{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39930365", "kind": "science-record", "revision": 2, "content_hash": "sha256:defcf0811d699bc1c50231fb91d4c972ae66b4f8f1fdd61c5cdb2843735b4b97", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:34Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Single-cell characterization of the immune heterogeneity of pulmonary hypertension identifies novel targets for immunotherapy.", "doi": "10.1186/s12865-025-00684-w", "pmid": "39930365", "authors": null, "journal": "BMC immunology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 124561.0, "unit": "cells", "tolerance": null, "source": "chars 898-990 of source sha256 5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00"}, "evidence": [{"asset": "source:pmid:39930365", "locator": "chars 898-990 of source sha256 5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "quote": "In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39930365"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:39930365", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39930365' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39930365", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12865-025-00684-w", "sha256": "sha256:5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12865-025-00684-w", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39930365:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4ec0b38490cf5f1c63a473fdfdc879f7b09a82f6421a3035f3167e9409b7eed1", "bytes": 4872, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab1", "version": null, "note": "Pathway enrichment results for the total population", "structure": {"pmcid": "PMC11809027", "section_index": 15, "section_title": "Integrated scRNA‐seq analysis quantified the diversity of major cell populations in pulmonary hypertension samples", "row_count": 51, "column_count": 5}, "table": {"label": "Table 1", "caption": "Pathway enrichment results for the total population", "rows": [["", "group", "Description", "pvalue", "ratio"], ["GO:0033077", "C1", "T cell differentiation in thymus", "##################", "25"], ["GO:0045059", "C1", "positive thymic T cell selection", "##################", "15"], ["GO:0030217", "C1", "T cell differentiation", "##################", "30"], ["GO:0002260", "C1", "lymphocyte homeostasis", "##################", "20"], ["GO:0070661", "C1", "leukocyte proliferation", "##################", "30"], ["GO:2,000,271", "C2", "positive regulation of fibroblast apoptotic process", "0.005809945", "9.090909091"], ["GO:0006470", "C2", "protein dephosphorylation", "0.006333995", "18.18181818"], ["GO:0045654", "C2", "positive regulation of megakaryocyte differentiation", "0.006389249", "9.090909091"], ["GO:2,001,256", "C2", "regulation of store-operated calcium entry", "0.009281166", "9.090909091"], ["GO:0031643", "C2", "positive regulation of myelination", "0.00985863", "9.090909091"], ["GO:0019886", "C3", "antigen processing and presentation of exogenous peptide antigen via MHC class II", "##################", "33.33333333"], ["GO:0002495", "C3", "antigen processing and presentation of peptide antigen via MHC class II", "4.7068302614186E-13", "33.33333333"], ["GO:0002504", "C3", "antigen processing and presentation of peptide or polysaccharide antigen via MHC class II", "##################", "33.33333333"], ["GO:0002478", "C3", "antigen processing and presentation of exogenous peptide antigen", "##################", "33.33333333"], ["GO:0019884", "C3", "antigen processing and presentation of exogenous antigen", "4.5704204447935E-12", "33.33333333"], ["GO:0071621", "C4", "granulocyte chemotaxis", "##################", "42.10526316"], ["GO:0030595", "C4", "leukocyte chemotaxis", "##################", "47.36842105"], ["GO:0097529", "C4", "myeloid leukocyte migration", "##################", "47.36842105"], ["GO:0097530", "C4", "granulocyte migration", "1.1389874848663E-12", "42.10526316"], ["GO:0030593", "C4", "neutrophil chemotaxis", "##################", "36.84210526"], ["GO:0060706", "C5", "cell differentiation involved in embryonic placenta development", "##################", "15"], ["GO:0001892", "C5", "embryonic placenta development", "0.000105193", "15"], ["GO:0098869", "C5", "cellular oxidant detoxification", "0.000149244", "15"], ["GO:0097284", "C5", "hepatocyte apoptotic process", "0.000200088", "10"], ["GO:0033209", "C5", "tumor necrosis factor-mediated signaling pathway", "0.000244527", "15"], ["GO:0007585", "C6", "respiratory gaseous exchange by respiratory system", "##################", "21.42857143"], ["GO:0043129", "C6", "surfactant homeostasis", "##################", "14.28571429"], ["GO:0048286", "C6", "lung alveolus development", "0.000637117", "14.28571429"], ["GO:0140962", "C6", "multicellular organismal-level chemical homeostasis", "0.001301037", "14.28571429"], ["GO:0007162", "C6", "negative