{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33081731", "kind": "science-record", "revision": 7, "content_hash": "sha256:b9ad6acf7e70c11b5d1b3c9b432aefce7509d9c643871c22a6925520924f0a77", "created_at": "2026-11-01T15:41:13Z", "updated_at": "2026-11-01T22:45:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development and validation of a fourteen- innate immunity-related gene pairs signature for predicting prognosis head and neck squamous cell carcinoma.", "doi": "10.1186/s12885-020-07489-7", "pmid": "33081731", "authors": ["Fujun Zhang", "Yu Liu", "Yixin Yang", "Kai Yang"], "journal": "BMC cancer", "year": 2020, "abstract": "BACKGROUND: Immune-related genes is closely related to the occurrence and prognosis of head and neck squamous cell carcinoma (HNSCC). At the same time, immune-related genes have great potential as prognostic markers in many types of cancer. The prognosis of HNSCC is still poor currently, and it may be effective to predict the clinical outcome of HNSCC by immunogenic analysis.\nMETHODS: RNASeq and clinical follow-up information were downloaded from The Cancer Genome Atlas (TCGA), the MINiML format GSE65858 chip expression data was downloaded from NCBI, and immune-related genes was downloaded from the InnateDB database. Immune-related genes in 519 HNSC patients were integrated from TCGA dataset. By using multivariate COX analysis and Lasso regression, robust immune-related gene pairs (IRGPs) that predict clinical outcomes of HNSCC were identified. Finally, a risk prognostic model related to immune gene pair was established and verified by clinical features, test sets and GEO external validation set.\nRESULTS: A total of 699 IRGPs were significantly correlated with the prognosis of HNSCC patients. Fourteen robust IRGPs were finally obtained by Lasso regression and a prognostic risk prediction model was constructed. Risk score of each sample were calculated based on Risk models and divided into the high-risk group (Risk-H) and low Risk group (Risk-L). Risk models were able to stratify the risk in patients with TNM Stage, Age, gender, and smoking history, and the AUC > 0.65 in training set and test set, shows that 14-IRGPs signature in patients with HNSCC has excellent classification performance. In addition, 14-IRGPs had the highest average C index compared with the prognostic characteristics and T, N, and Age of the 3 previously reported HNSCC.\nCONCLUSION: This study constructed 14-IRGPs as a novel prognostic marker for predicting survival in HNSCC patients.", "claims": [{"id": "claim-data-access", "statement": "The datasets used and analysed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33081731", "locator": "sections[30] \"notes\" paragraph 1", "quote": "The datasets used and analysed during the current study are available from the corresponding author on reasonable request."}], "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:33081731"], "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:GSE65858"], "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:GSE65858"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33081731", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-020-07489-7", "sha256": "sha256:60a3769e318a1f49bf50020823b2f76660acca63720946ffd993e944d5427d4a", "bytes": 