{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31947809", "kind": "science-record", "revision": 6, "content_hash": "sha256:69234fb12b1759c85fba7c01702afa4ef8092a61164847c24a85139a800fe79b", "created_at": "2026-11-01T15:40:55Z", "updated_at": "2026-11-01T21:22:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomic Studies for the Investigation of γ-Globin Induction by Decitabine in Human Primary Erythroid Progenitor Cultures.", "doi": "10.3390/jcm9010134", "pmid": "31947809", "authors": ["Andria Theodorou", "Marios Phylactides", "Eleni Katsantoni", "Kostas Vougas", "Spyros D Garbis", "Pavlos Fanis", "Maria Sitarou", "Swee Lay Thein", "Marina Kleanthous"], "journal": "Journal of clinical medicine", "year": 2020, "abstract": "Reactivation of γ-globin is considered a promising approach for the treatment of β-thalassemia and sickle cell disease. Therapeutic induction of γ-globin expression, however, is fraught with lack of suitable therapeutic targets. The aim of this study was to investigate the effects that treatment with decitabine has on the proteome of human primary erythroid cells from healthy and thalassemic volunteers, as a means of identifying new potential pharmacological targets. Decitabine is a known γ-globin inducer, which is not, however, safe enough for clinical use. A proteomic approach utilizing isobaric tags for relative and absolute quantitation (iTRAQ) analysis, in combination with high-pH reverse phase peptide fractionation followed by liquid chromatography-tandem mass spectrometry (LC-MS/MS), was employed to investigate the effects of decitabine treatment. Bioinformatics analysis making use of the Database for Annotation, Visualization and Integrated Discovery (DAVID) was employed for functional annotation of the 192 differentially expressed proteins identified. The data are available via ProteomeXchange with identifier PXD006889. The proteins fall into various biological pathways, such as the NF-κB signaling pathway, and into many functional categories including regulation of cell proliferation, transcription factor and DNA binding, protein stabilization, chromatin modification and organization, and oxidative stress proteins.", "claims": [{"id": "claim-method", "statement": "Log transformation of iTRAQ ratios resulted in normal distribution as checked by Kolmogorov-Smirnof test for normality.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31947809", "locator": "sections[10] \"2.5. Database Search and Data Analysis:\" paragraph 3", "quote": "Log transformation of iTRAQ ratios resulted in normal distribution as checked by Kolmogorov-Smirnof test for normality."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange [18] with identifier PXD006889.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31947809", "locator": "sections[10] \"2.5. Database Search and Data Analysis:\" paragraph 4", "quote": "Data are available via ProteomeXchange [18] with identifier PXD006889."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:31947809"], "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": "complete", "blocked_on": null, "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": ["data:geo:PXD006889"], "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": ["data:geo:PXD006889"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31947809", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/jcm9010134", "sha256": "sha256:058c0332351c787ebafc5072845bef8efba3c80f3376398ab9ca997dac6cc45f", "bytes": 50467, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/jcm9010134", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7019605", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD006889", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PXD006889", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD006889", "version": null, "note": "Data are available via ProteomeXchange [18] with identifier PXD006889.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange [18] with identifier PXD006889.