regulation of cell adhesion", "0.001393518", "21.42857143"], ["GO:0030199", "C7", "collagen fibril organization", "##################", "21.05263158"], ["GO:0030198", "C7", "extracellular matrix organization", "##################", "26.31578947"], ["GO:0043062", "C7", "extracellular structure organization", "##################", "26.31578947"], ["GO:0045229", "C7", "external encapsulating structure organization", "##################", "26.31578947"], ["GO:0085029", "C7", "extracellular matrix assembly", "##################", "15.78947368"], ["GO:0006956", "C8", "complement activation", "3.323539105868E-07", "23.52941176"], ["GO:0006958", "C8", "complement activation, classical pathway", "##################", "17.64705882"], ["GO:0002455", "C8", "humoral immune response mediated by circulating immunoglobulin", "##################", "17.64705882"], ["GO:2,000,146", "C8", "negative regulation of cell motility", "##################", "29.41176471"], ["GO:0040013", "C8", "negative regulation of locomotion", "##################", "29.41176471"], ["GO:0035633…41", "C9", "maintenance of blood–brain barrier", "##################", "17.64705882"], ["GO:0007189", "C9", "adenylate cyclase-activating G protein-coupled receptor signaling pathway", "1.0305787824359E-05", "23.52941176"], ["GO:0043114", "C9", "regulation of vascular permeability", "##################", "17.64705882"], ["GO:2,000,351", "C9", "regulation of endothelial cell apoptotic process", "##################", "17.64705882"], ["GO:0072577", "C9", "endothelial cell apoptotic process", "##################", "17.64705882"], ["GO:0071280", "C10", "cellular response to copper ion", "##################", "20"], ["GO:0072012", "C10", "glomerulus vasculature development", "0.00010888", "20"], ["GO:0061437", "C10", "renal system vasculature development", "0.000124078", "20"], ["GO:0061440", "C10", "kidney vasculature development", "0.000124078", "20"], ["GO:0035633…50", "C10", "maintenance of blood–brain barrier", "0.000175563", "20"]], "row_count": 51, "column_count": 5, "numeric_cells": 126, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:39930365:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ff46b13205f9da68d5666d182474b80de132d4b585a360ee2b499d01218e56c3", "bytes": 3562, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#Tab2", "version": null, "note": "Pathway enrichment results for T cells", "structure": {"pmcid": "PMC11809027", "section_index": 16, "section_title": "Comprehensive single-cell transcriptomic analysis reveals T cell heterogeneity and functional dynamics in PAH", "row_count": 36, "column_count": 5}, "table": {"label": "Table 2", "caption": "Pathway enrichment results for T cells", "rows": [["", "group", "Description", "pvalue", "ratio"], ["GO:0002181…1", "C1", "cytoplasmic translation", "##################", "13.80145278"], ["GO:0022613…2", "C1", "ribonucleoprotein complex biogenesis", "9.8571405619293E-11", "8.958837772"], ["GO:0042254…3", "C1", "ribosome biogenesis", "##################", "6.779661017"], ["GO:1,903,039", "C1", "positive regulation of leukocyte cell–cell adhesion", "##################", "6.295399516"], ["GO:0006119", "C1", "oxidative phosphorylation", "##################", "4.600484262"], ["GO:1,903,131", "C2", "mononuclear cell differentiation", "##################", "9.947643979"], ["GO:0002573", "C2", "myeloid leukocyte differentiation", "##################", "6.806282723"], ["GO:0030098", "C2", "lymphocyte differentiation", "##################", "8.90052356"], ["GO:0046631", "C2", "alpha–beta T cell activation", "##################", "5.759162304"], ["GO:0030099", "C2", "myeloid cell differentiation", "##################", "8.90052356"], ["GO:0002181…11", "C3", "cytoplasmic translation", "##################", "56.66666667"], ["GO:0022613…12", "C3", "ribonucleoprotein complex biogenesis", "1.3609964816541E-10", "36.66666667"], ["GO:0042255", "C3", "ribosome assembly", "##################", "20"], ["GO:0042254…14", "C3", "ribosome biogenesis", "##################", "30"], ["GO:0022618", "C3", "protein-RNA complex assembly", "##################", "26.66666667"], ["GO:1,902,175", "C4", "regulation of oxidative stress-induced intrinsic apoptotic signaling pathway", "##################", "5.494505495"], ["GO:0098869", "C4", "cellular oxidant detoxification", "##################", "6.593406593"], ["GO:0007566", "C4", "embryo implantation", "##################", "5.494505495"], ["GO:1,904,851", "C4", "positive regulation of establishment of protein localization to telomere", "##################", "3.296703297"], ["GO:0006457", "C4", "protein folding", "##################", "8.791208791"], ["GO:0008380", "C5", "RNA splicing", "##################", "7.819905213"], ["GO:0000377", "C5", "RNA splicing, via transesterification reactions with bulged