37537, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-020-07489-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7574345", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE65858", "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=GSE65858", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65858", "version": null, "note": "The datasets used and analysed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and analysed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1607684", "GSM1607685", "GSM1607686", "GSM1607687", "GSM1607688", "GSM1607689", "GSM1607690", "GSM1607691", "GSM1607692", "GSM1607693", "GSM1607694", "GSM1607695", "GSM1607696", "GSM1607697", "GSM1607698", "GSM1607699", "GSM1607700", "GSM1607701", "GSM1607702", "GSM1607703", "GSM1607704", "GSM1607705", "GSM1607706", "GSM1607707", "GSM1607708", "GSM1607709", "GSM1607710", "GSM1607711", "GSM1607712", "GSM1607713", "GSM1607714", "GSM1607715", "GSM1607716", "GSM1607717", "GSM1607718", "GSM1607719", "GSM1607720", "GSM1607721", "GSM1607722", "GSM1607723", "GSM1607724", "GSM1607725", "GSM1607726", "GSM1607727", "GSM1607728", "GSM1607729", "GSM1607730", "GSM1607731", "GSM1607732", "GSM1607733", "GSM1607734", "GSM1607735", "GSM1607736", "GSM1607737", "GSM1607738", "GSM1607739", "GSM1607740", "GSM1607741", "GSM1607742", "GSM1607743", "GSM1607744", "GSM1607745", "GSM1607746", "GSM1607747", "GSM1607748", "GSM1607749", "GSM1607750", "GSM1607751", "GSM1607752", "GSM1607753", "GSM1607754", "GSM1607755", "GSM1607756", "GSM1607757", "GSM1607758", "GSM1607759", "GSM1607760", "GSM1607761", "GSM1607762", "GSM1607763", "GSM1607764", "GSM1607765", "GSM1607766", "GSM1607767", "GSM1607768", "GSM1607769", "GSM1607770", "GSM1607771", "GSM1607772", "GSM1607773", "GSM1607774", "GSM1607775", "GSM1607776", "GSM1607777", "GSM1607778", "GSM1607779", "GSM1607780", "GSM1607781", "GSM1607782", "GSM1607783", "GSM1607784", "GSM1607785", "GSM1607786", "GSM1607787", "GSM1607788", "GSM1607789", "GSM1607790", "GSM1607791", "GSM1607792", "GSM1607793", "GSM1607794", "GSM1607795", "GSM1607796", "GSM1607797", "GSM1607798", "GSM1607799", "GSM1607800", "GSM1607801", "GSM1607802", "GSM1607803", "GSM1607804", "GSM1607805", "GSM1607806", "GSM1607807", "GSM1607808", "GSM1607809", "GSM1607810", "GSM1607811", "GSM1607812", "GSM1607813", "GSM1607814", "GSM1607815", "GSM1607816", "GSM1607817", "GSM1607818", "GSM1607819", "GSM1607820", "GSM1607821", "GSM1607822", "GSM1607823", "GSM1607824", "GSM1607825", "GSM1607826", "GSM1607827", "GSM1607828", "GSM1607829", "GSM1607830", "GSM1607831", "GSM1607832", "GSM1607833", "GSM1607834", "GSM1607835", "GSM1607836", "GSM1607837", "GSM1607838", "GSM1607839", "GSM1607840", "GSM1607841", "GSM1607842", "GSM1607843", "GSM1607844", "GSM1607845", "GSM1607846", "GSM1607847", "GSM1607848", "GSM1607849", "GSM1607850", "GSM1607851", "GSM1607852", "GSM1607853", "GSM1607854", "GSM1607855", "GSM1607856", "GSM1607857", "GSM1607858", "GSM1607859", "GSM1607860", "GSM1607861", "GSM1607862", "GSM1607863", "GSM1607864", "GSM1607865", "GSM1607866", "GSM1607867", "GSM1607868", "GSM1607869", "GSM1607870", "GSM1607871", "GSM1607872", "GSM1607873", "GSM1607874", "GSM1607875", "GSM1607876", "GSM1607877", "GSM1607878", "GSM1607879", "GSM1607880", "GSM1607881", "GSM1607882", "GSM1607883", "GSM1607884", "GSM1607885", "GSM1607886", "GSM1607887", "GSM1607888", "GSM1607889", "GSM1607890", "GSM1607891", "GSM1607892", "GSM1607893", "GSM1607894", "GSM1607895", "GSM1607896", "GSM1607897", "GSM1607898", "GSM1607899", "GSM1607900", "GSM1607901", "GSM1607902", "GSM1607