{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31274982", "kind": "science-record", "revision": 3, "content_hash": "sha256:981f3a25d08138de3dcacdde73f8c77494fd017ad62ce00bbc298802fe40fb7c", "created_at": "2026-11-01T15:40:46Z", "updated_at": "2026-11-01T18:50:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Biodiversidata: An Open-Access Biodiversity Database for Uruguay.", "doi": "10.3897/BDJ.7.e36226", "pmid": "31274982", "authors": ["Florencia Grattarola", "Germán Botto", "Inés da Rosa", "Noelia Gobel", "Enrique M González", "Javier González", "Daniel Hernández", "Gabriel Laufer", "Raúl Maneyro", "Juan A Martínez-Lanfranco", "Daniel E Naya", "Ana L Rodales", "Lucía Ziegler", "Daniel Pincheira-Donoso"], "journal": "Biodiversity data journal", "year": 2019, "abstract": "BACKGROUND: The continental and marine territories of Uruguay are characterised by a rich convergence of multiple biogeographic ecoregions of the Neotropics, making this country a peculiar biodiversity spot. However, despite the biological significance of Uruguay for the South American subcontinent, the distribution of biodiversity patterns in this country remain poorly understood, given the severe gaps in available records of geographic species distributions. Currently, national biodiversity datasets are not openly available and, thus, a dominant proportion of the primary biodiversity data produced by researchers and institutions across Uruguay remains highly dispersed and difficult to access for the wider scientific and environmental community. In this paper, we aim to fill this gap by developing the first comprehensive, open-access database of biodiversity records for Uruguay (Biodiversidata), which is the result of a large-scale collaboration involving experts working across the entire range of taxonomic diversity found in the country.\nNEW INFORMATION: As part of the first phase of Biodiversidata, we here present a comprehensive database of tetrapod occurrence records native from Uruguay, with the latest taxonomic updates. The database provides primary biodiversity data on extant Amphibia, Reptilia, Aves and Mammalia species recorded within the country. The total number of records collated is 69,380, spanning 673 species and it is available at the Zenodo repository: https://doi.org/10.5281/zenodo.2650169. This is the largest and most geographically and taxonomically comprehensive database of Uruguayan tetrapod species available to date and it represents the first open repository for the country.", "claims": [{"id": "claim-data-access", "statement": "The total number of records collated is 69,380, spanning 673 species and it is available at the Zenodo repository: https://doi.org/10.5281/zenodo.2650169.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31274982", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The total number of records collated is 69,380, spanning 673 species and it is available at the Zenodo repository: https://doi.org/10.5281/zenodo.2650169."}], "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:31274982"], "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:31274982", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3897/BDJ.7.e36226", "sha256": "sha256:0b7cdeaca630841545c8045abb5714084956d0c4990ea576396dec8736ac9a94", "bytes": 40574, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3897/BDJ.7.e36226", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6597616", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:31274982:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dd0795bca7405df82c957e1c649bcd43f9396c6c38d50f837dc75f836b0fb670", "bytes": 790, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#T5184678", "version": null, "note": "Records collected per tetrapod class showing: number of occurrence records (non-duplicated records/location/year), total number of species, records without information of the date of collection and records collected in the last 30 years, with percentage in parentheses.", "structure": {"pmcid": "PMC6597616", "section_index": 2, "section_title": "First open biodiversity database of Uruguay", "row_count": 6, "column_count": 5}, "table": {"label": "Table 1.", "caption": "Records collected per tetrapod class showing: number of occurrence records (non-duplicated records/location/year), total number of species, records without information of the date of collection and records