adenosine as nucleophile", "3.8781467157288E-12", "5.568720379"], ["GO:0000398", "C5", "mRNA splicing, via spliceosome", "3.8781467157288E-12", "5.568720379"], ["GO:0000375", "C5", "RNA splicing, via transesterification reactions", "##################", "5.568720379"], ["GO:0016032", "C5", "viral process", "##################", "5.805687204"], ["GO:0042267", "C6", "natural killer cell mediated cytotoxicity", "1.7393351392931E-05", "23.07692308"], ["GO:0002228", "C6", "natural killer cell mediated immunity", "##################", "23.07692308"], ["GO:0001732", "C6", "formation of cytoplasmic translation initiation complex", "##################", "15.38461538"], ["GO:0002449", "C6", "lymphocyte mediated immunity", "##################", "30.76923077"], ["GO:0001909", "C6", "leukocyte mediated cytotoxicity", "0.000117358", "23.07692308"], ["GO:0002757", "C7", "immune response-activating signaling pathway", "##################", "17.3553719"], ["GO:0002768", "C7", "immune response-regulating cell surface receptor signaling pathway", "1.2671190772334E-09", "13.2231405"], ["GO:0002429", "C7", "immune response-activating cell surface receptor signaling pathway", "3.464850660679E-09", "12.39669421"], ["GO:0002366", "C7", "leukocyte activation involved in immune response", "##################", "11.57024793"], ["GO:0002263", "C7", "cell activation involved in immune response", "9.7815141145771E-09", "11.57024793"]], "row_count": 36, "column_count": 5, "numeric_cells": 79, "header_rows": 1, "locator": "section[16]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:39930365:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ff1615a06f61c6ee01b13907204d5cd24062ace40ea54f60f587db758234c05c", "bytes": 3537, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab3", "version": null, "note": "Pathway enrichment results for myeloid cells", "structure": {"pmcid": "PMC11809027", "section_index": 17, "section_title": "Comprehensive single-cell transcriptomic analysis reveals myeloid cell heterogeneity and functional dynamics in PAH", "row_count": 36, "column_count": 5}, "table": {"label": "Table 3", "caption": "Pathway enrichment results for myeloid cells", "rows": [["", "group", "Description", "pvalue", "ratio"], ["GO:0045088", "C2", "regulation of innate immune response", "##################", "6.003752345"], ["GO:0050777", "C2", "negative regulation of immune response", "##################", "3.658536585"], ["GO:0006909", "C2", "phagocytosis", "##################", "3.939962477"], ["GO:0045824", "C2", "negative regulation of innate immune response", "6.178202982502E-11", "2.251407129"], ["GO:0002757", "C2", "immune response-activating signaling pathway", "##################", "6.191369606"], ["GO:0072594", "C3", "establishment of protein localization to organelle", "##################", "5.5028463"], ["GO:0008380", "C3", "RNA splicing", "##################", "5.5028463"], ["GO:0016032", "C3", "viral process", "##################", "5.028462998"], ["GO:0009206", "C3", "purine ribonucleoside triphosphate biosynthetic process", "##################", "2.182163188"], ["GO:0009145", "C3", "purine nucleoside triphosphate biosynthetic process", "##################", "2.182163188"], ["GO:0043161", "C4", "proteasome-mediated ubiquitin-dependent protein catabolic process", "##################", "10.16949153"], ["GO:0045333…12", "C4", "cellular respiration", "##################", "6.355932203"], ["GO:0032543", "C4", "mitochondrial translation", "##################", "4.661016949"], ["GO:0009060…14", "C4", "aerobic respiration", "##################", "5.508474576"], ["GO:0022900", "C4", "electron transport chain", "##################", "5.084745763"], ["GO:0002181", "C5", "cytoplasmic translation", "##################", "8.024691358"], ["GO:0009205", "C5", "purine ribonucleoside triphosphate metabolic process", "##################", "9.259259259"], ["GO:0009144", "C5", "purine nucleoside triphosphate metabolic process", "##################", "9.259259259"], ["GO:0009199", "C5", "ribonucleoside triphosphate metabolic process", "##################", "9.259259259"], ["GO:0046034", "C5", "ATP metabolic process", "##################", "8.641975309"], ["GO:0071222", "C6", "cellular response to lipopolysaccharide", "##################", "5.882352941"], ["GO:0071216", "C6", "cellular response to biotic stimulus", "##################", "6.302521008"], ["GO:0071219", "C6", "cellular response to molecule of bacterial origin", "##################", "5.882352941"], ["GO:0032496", "C6", "response to lipopolysaccharide", "##################", "6.722689076"], ["GO:0002237", "C6", "response to molecule of bacterial origin", "##################", "6.722689076"], ["GO:0009060…26", "C7", "aerobic respiration", "##################", "13.7254902"], ["GO:0045333…27", "C7", "cellular