{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31765425", "kind": "science-record", "revision": 6, "content_hash": "sha256:1d1f26a9acc75865e28f1ff731a5c30c89cd9e7fa401d7347210439b1f12ed06", "created_at": "2026-11-01T15:40:52Z", "updated_at": "2026-11-01T21:22:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "HHIP overexpression inhibits the proliferation, migration and invasion of non-small cell lung cancer.", "doi": "10.1371/journal.pone.0225755", "pmid": "31765425", "authors": ["Jian-Guo Zhao", "Jian-Fang Wang", "Jiang-Feng Feng", "Xue-Ying Jin", "Wan-Li Ye"], "journal": "PloS one", "year": 2019, "abstract": "OBJECTIVE: The primary purpose of this study is to investigate the effect of hedgehog-interacting protein (HHIP) overexpression on the proliferation, migration and invasion of non-small cell lung cancer (NSCLC).\nMETHODS: Firstly, HHIP gene expression data of NSCLC tissues and normal tissues were obtained from GSE18842/GSE19804/GSE43458 databases of the Gene Expression Omnibus (GEO) database and then validated by TCGA NSCLC database in a cohort of 1027 cases of NSCLC patients and 108 cases of normal people. A chi-square test was used to analyze the relationship between HHIP expression and clinicopathological characteristics of NSCLC. The expression levels of HHIP in NSCLC cells were detected by quantitative-real time PCR. The function of HHIP was investigated by a series of in vitro assays. CCK-8, wounding healing, Transwell invasion assay were utilized to explore the mechanisms of HHIP.\nRESULTS: HHIP mRNA were significantly down-regulated in NSCLC in three GEO databases and TCGA database (P<0.05). This result was confirmed in NSCLC cell lines by qRT-PCR analysis, its expression in normal NSCLC cell line BEAS-2B was significantly higher than that in NSCLC cells. Chi-square test results showed that the low expression of HHIP was correlated with gender, cancer type, TNM stage and tumor size. Functional experimental results showed that over-expressing HHIP significantly decreased the ability of cell proliferation, migration and invasion in NSCLC cells (P<0.05).\nCONCLUSION: Overall, the above results indicated that HHIP could regulate proliferation, migration and invasion, and could be used as a judging criterion for identifying NSCLC classification and stage.", "claims": [{"id": "claim-method", "statement": "Paired samples t test was performed for 60 cases of lung adenocarcinoma tissues (2.709±0.323) and adjacent normal tissues (3.163±0.21) in GSE19804 and 44 cases of that (2.128±0.308 vs 2.936±0.188) in GSE18842, finding that the expression of HHIP mRNA in cancer tissues significantly down-regulated(Fig 1A and 1B) and the difference were statistically significant (P < 0.001). Independent samples t test was performed for GSE43458 data, finding that the expression of HHIP mRNA of cancer patients (2.865±0.158) was significantly lower than that of normal people (3.285±0.152) (Fig 1C).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31765425", "locator": "sections[13] \"The expression of HHIP significantly decreased in samples and cell strains of NSCLC patients\" paragraph 2", "quote": "Paired samples t test was performed for 60 cases of lung adenocarcinoma tissues (2.709±0.323) and adjacent normal tissues (3.163±0.21) in GSE19804 and 44 cases of that (2.128±0.308 vs 2.936±0.188) in GSE18842, finding that the expression of HHIP mRNA in cancer tissues significantly down-regulated(Fig 1A and 1B) and the difference were statistically significant (P < 0.001). Independent samples t test was performed for GSE43458 data, finding that the expression of HHIP mRNA of cancer patients (2.865±0.158) was significantly lower than that of normal people (3.285±0.152) (Fig 1C)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All relevant data are within the manuscript and its Supporting Information files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31765425", "locator": "sections[19] \"Data Availability\" paragraph 2", "quote": "All relevant data are within the manuscript and its Supporting Information files."