collected in the last 30 years, with percentage in parentheses.", "rows": [["", "Number of Occurrence Records", "Number of Species", "Records without Date (%)", "Records from the last 30 years (%)"], ["Amphibia", "2,530", "51", "1,780 (70.4)", "683 (27.0)"], ["Reptilia", "2,308", "68", "1,999 (86.6)", "224 (9.7)"], ["Aves", "60,627", "437", "131 (0.2)", "60,308 (99.5)"], ["Mammalia", "3,915", "117", "1,687 (43.1)", "1,122 (28.7)"], ["Total", "69,380", "673", "", ""]], "row_count": 6, "column_count": 5, "numeric_cells": 19, "header_rows": 0, "locator": "section[2]/table-wrap[1]#T5184678"}}, {"id": "asset:table:pmid:31274982:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b54c74e0de238329dab88d7cffea055c1dd6befd7acabdf801546970a715e2d8", "bytes": 3501, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T5199711", "version": null, "note": "List of sources used to build the dataset, including the source type and the number of records extracted from each of the sources.", "structure": {"pmcid": "PMC6597616", "section_index": 4, "section_title": "Sampling description", "row_count": 54, "column_count": 4}, "table": {"label": "Table 2.", "caption": "List of sources used to build the dataset, including the source type and the number of records extracted from each of the sources.", "rows": [["Source", "Source type", "Number of records", "Groups"], ["Abreu (2015)", "Journal Article", "8", "Aves"], ["Andrade-Núñez and Aide (2010)", "Journal Article", "13", "Mammalia"], ["Azpiroz et al. (2012)", "Journal Article", "54", "Aves"], ["Bardier and Maneyro (2015)", "Journal Article", "20", "Amphibia"], ["Borteiro et al. (2006)", "Journal Article", "70", "Reptilia"], ["Borteiro et al. (2009)", "Journal Article", "1", "Reptilia"], ["Borteiro et al. (2013)", "Journal Article", "4", "Reptilia"], ["Borteiro et al. (2015)", "Journal Article", "13", "Reptilia"], ["Bou (2013)", "Thesis", "86", "Mammalia"], ["Carreira and Achaval (2007)", "Journal Article", "2", "Reptilia"], ["Carreira and Lombardo (2006)", "Journal Article", "1", "Reptilia"], ["Carreira et al. (2005)", "Book", "1880", "Reptilia"], ["Carreira et al. (2012)", "Journal Article", "2", "Reptilia"], ["Colina et al. (2012)", "Journal Article", "1", "Reptilia"], ["da Rosa", "This study", "13", "Amphibia + Reptilia"], ["de Giorgi Peirano (2016)", "Thesis", "67", "Aves"], ["Elgue and Maneyro (2017)", "Journal Article", "1", "Amphibia"], ["GBIF.org", "Online Database", "58355", "Amphibia + Reptilia + Aves + Mammalia"], ["Gobel & Laufer", "This study", "285", "Amphibia + Reptilia"], ["González-Paredes et al. (2017)", "Journal Article", "3", "Reptilia"], ["González & González", "This study", "1848", "Mammalia"], ["Grattarola", "This study", "53", "Mammalia"], ["Grattarola (2015)", "Thesis", "36", "Mammalia"], ["Hernández", "This study", "944", "Aves"], ["Kolenc et al. (2009)", "Journal Article", "2", "Amphibia"], ["Kolenc et al. (2012)", "Journal Article", "2", "Amphibia"], ["Kwet et al. (2002)", "Journal Article", "1", "Amphibia"], ["Lareschi et al. (2006)", "Journal Article", "11", "Mammalia"], ["Laufer et al. (2009)", "Journal Article", "2", "Amphibia"], ["Maneyro et al. (2008)", "Journal Article", "2", "Amphibia"], ["Maneyro", "This study", "165", "Amphibia + Reptilia"], ["Martínez-Lanfranco et al. (2010)", "Journal Article", "6", "Mammalia"], ["Martínez-Lanfranco", "This study", "1712", "Aves + Mammalia"], ["Masciadri et al. (2007)", "Conference Paper", "48", "Amphibia + Reptilia + Aves"], ["Montero (2016)", "Journal Article", "85", "Reptilia"], ["Naya and Achaval (2006)", "Journal Article", "5", "Mammalia"], ["Naya", "This study", "220", "Aves"], ["Núñez et al. (2004)", "Book", "1764", "Amphibia"], ["Prigioni et al. (2011)", "Journal Article", "43", "Amphibia + Reptilia"], ["Prigioni et al. (2013)", "Journal Article", "18", "Reptilia"], ["Prigioni et al. (2018)", "Journal Article", "3", "Mammalia"], ["Queirolo (2016)", "Journal Article", "1041", "Mammalia"], ["Rodales, Botto & González", "This study", "91", "Mammalia"], ["Rodríguez-Cajarville et al. (2017)", "Journal Article", "4", "Aves"], ["Rodríguez-Mazzini et al. 2001", "Report", "151", "Amphibia + Reptilia + Mammalia"], ["Santana et al. (2013)", "Journal Article", "1", "Amphibia"], ["Sarroca et al. 2009", "Report", "189", "Amphibia + Reptilia + Aves + Mammalia"], ["Vaz-Canosa and Rodríguez-Cajarville (2015)", "Journal Article", "1", "Aves"], ["Velasco-Charpentier