecimen, HumanObservation, unknown) | dwc:basisOfRecord"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original existence of a particular organism at a particular place at a particular time | dwc:recordedBy"], ["establishmentMeans", "The process by which the biological individual(s) represented in the record established at the spatial region or named place (e.g. native (= nativa), introduced (= introducida), unknown (= desconocido)) | dwc:establishmentMeans"], ["previousIdentifications", "A list (concatenated and separated) of previous assignments of names to the recorded organism | dwc:previousIdentifications"], ["eventDate", "The date during which the recording event occurred (format YYYY-MM-DD) | dwc:eventDate"], ["year", "The four-digit year in which the recording event occurred, according to the Common Era Calendar | dwc:year"], ["month", "The ordinal month in which the recording event occurred | dwc:month"], ["day", "The integer day of the month on which the recording event occurred | dwc:day"], ["higherGeography", "A list (concatenated and separated) of geographic names less specific than the information captured in the locality term | dwc:higherGeography"], ["continent", "The name of the continent in which the spatial region or named place occurs | dwc:continent"], ["country", "The name of the country or major administrative unit in which the spatial region or named place occurs | dwc:country"], ["countryCode", "The standard code for the country in which the spatial region or named place occurs | dwc:countryCode"], ["stateProvince", "The name of the next smaller administrative region than country (state, province, canton, department, region etc.) in which the location occurs | dwc:stateProvince"], ["locality", "The standardised description of the spatial region or named place of an event | dwc:locality"], ["decimalLatitude", "The geographic latitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLatitude"], ["decimalLongitude", "The geographic longitude (in decimal degrees, using the spatial reference system given in geodeticDatum) of the geographic centre of a spatial region or named place | dwc:decimalLongitude"], ["geodeticDatum", "The ellipsoid, geodetic datum, or spatial reference system (SRS) upon which the geographic coordinates given in decimalLatitude and decimalLongitude as based | dwc:geodeticDatum"], ["coordinateUncertaintyInMeters", "The horizontal distance (in metres) from the given decimalLatitude and decimalLongitude describing the smallest circle containing the whole of the spatial region or named place | dwc:coordinateUncertaintyInMeters"], ["coordinatePrecision", "A decimal representation of the precision of the coordinates given in the decimalLatitude and decimalLongitude | dwc:coordinatePrecision"], ["georeferencedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the georeference (spatial representation) for the spatial region or named place | dwc:georeferencedBy"], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the taxon to the subject | dwc:identifiedBy"], ["taxonID", "An global unique identifier for the set of taxon information | dwc:taxonID"], ["scientificName", "The full scientific name, with authorship and date information if known | dwc:scientificName"], ["nameAccordingTo", "The reference to the source in which the specific taxon concept circumscription is defined or implied | dwc:nameAccordingTo"], ["higherClassification", "A list (concatenated and separated) of taxa names terminating at the rank immediately superior to the taxon referenced in the taxon record | dwc:higherClassification"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified | dwc:kingdom"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified | dwc:phylum"], ["class", "The full scientific name of the class in which the taxon is classified | dwc:class"], ["order", "The full scientific name of the order in which the taxon is classified | dwc:order"], ["family", "The full scientific name of the family in which the taxon is classified | dwc:family"], ["genus", "The full scientific name of the genus in which the taxon is classified | dwc:genus"], ["specificEpithet", "The name of the first or species epithet of the scientificName | dwc:specificEpithet"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation | dwc:infraspecificEpithet"], ["taxonRank", "The taxonomic rank of the most specific name in the scientificName | dwc:taxonRank"], ["scientificNameAuthorship", "The authorship information for the scientificName | dwc:scientificNameAuthorship"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record | dwc:institutionCode"], ["collectionCode", "The name, acronym, coden or initialism identifying the collection or dataset from which the record was derived | dwc:collectionCode"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection | dwc:catalogNumber"], ["recordNumber", "An identifier given to the occurrence at the time it was recorded | dwc:recordNumber"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, URI) of literature associated with the existence of a particular organism at a particular place at a particular time | dwc:associatedReferences"], ["verbatimLocality", "The original textual description of the spatial region or named place of the record event | dwc:verbatimLocality"], ["georeferenceRemarks", "Notes or comments about the spatial description determination, explaining assumptions made | dwc:georeferenceRemarks"], ["vernacularName", "A list (concatenated and separated) of common or vernacular names | dwc:vernacularName"], ["locationAccordingTo", "Information about the source of the location information | dwc:locationAccordingTo"], ["georeferencedDate", "The date on which the location was georeferenced | dwc:georeferencedDate"], ["georeferenceSources", "A list (concatenated and separated) of maps, gazetteers or other resources used to georeference the Location, described specifically enough to allow anyone in the future to use the same resources | dwc:georeferenceSources"], ["georeferenceVerificationStatus", "A categorical description of the extent to which the georeference has been verified to represent the best possible spatial description (e.g. requires verification) | dwc:georeferenceVerificationStatus"], ["georeferenceProtocol", "A description or reference to the methods used to determine the spatial coordinates and uncertainties | dwc:georeferenceProtocol"], ["verbatimLatitude", "The verbatim original latitude of the location (spatial region or named place) | dwc:verbatimLatitude"], ["verbatimLongitude", "The verbatim original longitude of the location (spatial region or named place) | dwc:verbatimLongitude"], ["verbatimCoordinateSystem", "The spatial coordinate system for the verbatimLatitude and verbatimLongitude of the location | dwc:verbatimCoordinateSystem"], ["locationRemarks", "Comments or notes about the location (spatial region or named place) | dwc:locationRemarks"], ["measurementType", "The nature of the measurement, fact, characteristic or assertion | dwc:measurementType"], ["measurementValue", "The value of the measurement, fact, characteristic or assertion | dwc:measurementValue"], ["measurementDeterminedBy", "A list (concatenated and separated) of names of people, groups or organisations who determined the value of the measurement, fact, characteristic or assertion | dwc:measurementDeterminedBy"], ["measurementRemarks", "Comments or notes accompanying the measurement, fact, characteristic or assertion | dwc:measurementRemarks"], ["organismRemarks", "Comments or notes about the particular organism recorded | dwc:organismRemarks"], ["language", "Language of the resource | dcterms:language"], ["license", "A legal document giving official permission to do something with the resource | dcterms:license"]], "row_count": 62, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[28]/table-wrap[1]#DS1"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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 (not named), 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": ["The complete database can be accessed at the Zenodo repository: doi.org/10.5281/zenodo.3954406"], "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:33192152", "asset:table:pmid:33192152:1", "asset:table:pmid:33192152:2", "asset:table:pmid:33192152:3", "asset:table:pmid:33192152:4", "asset:table:pmid:33192152:5", "asset:table:pmid:33192152:6"], "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": "2026-10-31T18:24:04Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 38263, "completion_tokens": 1199, "cached_tokens": 792}}, "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:33192152", "type": "paper", "label": "pmid:33192152"}, {"id": "source:pmid:33192152", "type": "manuscript", "label": "PMID 33192152 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33192152", "type": "paper", "label": "pmid:33192152"}, {"id": "source:pmid:33192152", "type": "manuscript", "label": "PMID 33192152 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33192152", "type": "extraction", "used": ["source:pmid:33192152"], "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:33192152", "parent_hash": "sha256:1b1f6376985859031fea829e6ce0e68c93abd5376e5ee4f9a7e33369b3297a2a", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:10:02+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}