{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39801827", "kind": "science-record", "revision": 2, "content_hash": "sha256:10e2387764557015c39437c9b672684d14eb9d5c9d0d259df27a077f3fe7cd40", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:32Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Radiotherapy-induced Hypothalamic-Pituitary axis dysfunction in adult Brain, head and neck and skull base tumor patients – A systematic review and Meta-Analysis", "doi": "10.1016/j.ctro.2024.100900", "pmid": "39801827", "authors": null, "journal": "Clinical and Translational Radiation Oncology", "year": 2024, "abstract": null, "claims": [{"id": "claim-1", "statement": "the pooled prevalence of hypothalamic-pituitary axis dysfunction after radiotherapy for brain, head and neck and skull base tumours", "kind": "quantitative", "state": "complete", "target": {"value": 0.61, "unit": "prevalence", "tolerance": null, "source": "chars 19696-19826 of source sha256 f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755"}, "evidence": [{"asset": "source:pmid:39801827", "locator": "chars 19696-19826 of source sha256 f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "quote": "By means of random effects meta-regression, a prevalence of 0.61 (95 % CI 0.44–0.75) for insufficiency on any axis was calculated."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the pooled prevalence of hypothalamic-pituitary axis dysfunction after radiotherapy for brain, head and neck and skull base tumours", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39801827"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "data:accession_absent", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the source data behind the published result in pmid:39801827"], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": ["the source data behind the published result in pmid:39801827", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39801827", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.ctro.2024.100900", "sha256": "sha256:f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.ctro.2024.100900", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind the published result in pmid:39801827", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind the published result in pmid:39801827", "structure": {"material_kind": "dataset", "access_state": "not_identified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "asset:table:pmid:39801827:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a73172c6fb3261d6ce78d84df757e20bc0aaa9039b20783a7dea92f2b6bc011f", "bytes": 1251, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t0005", "version": null, "note": "Allocation of quality criteria related to NOS scale.", "structure": {"pmcid": "PMC11721507", "section_index": 4, "section_title": "Data review and analysis and risk of bias assessment", "row_count": 13, "column_count": 3}, "table": {"label": "Table 1", "caption": "Allocation of quality criteria related to NOS scale.", "rows": [["NOS criterion", "Assessed quality criterion", "points"], ["Selection"], ["Representativeness of the exposed cohort", "Age 17 or higher described", "1"], ["Selection of the non-exposed cohort", "No non-exposed cohorts (no radiotherapy) were used for this review", "skipped"], ["Ascertainment of exposure", "Dose to pituitary, hypothalamus or HP-axis described", "1"], ["Demonstration that outcome of interest was not present at start of the study", "Absence of endocrine insufficiency at the start of the study described", "1"], ["Comparability"], ["Comparability of cohorts on the basis of the design or analysis:", "Endocrine insufficiency of at least 3 different axes described", "1"], ["Insufficiency in more than one axis described", "1"], ["Outcome"], ["Assessment of outcome", "Methodology of endocrine evaluation described", "1"], ["Was follow-up long enough for outcomes to occur?", "Median or mean follow-up period for at least 24 months described", "1"], ["Adequacy of follow-up of cohorts", "Complete follow up of at least 75 % of subjects per axis described", "1"]], "row_count": 13, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[4]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:39801827:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c990ce225aed1683e0b268f90536bc0348da7ae10368882c85b15e02324c15e", "bytes": 