903", "GSM1607904", "GSM1607905", "GSM1607906", "GSM1607907", "GSM1607908", "GSM1607909", "GSM1607910", "GSM1607911", "GSM1607912", "GSM1607913", "GSM1607914", "GSM1607915", "GSM1607916", "GSM1607917", "GSM1607918", "GSM1607919", "GSM1607920", "GSM1607921", "GSM1607922", "GSM1607923", "GSM1607924", "GSM1607925", "GSM1607926", "GSM1607927", "GSM1607928", "GSM1607929", "GSM1607930", "GSM1607931", "GSM1607932", "GSM1607933", "GSM1607934", "GSM1607935", "GSM1607936", "GSM1607937", "GSM1607938", "GSM1607939", "GSM1607940", "GSM1607941", "GSM1607942", "GSM1607943", "GSM1607944", "GSM1607945", "GSM1607946", "GSM1607947", "GSM1607948", "GSM1607949", "GSM1607950", "GSM1607951", "GSM1607952", "GSM1607953"], "sample_count": 270, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Gene expression patterns and TP53 mutations are associated with HPV RNA status, lymph node metastasis, and survival in head and neck cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33081731:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dbb81b7330a314baf5df87a0b371e2cada7946db304cb1895173f53fc5ee0310", "bytes": 903, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Clinical information of data sets", "structure": {"pmcid": "PMC7574345", "section_index": 3, "section_title": "Data collection and processing", "row_count": 27, "column_count": 4}, "table": {"label": "Table 1", "caption": "Clinical information of data sets", "rows": [["Characteristic", "TCGA dataset (n = 517)", "GSE65858 (n = 270)"], ["Age (years)", "<=60", "256", "41"], ["> 60", "261", "229"], ["Survival status", "Living", "297", "176"], ["Dead", "220", "94"], ["Gender", "female", "136", "47"], ["male", "381", "223"], ["Grade", "G 1", "61", "–"], ["G 2", "303", "--"], ["G 3", "124", "--"], ["G 4", "7", "--"], ["pathologic_T", "T 1", "36", "35"], ["T 2", "149", "80"], ["T 3", "136", "58"], ["T 4", "184", "97"], ["pathologic_N", "N 0", "244", "94"], ["N 1", "83", "32"], ["N 2", "162", "132"], ["N 3", "9", "12"], ["pathologic_M", "M 0", "491", "263"], ["M 1/ M X", "23", "7"], ["Tumor stage", "Stage I", "27", "18"], ["Stage II", "81", "37"], ["Stage III", "93", "37"], ["Stage IV", "316", "178"], ["Smoking", "Non-Smoking", "117", "48"], ["Smoking", "388", "222"]], "row_count": 27, "column_count": 4, "numeric_cells": 66, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33081731:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3042210447c63ec83286f5514cabf169c64f052b05d6f81186c81ac4cbe1d630", "bytes": 996, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab2", "version": null, "note": "Sample statistics for training set and validation set", "structure": {"pmcid": "PMC7574345", "section_index": 4, "section_title": "Sample grouping", "row_count": 27, "column_count": 5}, "table": {"label": "Table 2", "caption": "Sample statistics for training set and validation set", "rows": [["Characteristic", "TrainingSet (n = 260)", "TestingSet (n = 257)", "p value"], ["Age (years)", "<=60", "124", "132", "0.38"], ["> 60", "136", "125"], ["Survival status", "Living", "148", "149", "0.878"], ["Dead", "112", "108"], ["Gender", "female", "69", "67", "0.983"], ["male", "191", "190"], ["Grade", "G 1", "29", "32", "0.653"], ["G 2", "152", "151"], ["G 3", "65", "59"], ["G 4", "5", "2"], ["pathologic_T", "T 1", "19", "17", "0.886"], ["T 2", "72", "77"], ["T 3", "70", "66"], ["T 4", "95", "89"], ["pathologic_N", "N 0", "131", "113", "0.004"], ["N 