}], "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:31765425"], "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:GSE18842"], "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:GSE18842"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31765425", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0225755", "sha256": "sha256:bb246a9adc3b48947202704fa95a46b6252ef1e648bf57cfa8194f1bdd654aa8", "bytes": 25981, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0225755", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6876884", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE18842", "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=GSE18842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18842", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM466947", "GSM466948", "GSM466949", "GSM466950", "GSM466951", "GSM466952", "GSM466953", "GSM466954", "GSM466955", "GSM466956", "GSM466957", "GSM466958", "GSM466959", "GSM466960", "GSM466961", "GSM466962", "GSM466963", "GSM466964", "GSM466965", "GSM466966", "GSM466967", "GSM466968", "GSM466969", "GSM466970", "GSM466971", "GSM466972", "GSM466973", "GSM466974", "GSM466975", "GSM466976", "GSM466977", "GSM466978", "GSM466979", "GSM466980", "GSM466981", "GSM466982", "GSM466983", "GSM466984", "GSM466985", "GSM466986", "GSM466987", "GSM466988", "GSM466989", "GSM466990", "GSM466991", "GSM466992", "GSM466993", "GSM466994", "GSM466995", "GSM466996", "GSM466997", "GSM466998", "GSM466999", "GSM467000", "GSM467001", "GSM467002", "GSM467003", "GSM467004", "GSM467005", "GSM467006", "GSM467007", "GSM467008", "GSM467009", "GSM467010", "GSM467011", "GSM467012", "GSM467013", "GSM467014", "GSM467015", "GSM467016", "GSM467017", "GSM467018", "GSM467019", "GSM467020", "GSM467021", "GSM467022", "GSM467023", "GSM467024", "GSM467025", "GSM467026", "GSM467027", "GSM467028", "GSM467029", "GSM467030", "GSM467031", "GSM467032", "GSM467033", "GSM467034", "GSM467035", "GSM467036", "GSM467037"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of human lung cancer and control samples", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19804", "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=GSE19804", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19804", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM494556", "GSM494557", "GSM494558", "GSM494559", "GSM494560", "GSM494561", "GSM494562", "GSM494563", "GSM494564", "GSM494565", "GSM494566", "GSM494567", "GSM494568", "GSM494569", "GSM494570", "GSM494571", "GSM494572", "GSM494573", "GSM494574", "GSM494575", "GSM494576", "GSM494577", "GSM494578", "GSM494579", "GSM494580", "GSM494581", "GSM494582", "GSM494583", "GSM494584", "GSM494585", "GSM494586", "GSM494587", "GSM494588", "GSM494589", "GSM494590", "GSM494591", "GSM494592", "GSM494593", "GSM494594", "GSM494595", "GSM494596", "GSM494597", "GSM494598", "GSM494599", "GSM494600", "GSM494601", "GSM494602", "GSM494603", "GSM494604", "GSM494605", "GSM494606", "GSM494607", "GSM494608", "GSM494609", "GSM494610", "GSM494611", "GSM494612", "GSM494613", "GSM494614", "GSM494615", "GSM494616", "GSM494617", "GSM494618", "GSM494619", "GSM494620", "GSM494621", "GSM494622", "GSM494623", "GSM494624", "GSM494625", "GSM494626", "GSM494627", "GSM494628", "GSM494629", "GSM494630", "GSM494631", "GSM494632", "GSM494633", "GSM494634", "GSM494635", "GSM494636", "GSM494637", "GSM494638", "GSM494639", "GSM494640", "GSM494641", "GSM494642", "GSM494643", "GSM494644", "GSM494645", "GSM494646", "GSM494647", "GSM494648", "GSM494649", "GSM494650", "GSM494651", "GSM494652", "GSM494653", "GSM494654", "GSM494655", "GSM494656", "GSM494657", "GSM494658", "GSM494659", "GSM494660", "GSM494661", "GSM494662", "GSM494663", "GSM494664", "GSM494665", "GSM494666", "GSM494667", "GSM494668", "GSM494669", "GSM494670", "GSM494671", "GSM494672", "GSM494673", "GSM494674", "GSM494675"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide screening of