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Mass spec analysis of primary human erythroid cultures (healthy or thalassemic and treated or untreated with Decitabine)", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31947809:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4f02e8fe80b89d49007b96fd9c87d575c4d34df1423db98a09407493297d4155", "bytes": 737, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#jcm-09-00134-t001", "version": null, "note": "The effect of decitabine induction on human erythroid progenitor cell cultures. The effect of decitabine on the levels of fetal hemoglobin levels in primary human erythroid progenitor cells from healthy and thalassemic donors. Fetal hemoglobin (HbF) levels were determined after 6 days of treatment with decitabine (Dec). The results are the average of 12 healthy cultures and 11 thalassemic cultures.", "structure": {"pmcid": "PMC7019605", "section_index": 12, "section_title": "3.1. Decitabine Increases HbF in Primary Erythroid Cultures from Healthy Donors and Thalassemic Patients", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "The effect of decitabine induction on human erythroid progenitor cell cultures. The effect of decitabine on the levels of fetal hemoglobin levels in primary human erythroid progenitor cells from healthy and thalassemic donors. Fetal hemoglobin (HbF) levels were determined after 6 days of treatment with decitabine (Dec). The results are the average of 12 healthy cultures and 11 thalassemic cultures.", "rows": [["Samples", "HbF Levels (% Relative to Un-Treated Control)", "p-Value (Paired t-Test ± Dec)"], ["Healthy", "62.68 ± 28.66", "0.00003"], ["Thalassemic", "43.89 ± 38.72", "0.0027"]], "row_count": 3, "column_count": 3, "numeric_cells": 4, "header_rows": 1, "locator": "section[12]/table-wrap[1]#jcm-09-00134-t001"}}, {"id": "asset:table:pmid:31947809:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:98becebfff38d0946f0e4f709651e41739237ba74c87f54e6d52985fdd685570", "bytes": 1190, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#jcm-09-00134-t002", "version": null, "note": "HbF induction data for the primary erythroid cultures from healthy and thalassemic donors selected for proteomic analysis. For each culture, the HbF levels before treatment with decitabine (un-treated) and after six days of treatment with decitabine are shown. (A) Data for cultures from healthy controls and (B) form thalassemic patients.", "structure": {"pmcid": "PMC7019605", "section_index": 13, "section_title": "3.2. Proteomic Analysis of Primary Human Erythroid Cultures Revealed 192 Proteins that Are Significantly Differentially Expressed Following Treatment with Decitabine", "row_count": 22, "column_count": 4}, "table": {"label": "Table 2", "caption": "HbF induction data for the primary erythroid cultures from healthy and thalassemic donors selected for proteomic analysis. For each culture, the HbF levels before treatment with decitabine (un-treated) and after six days of treatment with decitabine are shown. (A) Data for cultures from healthy controls and (B) form thalassemic patients.", "rows": [["(A)"], ["Healthy Samples"], ["Culture ID", "HbF (%)", "Increase in HbF (% Relative to Un-Treated)"], ["Un-treated", "300 nM Dec"], ["H1", "3.74", "8.01", "114.2"], ["H2", "10.3", "19.65", "90.89"], ["H3", "5.65", "8.86", "56.83"], ["H4", "12.83", "19.73", "53.78"], ["H5", "5.07", "9.1", "79.51"], ["H6", "2.53", "4.22", "66.78"], ["Average", "6.69", "11.6", "77"], ["(B)"], ["Thalassemic Samples"], ["Culture ID", "HbF (%)", "Increase in HbF (% Relative to Un-Treated)"], ["Un-Treated", "300 nM Dec"], ["Th1", "21.79", "31.35", "43.88"], ["Th2", "15.8", "22.65", "43.35"], ["Th3", "18.11", "45.21", "149.68"], ["Th4", "23.48", "36.67", "56.13"], ["Th5", "9.87", "15.46", "56.64"], ["Th6", "17.61", "27", "53.29"], ["Average", "17.78", "29.72", "67.16"]], "row_count": 22, "column_count": 4, "numeric_cells": 44, "header_rows": 0, "locator": "section[13]/table-wrap[1]#jcm-09-00134-t002"}}, {"id": "asset:table:pmid:31947809:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1b2650ad242c4e6ecbe2845ddab8e1fe9963d88af61205cc43f2f224dfcceff2", "bytes": 1042, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#jcm-09-00134-t003", "version": null, "note": "Numbers of significantly differentially expressed proteins. The number of statistically significant differentially expressed proteins identified through comparison of the different culture conditions (treated healthy cultures versus un-treated healthy cultures (ratio 1), treated thalassemic cultures versus un-treated