1", "50", "33"], ["N 2", "64", "98"], ["N 3", "6", "3"], ["pathologic_M", "M 0", "244", "247", "0.1"], ["M 1/ M X", "16", "7"], ["Tumor stage", "Stage I", "16", "11", "0.444"], ["Stage II", "40", "41"], ["Stage III", "52", "41"], ["Stage IV", "152", "164"], ["Smoking", "Non-Smoking", "55", "62", "0.511"], ["Smoking", "198", "190"]], "row_count": 27, "column_count": 5, "numeric_cells": 79, "header_rows": 1, "locator": "section[4]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33081731:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7d8020e4aec097366b6ae3d99b1bf266e69d043a67de8a2a1ed6cdf152f39823", "bytes": 1179, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab3", "version": null, "note": "14 IRGPs associated with prognosis", "structure": {"pmcid": "PMC7574345", "section_index": 13, "section_title": "Identification of IRGPs in patients with HNSCC", "row_count": 15, "column_count": 6}, "table": {"label": "Table 3", "caption": "14 IRGPs associated with prognosis", "rows": [["IRGPs", "Coef", "P value", "HR", "Low.95.CI.", "High.95.CI."], ["ARHGAP15_VS_CTSG", "−0.0415", "0.001833936", "0.507", "0.331", "0.778"], ["BTK_VS_CCR7", "−0.0015", "0.000471643", "0.512", "0.352", "0.745"], ["BTK_VS_CTSG", "−0.0371", "0.00101336", "0.512", "0.343", "0.763"], ["CAMK2A_VS_CLEC6A", "−0.0728", "0.001000155", "0.335", "0.175", "0.642"], ["CAMK2A_VS_MASP1", "−0.1535", "2.82E-05", "0.452", "0.312", "0.656"], ["CCL17_VS_SEMA3A", "0.0242", "0.00023524", "2.019", "1.388", "2.935"], ["CDKN2A_VS_CLTC", "0.1432", "0.000924265", "2.866", "1.537", "5.344"], ["DUSP16_VS_TRIM6", "0.1202", "7.15E-05", "4.076", "2.037", "8.154"], ["IKBKB_VS_TRIB3", "0.007", "0.001015171", "1.879", "1.290", "2.738"], ["MASP1_VS_SEMA3A", "0.0033", "0.000200249", "2.122", "1.427", "3.154"], ["MASP1_VS_TRIM6", "0.0728", "0.000288898", "2.307", "1.468", "3.626"], ["ORAI1_VS_SUGT1", "0.0751", "0.000457145", "2.617", "1.528", "4.481"], ["SEMA3A_VS_SLAMF1", "−0.0663", "0.000190953", "0.459", "0.305", "0.691"], ["STAP2_VS_TRIB3", "0.1549", "1.47E-05", "5.593", "2.567", "12.186"]], "row_count": 15, "column_count": 6, "numeric_cells": 75, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:33081731:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0ae3f2b08e487d394ec42c9f6ae208b68fa00dae9cfde95ffa56425a79033ce2", "bytes": 3111, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#Tab4", "version": null, "note": "Univariate and multivariate COX regression analysis identified clinical factors associated with prognosis", "structure": {"pmcid": "PMC7574345", "section_index": 16, "section_title": "Univariate and multivariate analysis of 14-IRGPs signature", "row_count": 41, "column_count": 7}, "table": {"label": "Table 4", "caption": "Univariate and multivariate COX regression analysis identified clinical factors associated with prognosis", "rows": [["Variables", "Univariate analysis", "Multivariable analysis"], ["HR", "95%CI of HR", "P value", "HR", "95%CI of HR", "P value"], ["TCGA training datasets"], ["14-IRGPs signature"], ["Risk score (High/Low)", "2.97", "1.99–4.43", "7.79E-08", "2.53", "1.54–4.13", "0.0002"], ["Age", "1.02", "1.01–1.04", "0.009", "1.02", "0.99–1.04", "0.0550"], ["Gender (Male vs Female)", "0.70", "0.47–1.04", "0.077", "0.94", "0.56–1.5", "0.8236"], ["T3/T4 vs T1/T2", "0.97", "0.66–1.43", "0.895", "0.43", "0.24–0.74", "0.0025"], ["N1/N2/N3 VS N0", "1.21", "0.78–1.85", "0.39", "1.00", "0.59–1.68", "0.9985"], ["Stage