transcriptional modulation in non-smoking female lung cancer in Taiwan", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE43458", "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=GSE43458", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43458", "version": null, "note": "All relevant data are within the manuscript and its Supporting Information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All relevant data are within the manuscript and its Supporting Information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1062765", "GSM1062766", "GSM1062767", "GSM1062768", "GSM1062769", "GSM1062770", "GSM1062771", "GSM1062772", "GSM1062773", "GSM1062774", "GSM1062775", "GSM1062776", "GSM1062777", "GSM1062778", "GSM1062779", "GSM1062780", "GSM1062781", "GSM1062782", "GSM1062783", "GSM1062784", "GSM1062785", "GSM1062786", "GSM1062787", "GSM1062788", "GSM1062789", "GSM1062790", "GSM1062791", "GSM1062792", "GSM1062793", "GSM1062794", "GSM1062795", "GSM1062796", "GSM1062797", "GSM1062798", "GSM1062799", "GSM1062800", "GSM1062801", "GSM1062802", "GSM1062803", "GSM1062804", "GSM1062805", "GSM1062806", "GSM1062807", "GSM1062808", "GSM1062809", "GSM1062810", "GSM1062811", "GSM1062812", "GSM1062813", "GSM1062814", "GSM1062815", "GSM1062816", "GSM1062817", "GSM1062818", "GSM1062819", "GSM1062820", "GSM1062821", "GSM1062822", "GSM1062823", "GSM1062824", "GSM1062825", "GSM1062826", "GSM1062827", "GSM1062828", "GSM1062829", "GSM1062830", "GSM1062831", "GSM1062832", "GSM1062833", "GSM1062834", "GSM1062835", "GSM1062836", "GSM1062837", "GSM1062838", "GSM1062839", "GSM1062840", "GSM1062841", "GSM1062842", "GSM1062843", "GSM1062844", "GSM1062845", "GSM1062846", "GSM1062847", "GSM1062848", "GSM1062849", "GSM1062850", "GSM1062851", "GSM1062852", "GSM1062853", "GSM1062854", "GSM1062855", "GSM1062856", "GSM1062857", "GSM1062858", "GSM1062859", "GSM1062860", "GSM1062861", "GSM1062862", "GSM1062863", "GSM1062864", "GSM1062865", "GSM1062866", "GSM1062867", "GSM1062868", "GSM1062869", "GSM1062870", "GSM1062871", "GSM1062872", "GSM1062873", "GSM1062874"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of lung adenocarcinomas and normal lung tissue", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31765425:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:697d4d3a4375385b785407e9d491eb9b89af3f45bd4de92b3335145cb752e92c", "bytes": 1090, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#pone.0225755.t001", "version": null, "note": "The relationship between HHIP expression and clinicopathological features in NSCLC.", "structure": {"pmcid": "PMC6876884", "section_index": 14, "section_title": "Analysis of HHIP expression-related factors", "row_count": 22, "column_count": 6}, "table": {"label": "Table 1", "caption": "The relationship between HHIP expression and clinicopathological features in NSCLC.", "rows": [["Clinicopathological Characteristics", "N", "HHIP High Expression", "HHIP Low Expression", "x2", "P Value"], ["Age", "", "", "", "", ""], ["<60", "171", "81", "90", "0.617", "0.485"], ["≥60", "567", "288", "279"], ["Gender", "", "", "", "", ""], ["Male", "466", "206", "260", "16.978", "0.000"], ["Female", "272", "163", "109"], ["Cancer Type", "", "", "", "", ""], ["Adenocarcinoma", "337", "208", "129", "34.083", "0.000"], ["Carcinoma and others", "401", "161", "240"], ["TNM Stage", "", "", "", "", ""], ["I", "365", "204", "161", "10.023", "0.002"], ["II-IV", "373", "165", "208"], ["Lymph Node Metastasis", "", "", "", "", ""], ["Yes", "272", "124", "148", "3.354", "0.079"], ["No", "466", "245", "221"], ["Hematogenous Metastasis", "", "", "", "", ""], ["Yes", "28", "16", "12", "0.594", "0.564"], ["No", "710", "353", "357"], ["Tumor Diameter", "", "", "", "", ""], ["<3 cm", "190", "121", "69", "19.166", "0.000"], ["≥3 cm", "548", "248", "300"]], "row_count": 22, "column_count": 6, "numeric_cells": 60, "header_rows": 1, "locator": "section[14]/table-wrap[1]#pone.0225755.t001"}}], "gaps": ["asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE43458 not downloaded", "asset:data:geo:GSE43458 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.7, "band": "medium", "quote": "chi-square"}}, {"id": "method-2", "family": null, "specific": null, "label": "Paired samples t test for paired tumor and adjacent-normal samples and independent samples t test for the unpaired GSE43458 comparison; source data were obtained from GEO and TCGA databases.