thalassemic cultures (ratio 2)). Expression ratios represent the fold change in protein expression.", "structure": {"pmcid": "PMC7019605", "section_index": 13, "section_title": "3.2. Proteomic Analysis of Primary Human Erythroid Cultures Revealed 192 Proteins that Are Significantly Differentially Expressed Following Treatment with Decitabine", "row_count": 4, "column_count": 9}, "table": {"label": "Table 3", "caption": "Numbers of significantly differentially expressed proteins. The number of statistically significant differentially expressed proteins identified through comparison of the different culture conditions (treated healthy cultures versus un-treated healthy cultures (ratio 1), treated thalassemic cultures versus un-treated thalassemic cultures (ratio 2)). Expression ratios represent the fold change in protein expression.", "rows": [["", "Number of Proteins with p-Value < 0.05", "Up-Regulated Proteins", "Down-Regulated Proteins"], ["Number of Proteins", "% Proteins with Expression Ratio < 1.2", "1.2 < % Proteins with Expression Ratio > 2", "% Proteins with Expression Ratio > 2", "Number of Proteins", "% Proteins with Expression Ratio < 0.8", "% Proteins with Expression Ratio < 0.5"], ["Ratio1", "105", "47", "0", "95.7", "4.3", "58", "100", "0"], ["Ratio2", "110", "55", "65.5", "25.5", "9.1", "55", "92.7", "7.2"]], "row_count": 4, "column_count": 9, "numeric_cells": 22, "header_rows": 2, "locator": "section[13]/table-wrap[2]#jcm-09-00134-t003"}}, {"id": "asset:table:pmid:31947809:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dfb0c346e4b35c7aff36890d5ad581b1c6f45cf890c9f72b91a4176ec2e9bded", "bytes": 2661, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[3]#jcm-09-00134-t004", "version": null, "note": "Functional analysis of the differentially expressed proteins using Database for Annotation, Visualization and Integrated Discovery (DAVID). Bioinformatic analysis of the 105 significantly differentially expressed proteins in response to decitabine in human primary erythroid cultures from healthy donors (Ratio 1) and the 110 significantly differentially expressed proteins in response to decitabine in human primary erythroid cultures from thalassemic donors (Ratio 2). Functional analysis by DAVID of significantly differentially expressed proteins (ratios with p-value < 0.05) using as a reference list of all 2189 proteins identified, grouped proteins according to their biological process (BP), molecular function (MF), and cellular component (CC). In DAVID, protein groups are categorized according to their enrichment scores and corresponding p-value and Benjamini values.", "structure": {"pmcid": "PMC7019605", "section_index": 13, "section_title": "3.2. Proteomic Analysis of Primary Human Erythroid Cultures Revealed 192 Proteins that Are Significantly Differentially Expressed Following Treatment with Decitabine", "row_count": 25, "column_count": 6}, "table": {"label": "Table 4", "caption": "Functional analysis of the differentially expressed proteins using Database for Annotation, Visualization and Integrated Discovery (DAVID). Bioinformatic analysis of the 105 significantly differentially expressed proteins in response to decitabine in human primary erythroid cultures from healthy donors (Ratio 1) and the 110 significantly differentially expressed proteins in response to decitabine in human primary erythroid cultures from thalassemic donors (Ratio 2). Functional analysis by DAVID of significantly differentially expressed proteins (ratios with p-value < 0.05) using as a reference list of all 2189 proteins identified, grouped proteins according to their biological process (BP), molecular function (MF), and cellular component (CC). In DAVID, protein groups are categorized according to their enrichment scores and corresponding p-value and Benjamini values.", "rows": [["", "Functional Clustering", "Enrichment Score", "Count", "p-Value", "Benjamini"], ["Ratio 1", "", "", "", "", ""], ["Transcription factor binding", "MF", "1.56", "11", "0.0045", "0.75"], ["Regulation of cell growth", "BP", "1.4", "5", "0.0081", "0.94"], ["Regulation of cellular component size", "BP", "1.4", "7", "0.015", "0.89"], ["Regulation of protein localization", "BP", "1.32", "5", "0.012", "0.88"], ["Lipid transport", "BP", "1.32", "6", "0.0027", "0.94"], ["Focal