et al. (2016)", "Journal Article", "4", "Reptilia"], ["Verrastro et al. (2006)", "Journal Article", "3", "Reptilia"], ["Verrastro et al. (2017)", "Journal Article", "1", "Reptilia"], ["Villamil (2014)", "Journal Article", "15", "Reptilia"], ["Ziegler", "This study", "31", "Amphibia"]], "row_count": 54, "column_count": 4, "numeric_cells": 95, "header_rows": 0, "locator": "section[4]/table-wrap[1]#T5199711"}}, {"id": "asset:table:pmid:31274982:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a49fdae1e06e94a2e02cdec22f78efb91ae702e13d5382d37cec0f67af024be", "bytes": 3572, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC6597616", "section_index": 7, "section_title": "Description", "row_count": 33, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the Occurrence (as opposed to a particular digital record of the occurrence), constructed from a combination of identifiers in the record that will most closely make the occurrenceID globally unique."], ["scientificName", "The full scientific name, with authorship and date information"], ["scientificNameAuthorship", "The authorship information for the scientificName"], ["vernacularName", "Common or vernacular name in Uruguay (in Spanish)"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified"], ["class", "The full scientific name of the class in which the taxon is classified"], ["order", "The full scientific name of the order in which the taxon is classified"], ["family", "The full scientific name of the family in which the taxon is classified"], ["genus", "The full scientific name of the genus in which the taxon is classified"], ["specificEpithet", "The name of the first or species epithet of the scientificName"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation"], ["countryCode", "The standard code for the country in which the Location occurs"], ["stateProvince", "The name of the next smaller administrative region than country (department) in which the Location occurs"], ["verbatimLocality", "The original textual description of the place"], ["decimalLatitude", "The geographic latitude (in decimal degrees)"], ["decimalLongitude", "The geographic longitude (in decimal degrees)"], ["georeferenceSources", "A list of maps, gazetteers or other resources used to georeference the Location"], ["georeferencedBy", "A person, group or organisation who determined the georeference (spatial representation) for the Location."], ["eventDate", "The date when the event was recorded. Format: dd-mm-yyyy"], ["year", "The four-digit year in which the Event occurred. Format: yyyy"], ["month", "The ordinal month in which the Event occurred. Format: mm"], ["day", "The integer day of the month on which the Event occurred. Format: dd"], ["basisOfRecord", "The specific nature of the data record"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record"], ["collectionCode", "The name or acronym identifying the collection or dataset from which the record was derived"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original Occurrence"], ["recordNumber", "An identifier given to the Occurrence at the time it was recorded. Often serves as a link between field notes and an Occurrence record, such as a specimen collector's number."], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the Taxon to the subject"], ["dynamicProperties", "Structured content about the record key:value encoding IUCN red list category of the taxon at the Global level"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, global unique identifier, URI) of literature associated with the Occurrence"]], "row_count": 33, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[26]/table-wrap[1]#DS1"}}, {"id": "asset:table:pmid:31274982:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a49fdae1e06e94a2e02cdec22f78efb91ae702e13d5382d37cec0f67af024be", "bytes": 3572, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC6597616", "section_index": 10, "section_title": "Description", "row_count": 33, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the Occurrence (as opposed to a particular digital record of the occurrence), constructed from a combination of identifiers in the record that will most closely make the occurrenceID globally unique."], ["scientificName", "The full scientific name, with authorship and date information"], ["scientificNameAuthorship", "The authorship information for the