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Paired samples t test was performed for 60 cases of lung adenocarcinoma tissues (2.709±0.323) and adjacent normal tissues (3.163±0.21) in GSE19804 and 44 cases of that (2.128±0.308 vs 2.936±0.188) in GSE18842, finding that the expression of HHIP mRNA in cancer tissues significantly down-regulated(Fig 1A and 1B) and the difference were statistically significant (P < 0.001). Independent samples t test was performed for GSE43458 data, finding that the expression of HHIP mRNA of cancer patients (2.865±0.158) was significantly lower than that of normal people (3.285±0.152) (Fig 1C)."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["chi_square_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: chi_square."}, "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": ["GSE19804", "GSE18842", "GSE43458"], "resolved_accessions": ["GSE19804", "GSE18842", "GSE43458"], "statements": ["All relevant data are within the manuscript and its Supporting Information files."], "basis": "The paper names GSE19804, GSE18842, GSE43458 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["chi_square_test"], "assets": ["source:pmid:31765425", "data:geo:GSE18842", "asset:table:pmid:31765425:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE18842"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 21198, "completion_tokens": 2080, "cached_tokens": 528}}, "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:31765425", "type": "paper", "label": "pmid:31765425"}, {"id": "source:pmid:31765425", "type": "manuscript", "label": "PMID 31765425 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31765425", "type": "paper", "label": "pmid:31765425"}, {"id": "source:pmid:31765425", "type": "manuscript", "label": "PMID 31765425 full text"}, {"id": "data:geo:GSE18842", "type": "dataset", "label": "GEO GSE18842"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31765425", "type": "extraction", "used": ["source:pmid:31765425"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE18842", "type": "accession_resolution", "used": ["data:geo:GSE18842"], "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:31765425", "parent_hash": "sha256:8d4a9ed8931e23f2d6f190a91c1772ad7f13d70d34d46ec926618c6cf85c62b3", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE19804 licence not read", "asset:data:geo:GSE19804 not downloaded", "asset:data:geo:GSE43458 licence not read", "asset:data:geo:GSE43458 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["investigated by a series of in vitro assays. CCK-8, wounding healing, Transwell invasion assay", "rom Shanghai Beinuo Biotechnology Co., Ltd.; CCK-8 kit was purchased from Shanghai Beyotime Bio"], "order_basis": "paper_text_order:858", "id": "assay:1"}, {"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": ["ulture BEAS-2B, H1975, HCC827, H226 and H385 cell lines were cultured in RPMI-1640 culture solution containing 10%", "H1975, HCC827, H226 and H385 cell lines were cultured in RPMI-1640 culture solution containing 10% FB"], "order_basis": "paper_text_order:2661", "id": "assay:2"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["g cancer was investigated. Three lung cancer microarray datasets were obtained from GEO database in"], "order_basis": "paper_text_order:3597", "id": "assay:3"}, {"role": "analysis", "definition_id": "contingency_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["chi_square_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["chi-square"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T02:57:49+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}}}