← All .science files
pmid:32561748
Dataset of segmented nuclei in hematoxylin and eosin stained histopathology images of ten cancer types.
Le Hou · Rajarsi Gupta · John S Van Arnam · Yuwei Zhang · Kaustubh Sivalenka · Dimitris Samaras · Tahsin M Kurc · Joel H Saltz
Scientific data · 2020 doi:10.1038/s41597-020-0528-1
Paper
complete
Experiment
partial
Data
partial
Analysis
complete
Execution
absent
Execution evidence has not yet been added to this .science file. Explore its methods, data and open questions to plan the next step.
Record details sci_version · id · kind · revision · content_hash · schema · created_at · updated_at · generator
paper object · 10 fields
authors array · 8 items
claims array · 2 items
[0] object · 6 fields
evidence array · 1 item
[0] object · 3 fields
[1] object · 6 fields
evidence array · 1 item
[0] object · 3 fields
gaps array · 0 items
experiment object · 8 fields
steps array · 3 items
[0] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[1] object · 13 fields
parameters object · 0 fields
inputs array · 0 items
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
parameters object · 0 fields
inputs array · 0 items
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
materials array · 0 items
instruments array · 0 items
reagents array · 0 items
conditions object · 0 fields
gaps array · 1 item
data object · 3 fields
assets array · 7 items
[0] object · 15 fields
structure object · 4 fields
[1] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 12 items
[0] array · 4 items
[1] array · 4 items
[2] array · 4 items
[3] array · 4 items
[4] array · 4 items
[5] array · 4 items
[6] array · 4 items
[7] array · 4 items
[8] array · 4 items
[9] array · 4 items
[10] array · 4 items
[11] array · 4 items
[2] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 7 items
[0] array · 3 items
[1] array · 3 items
[2] array · 3 items
[3] array · 3 items
[4] array · 3 items
[5] array · 3 items
[6] array · 1 item
[3] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 8 items
[0] array · 5 items
[1] array · 2 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[6] array · 6 items
[7] array · 6 items
[4] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 12 items
[0] array · 5 items
[1] array · 2 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[6] array · 6 items
[7] array · 6 items
[8] array · 6 items
[9] array · 6 items
[10] array · 6 items
[11] array · 6 items
[5] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 5 items
[0] array · 4 items
[1] array · 2 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[6] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 5 items
[0] array · 4 items
[1] array · 2 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
gaps array · 0 items
analysis object · 4 fields
methods array · 2 items
[0] object · 10 fields
dsl_operations array · 1 item
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[1] object · 10 fields
dsl_operations array · 2 items
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
targets array · 0 items
gaps array · 0 items
capability object · 3 fields
requirements array · 1 item
[0] object · 6 fields
assay_families array · 9 items
gaps array · 0 items
readiness object · 8 fields
axes object · 3 fields
method object · 5 fields
required_operations array · 1 item
missing_operations array · 0 items
capability object · 4 fields
data object · 6 fields
accessions array · 0 items
resolved_accessions array · 0 items
statements array · 1 item
can_run object · 3 fields
dsl_operations array · 1 item
assets array · 7 items
steps array · 1 item
must_build object · 5 fields
dsl_operations array · 0 items
converters array · 0 items
readers array · 0 items
capabilities array · 0 items
data_gaps array · 1 item
gaps array · 1 item
review object · 5 fields
machine_critique object · 5 fields
reader object · 5 fields
evidence_check object · 2 fields
usage object · 3 fields
stages array · 1 item
[0] object · 4 fields
gaps array · 3 items
provenance object · 7 fields
entities array · 3 items
activities array · 3 items
[0] object · 4 fields
used array · 3 items
[0] object · 3 fields
[1] object · 3 fields
[2] object · 3 fields
[1] object · 4 fields
agents array · 2 items
lineage object · 4 fields
gaps array · 5 items
assays array · 1 item
[0] object · 11 fields
required_operations array · 1 item
source_hashes object · 1 field
evidence array · 1 item
Complete file
