{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31438567", "kind": "science-record", "revision": 8, "content_hash": "sha256:f44fa3633c680d41d11ed3ceaec35b99d9cda2de8a8264dbed53df18d714b9e8", "created_at": "2026-11-01T15:40:48Z", "updated_at": "2026-11-01T22:00:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Hyper-Activation of STAT3 Sustains Progression of Non-Papillary Basal-Type Bladder Cancer via FOSL1 Regulome.", "doi": "10.3390/cancers11091219", "pmid": "31438567", "authors": ["Luisa Benerini Gatta", "Laura Melocchi", "Mattia Bugatti", "Francesco Missale", "Silvia Lonardi", "Benedetta Zanetti", "Luca Cristinelli", "Sandra Belotti", "Claudio Simeone", "Roberto Ronca", "Elisabetta Grillo", "Sara Licini", "Debora Bresciani", "Regina Tardanico", "Szeman Ruby Chan", "Emanuele Giurisato", "Stefano Calza", "William Vermi"], "journal": "Cancers", "year": 2019, "abstract": "Urothelial bladder cancer (UBC) are classified into luminal and basal subtypes showing distinct molecular features and clinical behaviour. Recent in silico data have proposed the activation on the Signal Transducer and Activator of Transcription 3 (STAT3) as relevant transcription factor in UBC. To answer this question, we have combined the retrospective analysis of clinical samples, functional assays on cell lines, interrogation of public UBC datasets and a murine model of basal-type UBC. Immunohistochemistry on a retrospective UBC cohort uncovered that STAT3 Y705 phosphorylation (pSTAT3) is significantly increased in infiltrating basal-type UBC compared to luminal UBC. In vitro, STAT3 silencing in UBC cell lines significantly reduced tumor cell viability and invasion. Gene expression profile of UBC cell lines combined with the analysis of the Cancer Genome Atlas (TCGA) and GSE32894 UBC datasets showed that increased expression of a set of STAT3 targets predicts basal-type, propensity to local progression and worse prognosis. MYC and FOSL1 represent relevant STAT3 downstream targets, as validated by their co-localization in pSTAT3+ UBC cancer cells. These findings were largely reproduced in the BBN-induced murine model of basal-type UBC. Of note, FOSL1 protein resulted strongly expressed in the non-papillary UBC pathway and FOSL1-regulated transcripts were significantly enriched in the transition from NMIBC to MIBC, as indicated by the interrogation of the GSE32894 dataset. The blockade of the STAT3 pathway might represent a novel treatment option for these neoplasms. Monitoring pSTAT3 and the downstream targets, particularly FOSL1, could provide meaningful levels of UBC stratification.", "claims": [{"id": "claim-method", "statement": "Classification was performed using regularized logistic regression via elastic-net algorithm.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31438567", "locator": "sections[6] \"2.4. STAT3 Signature Predicts Basal-Type UBC with Poor Prognosis\" paragraph 3", "quote": "Classification was performed using regularized logistic regression via elastic-net algorithm."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw counts for primary solid tumor samples were downloaded from GDC portal harmonized repository using TCGAbiolinks R/Bioconductor package (N = 408 cases). The FFPE samples were removed and only samples corresponding to Luminal or Basal subtype were kept. The duplicated samples counts were averaged (N = 388).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31438567", "locator": "sections[21] \"4.12. Data Preprocessing and Statistical Analysis of the TCGA and GSE32894 Datasets\" paragraph 2", "quote": "Raw counts for primary solid tumor samples were downloaded from GDC portal harmonized repository using TCGAbiolinks R/Bioconductor package (N = 408 cases). The FFPE samples were removed and only samples corresponding to Luminal or Basal subtype were kept. The duplicated samples counts were averaged (N = 388)."}], "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:31438567"], "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:GSE32894"], "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:GSE32894"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31438567", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers11091219", "sha256": "sha256:f2ae89fb8be46af9c1d3493b710fbc348c35fa2ad98cd1fd4a823cfa92476722", "bytes": 80413, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers11091219", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6770563", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE32894", "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=GSE32894", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32894", "version": null, "note": "Raw counts for primary solid tumor samples were downloaded from GDC portal harmonized repository using TCGAbiolinks R/Bioconductor package (N = 408 cases). The FFPE samples were removed and only samples corresponding to Luminal or Basal subtype were kept. The duplicated samples counts were averaged (N = 388).