scientificName"], ["vernacularName", "Common or vernacular name in Uruguay (in Spanish)"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified"], ["class", "The full scientific name of the class in which the taxon is classified"], ["order", "The full scientific name of the order in which the taxon is classified"], ["family", "The full scientific name of the family in which the taxon is classified"], ["genus", "The full scientific name of the genus in which the taxon is classified"], ["specificEpithet", "The name of the first or species epithet of the scientificName"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation"], ["countryCode", "The standard code for the country in which the Location occurs"], ["stateProvince", "The name of the next smaller administrative region than country (department) in which the Location occurs"], ["verbatimLocality", "The original textual description of the place"], ["decimalLatitude", "The geographic latitude (in decimal degrees)"], ["decimalLongitude", "The geographic longitude (in decimal degrees)"], ["georeferenceSources", "A list of maps, gazetteers or other resources used to georeference the Location"], ["georeferencedBy", "A person, group or organisation who determined the georeference (spatial representation) for the Location."], ["eventDate", "The date when the event was recorded. Format: dd-mm-yyyy"], ["year", "The four-digit year in which the Event occurred. Format: yyyy"], ["month", "The ordinal month in which the Event occurred. Format: mm"], ["day", "The integer day of the month on which the Event occurred. Format: dd"], ["basisOfRecord", "The specific nature of the data record"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record"], ["collectionCode", "The name or acronym identifying the collection or dataset from which the record was derived"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original Occurrence"], ["recordNumber", "An identifier given to the Occurrence at the time it was recorded. Often serves as a link between field notes and an Occurrence record, such as a specimen collector's number."], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the Taxon to the subject"], ["dynamicProperties", "Structured content about the record key:value encoding IUCN red list category of the taxon at the Global level"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, global unique identifier, URI) of literature associated with the Occurrence"]], "row_count": 33, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[26]/table-wrap[1]#DS1"}}, {"id": "asset:table:pmid:31274982:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cf015dc73b93de998f26bf285b8413698f521a9ae573dfe75619c566d1e486bc", "bytes": 472, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#taxonomic_coverage", "version": null, "note": null, "structure": {"pmcid": "PMC6597616", "section_index": 11, "section_title": "Taxa included", "row_count": 10, "column_count": 3}, "table": {"label": null, "caption": null, "rows": [["Rank", "Scientific Name", "Common Name"], ["kingdom", "Animalia", "Animals"], ["subkingdom", "Eumetazoa", ""], ["phylum", "Chordata", ""], ["subphylum", "Vertebrata", ""], ["superclass", "Tetrapoda", ""], ["class", "Amphibia", "Amphibians"], ["class", "Reptilia", "Reptiles"], ["class", "Aves", "Birds"], ["class", "Mammalia", "Mammals"]], "row_count": 10, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[11]/table-wrap[1]#taxonomic_coverage"}}, {"id": "asset:table:pmid:31274982:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a49fdae1e06e94a2e02cdec22f78efb91ae702e13d5382d37cec0f67af024be", "bytes": 3572, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#DS1", "version": null, "note": "Data set 1.", "structure": {"pmcid": "PMC6597616", "section_index": 26, "section_title": "Description", "row_count": 33, "column_count": 2}, "table": {"label": "Data set 1.", "caption": null, "rows": [["Column label", "Column description"], ["occurrenceID", "An identifier for the Occurrence (as opposed to a particular digital record of the occurrence), constructed from a combination of identifiers in the record that will most closely make the occurrenceID globally unique."], ["scientificName", "The full scientific name, with authorship and date information"], ["scientificNameAuthorship", "The authorship information for the scientificName"], ["vernacularName", "Common or vernacular name in Uruguay (in