IV vs Stage I/ II/III", "1.97", "1.31–2.95", "0.001", "2.65", "1.46–4.78", "0.0012"], ["G3/G4 vs G1/G2", "1.16", "0.76–1.77", "0.491", "0.94", "0.57–1.52", "0.7969"], ["Smoking vs Non-smoking", "0.95", "0.59–1.52", "8.35E-01", "0.85", "0.48–1.49", "0.5707"], ["TCGA validation datasets"], ["14-IRGPs signature"], ["Risk score (High/Low)", "1.96", "1.32–2.91", "7.93E-04", "1.72", "1.12–2.62", "0.0123"], ["Age", "1.02", "0.99–1.04", "0.064", "1.02", "0.99–1.03", "0.1549"], ["Gender (Male vs Female)", "0.77", "0.51–1.17", "0.223", "0.79", "0.47–1.31", "0.3577"], ["T3/T4 vs T1/T2", "1.75", "1.13–2.71", "0.011", "2.05", "1.17–3.59", "0.0120"], ["N1/N2/N3 VS N0", "1.29", "0.87–1.91", "0.209", "1.39", "0.86–2.23", "0.1674"], ["Stage IV vs Stage I/ II/III", "1.36", "0.90–2.05", "0.142", "0.87", "0.49–1.53", "0.6379"], ["G3/G4 vs G1/G2", "1.22", "0.77–1.93", "0.393", "1.20", "0.74–1.93", "0.4439"], ["Smoking vs Non-smoking", "1.33", "0.82–2.15", "0.247", "1.34", "0.77–2.31", "0.2987"], ["TCGA entire datasets"], ["14-IRGPs signature"], ["Risk score (High/Low)", "2.54", "1.92–3.35", "6.51E-11", "2.01", "1.41–2.84", "9.36E-05"], ["Age", "1.02", "1.01–1.03", "0.0013", "1.02", "1.01–1.04", "0.0087"], ["Gender (Male vs Female)", "0.74", "0.55–0.97", "0.034", "0.97", "0.66–1.41", "0.8830"], ["T3/T4 vs T1/T2", "1.28", "0.96–1.70", "0.093", "0.72", "0.47–1.09", "0.1107"], ["N1/N2/N3 VS N0", "1.20", "0.87–1.66", "0.271", "1.07", "0.73–1.54", "0.7276"], ["Stage IV vs Stage I/ II/III", "1.65", "1.24–2.20", "6.20E-04", "1.85", "1.21–2.82", "0.0046"], ["G3/G4 vs G1/G2", "1.15", "0.84–1.57", "0.365", "0.83", "0.58–1.18", "0.3067"], ["Smoking vs Non-smoking", "1.14", "0.81–1.59", "0.45", "1.07", "0.7–1.63", "0.7539"], ["GSE65858"], ["14-IRGPs signature"], ["Risk score (High/Low)", "1.94", "1.27–2.97", "0.0021", "1.90", "1.23–2.92", "0.0035"], ["Age", "1.03", "1.01–1.05", "0.0130", "1.04", "1.01–1.06", "0.0036"], ["Gender (Male vs Female)", "1.05", "0.62–1.77", "0.8680", "1.06", "0.62–1.82", "0.8378"], ["T3/T4 vs T1/T2", "2.92", "1.81–4.72", "1.23E-05", "2.16", "1.26–3.69", "0.0049"], ["N1/N2/N3 VS N0", "2.14", "1.38–3.32", "0.0007", "1.39", "0.73–2.65", "0.3216"], ["Stage IV vs Stage I/ II/III", "2.92", "1.72–4.95", "7.22E-05", "1.55", "0.68–3.55", "0.2987"], ["Smoking vs Non-smoking", "0.94", "0.55–1.59", "0.8210", "1.14", "0.64–2.03", "0.6493"]], "row_count": 41, "column_count": 7, "numeric_cells": 193, "header_rows": 2, "locator": "section[16]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:33081731:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7390049a08fb53dee72bd2d3cf7efb77e28249917daa127b0aa5ec41091eff63", "bytes": 1154, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#Tab5", "version": null, "note": "Comparision for 4 models and clinical features", "structure": {"pmcid": "PMC7574345", "section_index": 19, "section_title": "14-IRGPs was compared with other signatures and clinical features", "row_count": 9, "column_count": 5}, "table": {"label": "Table 5", "caption": "Comparision for 4 models and clinical features", "rows": [["Characteristics", "C-index (95%CI)", "1-year AUC (95%CI)", "3-year AUC (95%CI)", "5-year AUC (95%CI)"], ["T", "0.50 (0.426–0.583, 0.571)", "0.53 (0.47–0.6)", "0.52 (0.46–0.58)", "0.6 (0.52–0.67)"], ["N", "0.53 (0.452–0.610,0.835)", "0.52 (0.47–0.59)", "0.53 (0.47–0.59)", "0.45 (0.46–0.54)"], ["Age", "0.56 (0.490–0.626,0.0096)", "0.62 (0.53–0.71)", "0.55 (0.48–0.62)", "0.51 (0.42–0.6)"], ["AJCC stage", "0.52 (0.434–0.600,0.412)", "0.56 (0.5–0.63)", "0.58 (0.52–0.64)", "0.5 (0.41–0.59)"], ["14-IGPS signature", "0.78 (0.693–0.859,3.65E-08)", "0.73 (0.66–0.8)", "0.82 (0.77–0.87)", "0.75 (0.66–0.82)"], ["3-gene signature", "0.67 (0.579–0.767, 0.002)", "0.56 (0.48–0.63)", "0.64 (0.57–0.71)", "0.63 (0.52–0.74)"], ["6-gene signature", "0.65 (0.560–0.750, 7.07E-5)", "0.56 (0.48–0.63)", "0.63 (0.56–0.7)", "0.71 (0.62–0.81)"], ["3-gene signature", "0.62 (0.519–0.715,0.043", "0.59 (0.50–0.67)", "0.58 (0.51–0.66)", "0.51 (0.40–0.61)"]], "row_count": 9, "column_count": 5, "numeric_cells": 40, "header_rows": 1, "locator": "section[19]/table-wrap[1]#Tab5"}}], "gaps": ["asset:data:geo:GSE65858 not downloaded", "asset:data:geo:GSE65858 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "reordered", "quote": "“The log-rank test and Cox regression analysis were conducted to evaluate overall survival difference between the low risk and high risk groups.”"}}, {"id": "method-2", "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-3", "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-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE65858"], "resolved_accessions": ["GSE65858"], "statements": ["The datasets used and analysed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE65858 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:33081731", "data:geo:GSE65858", "asset:table:pmid:33081731:1", "asset:table:pmid:33081731:2", "asset:table:pmid:33081731:3", "asset:table:pmid:33081731:4", "asset:table:pmid:33081731:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE65858"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:36Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32660, "completion_tokens": 1298, "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:33081731", "type": "paper", "label": "pmid:33081731"}, {"id": "source:pmid:33081731", "type": "manuscript", "label": "PMID 33081731 full text"}, {"id": "data:geo:GSE65858", "type": "dataset", "label": "GEO GSE65858"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33081731", "type": "paper", "label": "pmid:33081731"}, {"id": "source:pmid:33081731", "type": "manuscript", "label": "PMID 33081731 full text"}, {"id": "data:geo:GSE65858", "type": "dataset", "label": "GEO GSE65858"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33081731", "type": "extraction", "used": ["source:pmid:33081731"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE65858", "type": "accession_resolution", "used": ["data:geo:GSE65858"], "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:33081731", "parent_hash": "sha256:2a505f671aee14e1b1a797f86867e4d894ccc51689f1dce1c204f7cb2d64c1d6", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE65858 licence not read", "asset:data:geo:GSE65858 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["e of HNSCC by immunogenic analysis. METHODS: RNASeq and clinical follow-up information were down"], "order_basis": "paper_text_order:494", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["“The log-rank test and Cox regression analysis were conducted to evaluate overall survival difference between the low risk and high risk groups.”"], "order_basis": "consumes_earlier_output", "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":"2026-11-04T03:38:24+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}}}