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw counts for primary solid tumor samples were downloaded from GDC portal harmonized repository using TCGAbiolinks R/Bioconductor package (N = 408 cases). The FFPE samples were removed and only samples corresponding to Luminal or Basal subtype were kept. The duplicated samples counts were averaged (N = 388).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM814052", "GSM814053", "GSM814054", "GSM814055", "GSM814056", "GSM814057", "GSM814058", "GSM814059", "GSM814060", "GSM814061", "GSM814062", "GSM814063", "GSM814064", "GSM814065", "GSM814066", "GSM814067", "GSM814068", "GSM814069", "GSM814070", "GSM814071", "GSM814072", "GSM814073", "GSM814074", "GSM814075", "GSM814076", "GSM814077", "GSM814078", "GSM814079", "GSM814080", "GSM814081", "GSM814082", "GSM814083", "GSM814084", "GSM814085", "GSM814086", "GSM814087", "GSM814088", "GSM814089", "GSM814090", "GSM814091", "GSM814092", "GSM814093", "GSM814094", "GSM814095", "GSM814096", "GSM814097", "GSM814098", "GSM814099", "GSM814100", "GSM814101", "GSM814102", "GSM814103", "GSM814104", "GSM814105", "GSM814106", "GSM814107", "GSM814108", "GSM814109", "GSM814110", "GSM814111", "GSM814112", "GSM814113", "GSM814114", "GSM814115", "GSM814116", "GSM814117", "GSM814118", "GSM814119", "GSM814120", "GSM814121", "GSM814122", "GSM814123", "GSM814124", "GSM814125", "GSM814126", "GSM814127", "GSM814128", "GSM814129", "GSM814130", "GSM814131", "GSM814132", "GSM814133", "GSM814134", "GSM814135", "GSM814136", "GSM814137", "GSM814138", "GSM814139", "GSM814140", "GSM814141", "GSM814142", "GSM814143", "GSM814144", "GSM814145", "GSM814146", "GSM814147", "GSM814148", "GSM814149", "GSM814150", "GSM814151", "GSM814152", "GSM814153", "GSM814154", "GSM814155", "GSM814156", "GSM814157", "GSM814158", "GSM814159", "GSM814160", "GSM814161", "GSM814162", "GSM814163", "GSM814164", "GSM814165", "GSM814166", "GSM814167", "GSM814168", "GSM814169", "GSM814170", "GSM814171", "GSM814172", "GSM814173", "GSM814174", "GSM814175", "GSM814176", "GSM814177", "GSM814178", "GSM814179", "GSM814180", "GSM814181", "GSM814182", "GSM814183", "GSM814184", "GSM814185", "GSM814186", "GSM814187", "GSM814188", "GSM814189", "GSM814190", "GSM814191", "GSM814192", "GSM814193", "GSM814194", "GSM814195", "GSM814196", "GSM814197", "GSM814198", "GSM814199", "GSM814200", "GSM814201", "GSM814202", "GSM814203", "GSM814204", "GSM814205", "GSM814206", "GSM814207", "GSM814208", "GSM814209", "GSM814210", "GSM814211", "GSM814212", "GSM814213", "GSM814214", "GSM814215", "GSM814216", "GSM814217", "GSM814218", "GSM814219", "GSM814220", "GSM814221", "GSM814222", "GSM814223", "GSM814224", "GSM814225", "GSM814226", "GSM814227", "GSM814228", "GSM814229", "GSM814230", "GSM814231", "GSM814232", "GSM814233", "GSM814234", "GSM814235", "GSM814236", "GSM814237", "GSM814238", "GSM814239", "GSM814240", "GSM814241", "GSM814242", "GSM814243", "GSM814244", "GSM814245", "GSM814246", "GSM814247", "GSM814248", "GSM814249", "GSM814250", "GSM814251", "GSM814252", "GSM814253", "GSM814254", "GSM814255", "GSM814256", "GSM814257", "GSM814258", "GSM814259", "GSM814260", "GSM814261", "GSM814262", "GSM814263", "GSM814264", "GSM814265", "GSM814266", "GSM814267", "GSM814268", "GSM814269", "GSM814270", "GSM814271", "GSM814272", "GSM814273", "GSM814274", "GSM814275", "GSM814276", "GSM814277", "GSM814278", "GSM814279", "GSM814280", "GSM814281", "GSM814282", "GSM814283", "GSM814284", "GSM814285", "GSM814286", "GSM814287", "GSM814288", "GSM814289", "GSM814290", "GSM814291", "GSM814292", "GSM814293", "GSM814294", "GSM814295", "GSM814296", "GSM814297", "GSM814298", "GSM814299", "GSM814300", "GSM814301", "GSM814302", "GSM814303", "GSM814304", "GSM814305", "GSM814306", "GSM814307", "GSM814308", "GSM814309", "GSM814310", "GSM814311", "GSM814312", "GSM814313", "GSM814314", "GSM814315", "GSM814316", "GSM814317", "GSM814318", "GSM814319", "GSM814320", "GSM814321", "GSM814322", "GSM814323", "GSM814324", "GSM814325", "GSM814326", "GSM814327", "GSM814328", "GSM814329", "GSM814330", "GSM814331", "GSM814332", "GSM814333", "GSM814334", "GSM814335", "GSM814336", "GSM814337", "GSM814338", "GSM814339", "GSM814340", "GSM814341", "GSM814342", "GSM814343", "GSM814344", "GSM814345", "GSM814346", "GSM814347", "GSM814348", "GSM814349", "GSM814350", "GSM814351", "GSM814352", "GSM814353", "GSM814354", "GSM814355", "GSM814356", "GSM814357", "GSM814358", "GSM814359"], "sample_count": 308, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "A Molecular Taxonomy of Urothelial Carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE32894 not downloaded", "asset:data:geo:GSE32894 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Classification was performed using regularized logistic regression via elastic-net algorithm."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student t-test"}}, {"id": "method-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-4", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-5", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox proportional hazards"}}, {"id": "method-6", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-7", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["glm_logit_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: logistic."