{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32561748", "kind": "science-record", "revision": 7, "content_hash": "sha256:782918e14d5202c792181c55083b61ff7c592194e8e4cbe2bf03acf5a07dd5f0", "created_at": "2026-11-01T15:41:03Z", "updated_at": "2026-11-01T22:01:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of segmented nuclei in hematoxylin and eosin stained histopathology images of ten cancer types.", "doi": "10.1038/s41597-020-0528-1", "pmid": "32561748", "authors": ["Le Hou", "Rajarsi Gupta", "John S Van Arnam", "Yuwei Zhang", "Kaustubh Sivalenka", "Dimitris Samaras", "Tahsin M Kurc", "Joel H Saltz"], "journal": "Scientific data", "year": 2020, "abstract": "The distribution and appearance of nuclei are essential markers for the diagnosis and study of cancer. Despite the importance of nuclear morphology, there is a lack of large scale, accurate, publicly accessible nucleus segmentation data. To address this, we developed an analysis pipeline that segments nuclei in whole slide tissue images from multiple cancer types with a quality control process. We have generated nucleus segmentation results in 5,060 Whole Slide Tissue images from 10 cancer types in The Cancer Genome Atlas. One key component of our work is that we carried out a multi-level quality control process (WSI-level and image patch-level), to evaluate the quality of our segmentation results. The image patch-level quality control used manual segmentation ground truth data from 1,356 sampled image patches. The datasets we publish in this work consist of roughly 5 billion quality controlled nuclei from more than 5,060 TCGA WSIs from 10 different TCGA cancer types and 1,356 manually segmented TCGA image patches from the same 10 cancer types plus additional 4 cancer types.", "claims": [{"id": "claim-method", "statement": "In addition, we compute the Pearson correlation and Mean Absolute Error Ratio (MAE%) between the number of nuclei segmented by U-net (defined as p), against the number of nuclei segmented by human annotators (defined as t).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32561748", "locator": "sections[24] \"Evaluation metric\" paragraph 2", "quote": "In addition, we compute the Pearson correlation and Mean Absolute Error Ratio (MAE%) between the number of nuclei segmented by U-net (defined as p), against the number of nuclei segmented by human annotators (defined as t)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Source code is available at on github. It contains the following repositories:\ntraining-data-synthesis Code for generating synthetic training data for nucleus segmentation model training.\ntraining-data-real-patch-extraction Code for converting the format of real training data.\nsegmentation-of-nuclei Code for training a nucleus segmentation model on patches generated by the above-mentioned repositories, and applying a trained model on WSIs.\nDetailed descriptions are in the README files in the Github repository. We also provide a Dockerfile in Github, containing a trained model for easy deployment.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32561748", "locator": "sections[31] \"Code availability\" paragraphs 1-6", "quote": "Source code is available at on github. It contains the following repositories:\ntraining-data-synthesis Code for generating synthetic training data for nucleus segmentation model training.\ntraining-data-real-patch-extraction Code for converting the format of real training data.\nsegmentation-of-nuclei Code for training a nucleus segmentation model on patches generated by the above-mentioned repositories, and applying a trained model on WSIs.\nDetailed descriptions are in the README files in the Github repository. We also provide a Dockerfile in Github, containing a trained model for easy deployment."}], "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:32561748"], "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:32561748", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41597-020-0528-1", "sha256": "sha256:6cf862a5277e9c1a4a779699c80bfc9c730b75f0280636010bebcb896252d4d4", "bytes": 39230, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41597-020-0528-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7305328", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:32561748:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:742d8815b4a5d7050b96c9fd84049d4dbf07af5f50a2dea0568a23af5ece30ce", "bytes": 872, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "The main contribution of our work: nucleus segmentation data in 10 cancer types.", "structure": {"pmcid": "PMC7305328", "section_index": 3, "section_title": "Random segmentation region checking and WSI-level quality control", "row_count": 12, "column_count": 4}, "table": {"label": "Table 1", "caption": "The main contribution of our work: nucleus segmentation data in 10 cancer types.", "rows": [["Abbre.", "Cancer type", "#. slides in total", "#. slides failed QC"], ["BLCA", "Urothelial carcinoma of the bladder", "380", "14"], ["BRCA", "Invasive carcinoma of the breast", "1,096", "88"], ["CESC", "Cervical squamous cell carcinoma and endocervical adenocarcinoma", "249", "54"], ["GBM", "Glioblastoma Multiforme", "772", "40"], ["LUAD", "Lung adenocarcinoma", "540", "59"], ["LUSC", "Lung squamous cell carcinoma", "431", "35"], ["PAAD", "Pancreatic adenocarcinoma", "190", "11"], ["PRAD", "Prostate adenocarcinoma", "387", "19"], ["SKCM", "Skin Cutaneous Melanoma", "470", "64"], ["UCEC", "Endometrial Carcinoma of the Uterine Corpua", "545", "192"], ["Total", "", "5,060", "576"]], "row_count": 12, "column_count": 4, "numeric_cells": 22, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32561748:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4195091a8ba4aa06c8fb688d9b1c58e91f876bcc5ad6f15edd825d5a30d3550b", "bytes": 475, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab2", "version": null, "note": "We categorize WSIs into groups with different segmentation quality levels.", "structure": {"pmcid": "PMC7305328", "section_index": 9, "section_title": "Random segmentation region checking for quality control and rating", "row_count": 7, "column_count": 3}, "table": {"label": "Table 2", "caption": "We categorize WSIs into groups with different segmentation quality levels.", "rows": [["WSI groups", "Percentage of patches with bad segmentations", "#. slides"], ["Best", "0%", "2,346"], ["Good", "0.01–6.67%", "1,246"], ["Adequate", "6.68–13.3%", "593"], ["Problematic", "13.4–20.0%", "302"], ["Unacceptable", ">20.0%", "573"], ["or failed WSI QC"]], "row_count": 7, "column_count": 3, "numeric_cells": 10, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32561748:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ffac09763035e333bce37775e36a7d92a43a9be0867e1a7f84d9a2245f42ad7c", "bytes": 647, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#Tab3", "version": null, "note": "Quantitative assessment of the quality of nucleus segmentation, across 10 cancer types.", "structure": {"pmcid": "PMC7305328", "section_index": 25, "section_title": "Generated segmentation results vs. corrected Mask R-CNN’s results", "row_count": 8, "column_count": 6}, "table": {"label": "Table 3", "caption": "Quantitative assessment of the quality of nucleus segmentation, across 10 cancer types.", "rows": [["WSI groups", "#. patch labels", "Dice", "Instance-Dice", "Nuclei count"], ["Correlat.", "MAE%"], ["Best", "446", "0.797", "0.687", "0.947", "15.2%"], ["Good", "242", "0.789", "0.660", "0.930", "16.1%"], ["Adequate", "128", "0.774", "0.636", "0.915", "17.6%"], ["Problematic", "52", "0.788", "0.625", "0.879", "20.5%"], ["Unacceptable", "103", "0.690", "0.545", "0.718", "33.8%"], ["Excluding unacceptable", "868", "0.790", "0.667", "0.932", "16.2%"]], "row_count": 8, "column_count": 6, "numeric_cells": 30, "header_rows": 2, "locator": "section[25]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:32561748:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4b21039ac45e9f6670aa3c535baba92ef417864adad7b350f681cf6eb00ef78f", "bytes": 798, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[2]#Tab4", "version": null, "note": "Quantitative assessment of the quality of nucleus segmentation, in each of the 10 cancer types.", "structure": {"pmcid": "PMC7305328", "section_index": 25, "section_title": "Generated segmentation results vs. corrected Mask R-CNN’s results", "row_count": 12, "column_count": 6}, "table": {"label": "Table 4", "caption": "Quantitative assessment of the quality of nucleus segmentation, in each of the 10 cancer types.", "rows": [["Cancer Type", "#. patch labels", "Dice", "Instance-Dice", "Nuclei count"], ["Correlat.", "MAE%"], ["BLCA", "95", "0.779", "0.668", "0.941", "20.5%"], ["BRCA", "89", "0.798", "0.649", "0.922", "19.6%"], ["CESC", "79", "0.818", "0.677", "0.947", "13.4%"], ["GBM", "86", "0.809", "0.723", "0.938", "14.4%"], ["LUAD", "88", "0.772", "0.641", "0.896", "17.4%"], ["LUSC", "97", "0.789", "0.665", "0.924", "16.1%"], ["PAAD", "91", "0.785", "0.679", "0.933", "15.8%"], ["PRAD", "96", "0.799", "0.670", "0.940", "14.7%"], ["SKCM", "86", "0.774", "0.675", "0.933", "17.1%"], ["UCEC", "61", "0.778", "0.629", "0.900", "14.6%"]], "row_count": 12, "column_count": 6, "numeric_cells": 50, "header_rows": 2, "locator": "section[25]/table-wrap[2]#Tab4"}}, {"id": "asset:table:pmid:32561748:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2a9ae32c0502a708959691db6f5d015fcc924a8ff1b2280a71a188d81a523f38", "bytes": 527, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#Tab5", "version": null, "note": "Agreements between annotations from different human annotators. This is the performance upper bond of any automatic segmentation method.", "structure": {"pmcid": "PMC7305328", "section_index": 26, "section_title": "Evaluating level of approximation in manual segmentation", "row_count": 5, "column_count": 5}, "table": {"label": "Table 5", "caption": "Agreements between annotations from different human annotators. This is the performance upper bond of any automatic segmentation method.", "rows": [["Inter-annotator", "Dice", "Instance-Dice", "Nuclei count"], ["Correlat.", "MAE%"], ["Annotator A vs. B", "0.760", "0.600", "0.959", "10.8%"], ["Annotator B vs. C", "0.752", "0.622", "0.959", "15.5%"], ["Annotator C vs. A", "0.774", "0.697", "0.954", "12.2%"]], "row_count": 5, "column_count": 5, "numeric_cells": 12, "header_rows": 2, "locator": "section[26]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:32561748:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:abad08683aae944427683c91ffbb60cae7bc693adf70f3dea680b068f2c54f20", "bytes": 436, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[1]#Tab6", "version": null, "note": "Comparing labeling from scratch vs. correcting Mask R-CNN’s results.", "structure": {"pmcid": "PMC7305328", "section_index": 27, "section_title": "Labeling from scratch vs. correcting Mask R-CNN’s results", "row_count": 5, "column_count": 5}, "table": {"label": "Table 6", "caption": "Comparing labeling from scratch vs. correcting Mask R-CNN’s results.", "rows": [["Annotator", "Dice", "Instance-Dice", "Nuclei count"], ["Correlat.", "MAE%"], ["Annotator A", "0.803", "0.664", "0.962", "12.4%"], ["Annotator B", "0.793", "0.631", "0.984", "11.2%"], ["Annotator C", "0.780", "0.683", "0.973", "9.5%"]], "row_count": 5, "column_count": 5, "numeric_cells": 12, "header_rows": 2, "locator": "section[27]/table-wrap[1]#Tab6"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "In addition, we compute the Pearson correlation and Mean Absolute Error Ratio (MAE%) between the number of nuclei segmented by U-net (defined as p), against the number of nuclei segmented by human annotators (defined as t)."}}, {"id": "method-2", "family": "image_quantification", "specific": "segmentation", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.7, "band": "medium", "quote": "segmentation"}}], "targets": [], "gaps": []}, "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": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["Source code is available at on github. It contains the following repositories:\ntraining-data-synthesis Code for generating synthetic training data for nucleus segmentation model training.\ntraining-data-real-patch-extraction Code for converting the format of real training data.\nsegmentation-of-nuclei Code for training a nucleus segmentation model on patches generated by the above-mentioned repositories, and applying a trained model on WSIs.\nDetailed descriptions are in the README files in the Github repository. We also provide a Dockerfile in Github, containing a trained model for easy deployment."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:32561748", "asset:table:pmid:32561748:1", "asset:table:pmid:32561748:2", "asset:table:pmid:32561748:3", "asset:table:pmid:32561748:4", "asset:table:pmid:32561748:5", "asset:table:pmid:32561748:6"], "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": "2026-10-31T19:04:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28959, "completion_tokens": 1751, "cached_tokens": 648}}, "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:32561748", "type": "paper", "label": "pmid:32561748"}, {"id": "source:pmid:32561748", "type": "manuscript", "label": "PMID 32561748 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32561748", "type": "paper", "label": "pmid:32561748"}, {"id": "source:pmid:32561748", "type": "manuscript", "label": "PMID 32561748 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32561748", "type": "extraction", "used": ["source:pmid:32561748"], "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:32561748", "parent_hash": "sha256:51cf223ddcc4ad93358ef624f4a8f2cb9244fc66c2409083a9930c919ef98bc9", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["In addition, we compute the Pearson correlation and Mean Absolute Error Ratio (MAE%) between the number of nuclei segmented by U-net (defined as p), against the number of nuclei segmented by human annotators (defined as t)."], "order_basis": "analysis_only", "id": "assay:1"}]}