adhesion", "CC", "1.13", "5", "0.02", "0.74"], ["Kinase inhibitor activity", "MF", "0.89", "3", "0.068", "0.91"], ["Protein stabilization", "BP", "0.92", "4", "0.0092", "0.91"], ["Protein kinase cascade", "BP", "0.79", "6", "0.035", "0.98"], ["Chromatin organization", "BP", "0.74", "8", "0.047", "0.96"], ["Transcription cofactor activation", "MF", "0.72", "8", "0.012", "0.83"], ["Macromolecular complex assembly", "BP", "0.7", "15", "0.038", "0.97"], ["Regulation of I-kappaB kinase/NF-kappaB cascade", "BP", "0.66", "4", "0.055", "0.97"], ["Regulation of transferase activity", "BP", "0.61", "6", "0.039", "0.96"], ["Ratio 2", "", "", "", "", ""], ["Transition metal ion binding", "MF", "1.52", "19", "1.70 × 102", "9.90 × 101"], ["Zing finger", "MF", "1.52", "10", "2.00 × 102", "9.80 × 101"], ["Cerebral cortex development", "BP", "1.35", "3", "2.50 × 102", "9.80 × 101"], ["Chromatin organization", "BP", "1.35", "12", "2.00 × 104", "1.70 × 101"], ["Transcription", "BP", "1.29", "14", "2.10 × 102", "9.90 × 101"], ["Gamete generation", "BP", "1.13", "6", "4.10 × 102", "9.50 × 101"], ["Chromatin modification", "BP", "0.98", "6", "2.30 × 102", "9.90 × 101"], ["Positive regulation of I-kappaB kinase/NF-kappaB cascade", "BP", "0.95", "4", "3.60 × 102", "9.50 × 101"]], "row_count": 25, "column_count": 6, "numeric_cells": 90, "header_rows": 1, "locator": "section[13]/table-wrap[3]#jcm-09-00134-t004"}}], "gaps": ["asset:data:geo:PXD006889 not downloaded", "asset:data:geo:PXD006889 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Kolmogorov-Smirnof test for normality", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Log transformation of iTRAQ ratios resulted in normal distribution as checked by Kolmogorov-Smirnof test for normality."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Kolmogorov-Smirnof test for normality), 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": "R1", "reachable": true, "accessions": ["PXD006889"], "resolved_accessions": ["PXD006889"], "statements": ["Data are available via ProteomeXchange [18] with identifier PXD006889."], "basis": "The paper names PXD006889 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31947809", "data:geo:PXD006889", "asset:table:pmid:31947809:1", "asset:table:pmid:31947809:2", "asset:table:pmid:31947809:3", "asset:table:pmid:31947809:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD006889"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 39981, "completion_tokens": 1179, "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:31947809", "type": "paper", "label": "pmid:31947809"}, {"id": "source:pmid:31947809", "type": "manuscript", "label": "PMID 31947809 full text"}, {"id": "data:geo:PXD006889", "type": "dataset", "label": "GEO PXD006889"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31947809", "type": "paper", "label": "pmid:31947809"}, {"id": "source:pmid:31947809", "type": "manuscript", "label": "PMID 31947809 full text"}, {"id": "data:geo:PXD006889", "type": "dataset", "label": "GEO PXD006889"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31947809", "type": "extraction", "used": ["source:pmid:31947809"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD006889", "type": "accession_resolution", "used": ["data:geo:PXD006889"], "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:31947809", "parent_hash": "sha256:bf6f08369ddf6471c560d02fc28b59ee68f560e4daf059b30352b4c0607f7445", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD006889 licence not read", "asset:data:geo:PXD006889 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Proteomic Studies for the Investigation of γ-Globin In", "ot, however, safe enough for clinical use. A proteomic approach utilizing isobaric tags for relativ", "y cultures and 11 thalassemic cultures. 3.2. Proteomic Analysis of Primary Human Erythroid Cultures", "cted for proteomic analysis (Table 2). iTRAQ proteomic analysis was performed for the twelve cultur"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["an be suggested that decitabine might affect caspase-mediated apoptotic pathways and ubiquitin li"], "order_basis": "paper_text_order:5500", "id": "assay:2"}]},"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":"2026-11-04T03:11:53+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}}}