}, "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": ["GSE32894"], "resolved_accessions": ["GSE32894"], "statements": ["Raw counts for primary solid tumor samples were downloaded from GDC portal harmonized repository using TCGAbiolinks R/Bioconductor package (N = 408 cases). The FFPE samples were removed and only samples corresponding to Luminal or Basal subtype were kept. The duplicated samples counts were averaged (N = 388)."], "basis": "The paper names GSE32894 in GSE32894 UBC dataset and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["glm_logit_fit"], "assets": ["source:pmid:31438567", "data:geo:GSE32894"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE32894"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:15:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 64889, "completion_tokens": 1679, "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:31438567", "type": "paper", "label": "pmid:31438567"}, {"id": "source:pmid:31438567", "type": "manuscript", "label": "PMID 31438567 full text"}, {"id": "data:geo:GSE32894", "type": "dataset", "label": "GEO GSE32894"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31438567", "type": "paper", "label": "pmid:31438567"}, {"id": "source:pmid:31438567", "type": "manuscript", "label": "PMID 31438567 full text"}, {"id": "data:geo:GSE32894", "type": "dataset", "label": "GEO GSE32894"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31438567", "type": "extraction", "used": ["source:pmid:31438567"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE32894", "type": "accession_resolution", "used": ["data:geo:GSE32894"], "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:31438567", "parent_hash": "sha256:8f84fc25cd6db79e37e3748b266cd0fdd6a1549dae2d5c6feee927083b43d0d3", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE32894 licence not read", "asset:data:geo:GSE32894 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": [", interrogation of public UBC datasets and a murine model of basal-type UBC. Immunohistochemistr", "s were largely reproduced in the BBN-induced murine model of basal-type UBC. Of note, FOSL1 prot", "washing, cells were incubated with goat anti-mouse IgG F(ab’)2 fragment Texas Red-conjugated (c"], "order_basis": "paper_text_order:528", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["tasets and a murine model of basal-type UBC. Immunohistochemistry on a retrospective UBC cohort uncovered that", "ctive UBC cohort); Table S3: MIBC subtype by immunohistochemistry score (retrospective UBC cohort); Table S4:", "); Figure S18: Controls for pSTAT3 and FOSL1 IHC; Figure S19: Whole western-blots correspondi", "L1 signature in GSE32894 dataset; Table S12: IHC and western blotting antibodies. Click here"], "order_basis": "paper_text_order:560", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["tific, Waltham, MA, USA). HT-1376 cells were cultured in ATCC-formulated Eagle’s Minimum Essential Me", "protech) for 36 h. Non stimulated cells were cultured in 0.5% FBS containing medium. For BrdU incorpo"], "order_basis": "paper_text_order:3891", "id": "assay:3"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["12K, ATCC). 4.9. Analysis of Cell Viability, Apoptosis and Proliferation To evaluate cell viability", "ed and re-suspended in complete medium. Cell apoptosis was investigated by Pacific Blue™ Annexin V/", "by Pacific Blue™ Annexin V/SYTOX™ AADvanced™ Apoptosis Kit, for flow cytometry (cat. No. A35136, Th", "igure S8: Effects of STAT3 inhibition on the apoptosis of UBC cell lines; Figure S9: Effects of STA"], "order_basis": "paper_text_order:4574", "id": "assay:4"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nexin V/SYTOX™ AADvanced™ Apoptosis Kit, for flow cytometry (cat. No. A35136, Thermo Fisher Scientific),", "SYTOX™ AADvanced™ emissions were analyzed by flow cytometry using a MACS Quant Analyzer (Miltenyi Biotec"], "order_basis": "paper_text_order:5122", "id": "assay:5"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["UBC cell lines growth curves (RT4, 5637) and knockdown of STAT3 in UBC cell lines (5637, HT-1376, R"], "order_basis": "paper_text_order:12420", "id": "assay:6"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ture in GSE32894 dataset; Table S12: IHC and western blotting antibodies. Click here for additional data f"], "order_basis": "paper_text_order:14799", "id": "assay:7"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["glm_logit_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Classification was performed using regularized logistic regression via elastic-net algorithm."], "order_basis": "consumes_earlier_output", "id": "assay:8"}]},"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":"2026-11-04T03:34:12+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}}}