Spanish)"], ["kingdom", "The full scientific name of the kingdom in which the taxon is classified"], ["phylum", "The full scientific name of the phylum or division in which the taxon is classified"], ["class", "The full scientific name of the class in which the taxon is classified"], ["order", "The full scientific name of the order in which the taxon is classified"], ["family", "The full scientific name of the family in which the taxon is classified"], ["genus", "The full scientific name of the genus in which the taxon is classified"], ["specificEpithet", "The name of the first or species epithet of the scientificName"], ["infraspecificEpithet", "The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation"], ["countryCode", "The standard code for the country in which the Location occurs"], ["stateProvince", "The name of the next smaller administrative region than country (department) in which the Location occurs"], ["verbatimLocality", "The original textual description of the place"], ["decimalLatitude", "The geographic latitude (in decimal degrees)"], ["decimalLongitude", "The geographic longitude (in decimal degrees)"], ["georeferenceSources", "A list of maps, gazetteers or other resources used to georeference the Location"], ["georeferencedBy", "A person, group or organisation who determined the georeference (spatial representation) for the Location."], ["eventDate", "The date when the event was recorded. Format: dd-mm-yyyy"], ["year", "The four-digit year in which the Event occurred. Format: yyyy"], ["month", "The ordinal month in which the Event occurred. Format: mm"], ["day", "The integer day of the month on which the Event occurred. Format: dd"], ["basisOfRecord", "The specific nature of the data record"], ["institutionCode", "The name (or acronym) in use by the institution having custody of the object(s) or information referred to in the record"], ["collectionCode", "The name or acronym identifying the collection or dataset from which the record was derived"], ["catalogNumber", "An identifier (preferably unique) for the record within the dataset or collection"], ["recordedBy", "A list (concatenated and separated) of names of people, groups or organisations responsible for recording the original Occurrence"], ["recordNumber", "An identifier given to the Occurrence at the time it was recorded. Often serves as a link between field notes and an Occurrence record, such as a specimen collector's number."], ["identifiedBy", "A list (concatenated and separated) of names of people, groups or organisations who assigned the Taxon to the subject"], ["dynamicProperties", "Structured content about the record key:value encoding IUCN red list category of the taxon at the Global level"], ["associatedReferences", "A list (concatenated and separated) of identifiers (publication, bibliographic reference, global unique identifier, URI) of literature associated with the Occurrence"]], "row_count": 33, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[26]/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 total number of records collated is 69,380, spanning 673 species and it is available at the Zenodo repository: https://doi.org/10.5281/zenodo.2650169."], "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:31274982", "asset:table:pmid:31274982:1", "asset:table:pmid:31274982:2", "asset:table:pmid:31274982:3", "asset:table:pmid:31274982:4", "asset:table:pmid:31274982:5", "asset:table:pmid:31274982:6"], "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": "2026-10-31T18:15:32Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32286, "completion_tokens": 2030, "cached_tokens": 784}}, "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:31274982", "type": "paper", "label": "pmid:31274982"}, {"id": "source:pmid:31274982", "type": "manuscript", "label": "PMID 31274982 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31274982", "type": "paper", "label": "pmid:31274982"}, {"id": "source:pmid:31274982", "type": "manuscript", "label": "PMID 31274982 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31274982", "type": "extraction", "used": ["source:pmid:31274982"], "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:31274982", "parent_hash": "sha256:0efb7fca2b622366fb836705f7f79b71dad5fb9c1409a4a45b265945f1914c39", "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":"2026-11-04T03:47:24+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}}}