respiration", "##################", "13.7254902"], ["GO:0010257", "C7", "NADH dehydrogenase complex assembly", "##################", "7.843137255"], ["GO:0032981", "C7", "mitochondrial respiratory chain complex I assembly", "##################", "7.843137255"], ["GO:0015980", "C7", "energy derivation by oxidation of organic compounds", "##################", "13.7254902"], ["GO:0007015", "C8", "actin filament organization", "##################", "17.85714286"], ["GO:0034975", "C8", "protein folding in endoplasmic reticulum", "##################", "5.357142857"], ["GO:0006119", "C8", "oxidative phosphorylation", "##################", "10.71428571"], ["GO:0042773", "C8", "ATP synthesis coupled electron transport", "1.2773122140192E-05", "8.928571429"], ["GO:0042775", "C8", "mitochondrial ATP synthesis coupled electron transport", "1.2773122140192E-05", "8.928571429"]], "row_count": 36, "column_count": 5, "numeric_cells": 73, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab3"}}], "gaps": ["asset:source:pmid:39930365 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39930365", "asset:table:pmid:39930365:1", "asset:table:pmid:39930365:2", "asset:table:pmid:39930365:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39930365"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "64db5d69ef5805954b99197383883bec39d93a535305ee712e4832edc00b5186", "source_hash": "5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "raw_response_sha256": "sha256:859de837a590f5b48e25058e4027ab7bd84466e30176cd9d66bb096ad3e718b0", "raw_response_chars": 7601}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "51f27395813fb52551edd7ff7a7bc6cfd72d8ab5ab3cb405d0951c74f96d6156", "source_hash": "5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "raw_response_sha256": "sha256:0bcadcef6ffe804be209ca11ce5fb1f1d6d763dcb59dbdbb426f7e9098e9823c", "raw_response_chars": 74650}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "9d3c60eff198814402f0c1060be070400eed0c712d8711f003bdbcea8a033536", "source_hash": "5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "raw_response": "{\"parent_value\":124561,\"unit\":\"cells\",\"evidence\":\"In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\",\"target_result\":\"Approximately 124,561 cells were analyzed.\",\"number_stated\":true}", "reading": {"parent_value": 124561, "unit": "cells", "evidence": "In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.", "target_result": "Approximately 124,561 cells were analyzed.", "number_stated": true, "source_locator": "chars 898-990 of source sha256 5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00"}, "recorded_at": "2026-10-31T15:23:55.280002+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "9a11f100ea90b33880b63d66841066d9fef54c9c413297091315634abb39acd8", "source_hash": "5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states main finding. Source abstract gives approximately 124,561 cells analyzed and 34 clusters. Which headline number? User says single numerical result paper itself states for registered target. Registered target generic: headline numerical result paper states for main finding. Need likely 124,561 cells is headline result. Need exact contiguous quote containing number, whole clause perhaps \"In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\" But asks headline number only value, unit paper prints. Unit \"cells\". Evidence exact contiguous quote. target_result likely \"Approximately 124,561 cells were analyzed.\" Need parent_value number 124561, unit perhaps \"cells\" or maybe no printed unit after number, wording cells. Evidence can include sentence with both numbers but value only one? They want single numerical result. Maybe quote clause around number. Exact: \"In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\" This contains another number 34. They ask headline number only. Could quote whole clause inevitably second number. Is there a narrower exact contiguous quote: \"approximately 124,561 cells were analyzed\" is exact contiguous and contains number, attribution? It states exactly. But instruction says attribution may be carried wording; quote whole clause so reader can check. Full sentence is safe. Yet \"headline number only\" likely output number only in parent_value, but evidence can contain other source numbers if full quote. Maybe choose quote \"In total, approximately 124,561 cells were analyzed\" exact contiguous; it is a clause and target is clearly result. They specifically say exact contiguous quotation containing number; do not shorten it. \"do not shorten it\" might mean quote full clause/sentence, not selectively truncate. Use full sentence.\n\nBut need consider perhaps main headline numerical result is 34 clusters, or 124,561 cells? \"headline numerical result\" replication target likely abstract's key count. Usually benchmark asks extract \"single numerical result\" from paper. The main quantitative result likely number of cells and clusters; but registered target singular headline numerical result. In abstract: \"In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\" Which one is headline? They might expect 124,561 cells because more headline, perhaps \"approximately 124,561 cells were analyzed\" and unit cells. The 34 clusters equally a numerical result. The prompt says \"single numerical result\" likely source contains a target phrase somewhere in paper. But target is generic, perhaps evaluation expects identify headline number from text. Need infer intended.\n\nLet's parse request framing. \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" Registered target: \"the headline numerical result the paper states for its main finding\". This likely generated benchmark where target description could be vague. They expect headline number stated in source. In paper abstract, headline number likely 124,561 cells analyzed and 34 clusters identified. But \"single numerical result\" perhaps one number attached to main finding. There are multiple. Maybe title and abstract first quantitative: 124,561 cells and 34 clusters. Which is headline? Maybe the result is \"approximately 124,561 cells were analyzed and a total 34 clusters were identified\"—two numbers, conflicting with \"single\". They specifically say \"headline number only\", perhaps target number is 124,561 and 34 clusters is a secondary method metric. Need choose 124,561 cells.\n\nCould \"headline numerical result\" be 34 clusters? Abstract:\n\"We performed single-cell RNA sequencing ... In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\"\nA replication's central output might reproduce 34 cell clusters. The cells analyzed is dataset scale, while number of identified clusters is result. But \"headline number\" could be 124,561, often abstract headline first. Registered target explicitly says \"for its main finding\", paper main finding is immune heterogeneity and novel targets GPNMB, with no singular quantitative finding. The only abstract counts are 124,561 cells and 34 clusters. Which is \"headline numerical result\"? Maybe they consider whole sentence's \"approximately 124,561 cells\" as headline. User asks \"the value the paper itself states for the registered target\", no calculated. We need formulate target_result perhaps \"The paper states that approximately 124,561 cells were analyzed.\" number_stated true. Evidence exact quote. Unit \"cells\". Could unit be \"cells analyzed\" to preserve printed semantic unit? Unit the paper prints: \"cells\". Use cells.\n\nJSON valid. Ensure no commas in number issue JSON supports 124561. Evidence exact.</think>\n\n{\"parent_value\":124561,\"unit\":\"cells\",\"evidence\":\"In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.\",\"target_result\":\"The paper states that approximately 124,561 cells were analyzed.\",\"number_stated\":true}", "reading": {"parent_value": 124561, "unit": "cells", "evidence": "In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.", "target_result": "The paper states that approximately 124,561 cells were analyzed.", "number_stated": true, "source_locator": "chars 898-990 of source sha256 5bc7296bc5fe4573a597e65ca5f0624f56c8f39e18c99d00c303bf01d7d42b00"}, "recorded_at": "2026-10-31T15:23:59.684730+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "Approximately 124,561 cells were analyzed and a total of 34 clusters were identified.", "minimax_alt": "In total, approximately 124,561 cells were analyzed and a total 34 clusters were identified.", "decisive": false}, "analysis_methods": {"minimax": ["Single-cell RNA sequencing", "Integrated scRNA-seq analysis", "Clustering analysis", "Monocle2 trajectory analysis", "KEGG and GO enrichment analysis", "SCENIC regulatory-network analysis", "CellChat cell-cell communication analysis", "scMLnet and multiichenet signaling-network analysis", "Spearman correlation analysis"], "minimax_alt": ["single-cell RNA sequencing (scRNA-seq)", "integrated scRNA-seq bioinformatics analysis", "clustering analysis"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:9fc7c22b7141b54d58791a4d6b1160aa7d401165ae6c8e4b6f2b580e81bd2c89", "type": "sep_package", "label": "SEP v1 package for pmid:39930365"}], "activities": [{"id": "activity:conversion:pmid:39930365", "type": "conversion", "used": ["package:9fc7c22b7141b54d58791a4d6b1160aa7d401165ae6c8e4b6f2b580e81bd2c89"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39930365", "parent_hash": "sha256:dc412abcebe780ebb2e8a2c7375a7698f9d41363fb8166a0c317a523b8f34ae5", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39930365 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39930365' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T02:52:28+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}}}