11069, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[2]#t0010", "version": null, "note": "Patient characteristics, risk of bias assessment, nature and location of the primary tumor, radiation dose to tumor and/or HP AXIS, follow-up period, method of endocrine evaluation and additional treatment modalities. Publications with * were excluded from the meta-analysis. Abbreviations: NSCLC: Non-small cell lung carcinoma; SCLC: small cell lung carcinoma; NPC: nasopharyngeal carcinoma; BM: brain metastasis; Gy: Gray; TD: total dose; PCI: prophylactic cranial irradiation; WBRT: whole brain radiotherapy; SRS: stereotactic radiosurgery; RT: radiotherapy; SRT: stereotactic radiotherapy; FSRT: fractionated stereotactic radiotherapy; IMRS: intensity-modulated radiosurgery; gEUD: generalized equivalent uniform dose; RBE: relative biological effectiveness; IDL: isodose line; IGF-1: insulin-like growth factor; LH: luteinizing hormone; FSH: follicle stimulating hormone; SHBG: sex hormone binding globulin; PRL: prolactin; TSH: thyroid stimulating hormone; fT4: free T4; ACTH: adrenocorticotrophic hormone; GH: growth hormone; ITT: insulin tolerance test; GST: glucose suppression test; GHRH: growth hormone releasing hormone; CV: cardio-vascular; (c)ChT: (concurrent) chemotherapy; TMZ: temozolomide; Dpit : dose to pituitary gland; Dhypo : dose to hypothalamus; Dhpa : dose to hypothalamic-pituitary axis; NA: data not available.", "structure": {"pmcid": "PMC11721507", "section_index": 4, "section_title": "Data review and analysis and risk of bias assessment", "row_count": 23, "column_count": 10}, "table": {"label": "Table 2a", "caption": "Patient characteristics, risk of bias assessment, nature and location of the primary tumor, radiation dose to tumor and/or HP AXIS, follow-up period, method of endocrine evaluation and additional treatment modalities. Publications with * were excluded from the meta-analysis. Abbreviations: NSCLC: Non-small cell lung carcinoma; SCLC: small cell lung carcinoma; NPC: nasopharyngeal carcinoma; BM: brain metastasis; Gy: Gray; TD: total dose; PCI: prophylactic cranial irradiation; WBRT: whole brain radiotherapy; SRS: stereotactic radiosurgery; RT: radiotherapy; SRT: stereotactic radiotherapy; FSRT: fractionated stereotactic radiotherapy; IMRS: intensity-modulated radiosurgery; gEUD: generalized equivalent uniform dose; RBE: relative biological effectiveness; IDL: isodose line; IGF-1: insulin-like growth factor; LH: luteinizing hormone; FSH: follicle stimulating hormone; SHBG: sex hormone binding globulin; PRL: prolactin; TSH: thyroid stimulating hormone; fT4: free T4; ACTH: adrenocorticotrophic hormone; GH: growth hormone; ITT: insulin tolerance test; GST: glucose suppression test; GHRH: growth hormone releasing hormone; CV: cardio-vascular; (c)ChT: (concurrent) chemotherapy; TMZ: temozolomide; Dpit : dose to pituitary gland; Dhypo : dose to hypothalamus; Dhpa : dose to hypothalamic-pituitary axis; NA: data not available.", "rows": [["First author, year of publication, [Ref.]", "No. of pts, age (range), gender", "Risk of bias", "Tumor characteristics", "Irradiation", "Single fraction dose", "BED HP structures", "Follow-up period", "Endocrine evaluation", "Other treatment modalities"], ["Gebauer, 2020 [55]", "26,Median 58 (36–81),16F/10 M", "6", "BM from NSCLC (n = 6), breast cancer (n = 3), SCLC (n = 2), urothelial cancer (n = 2) or PCI in SCLC (n = 12). Total pts 25.", "WBRT for BM: TD 36 or 35–37.5 Gy or 40 GY (n = 14); PCI TD 30 Gy (n = 12). Equal on HP-axis due to homogenic dose distribution", "TD 36 or 40 Gy: 2 Gy; TD 35–37.5 Gy: 2.5 Gy", "TD 36 Gy: 60 Gy; TD 40 Gy: 66.67 Gy; TD 35–37.2 Gy: 64.17–68.75 Gy", "Median 20.5 months (6–151 months).", "Early-morning measurement of IGF1, LH, FSH, Testosterone, SHBG (M), 17 beta-estradiol, PRL, TSH, fT4, cortisol, ACTH", "NA"], ["Kyriakakis, 2019 [20]*", "58,Mean 41 (30–52),26F/32 M", "7", "Astrocytoma (n = 32), Oligodendroglioma (n = 12), Glioblastoma (n = 8), Ependymoma (n = 5), Uncategorized glioma (n = 1)", "Dose to tumor 53.9 Gy +/- 5.6 Gy;Mean Dhpa 36.7 Gy +/- 15.9 Gy", "2 Gy", "Mean Dhpa 61.17 Gy", "Mean 98.4 months (36–161)", "ITT and GST (ACTH, GH). Basal serum levels LH/FSH, TSH, fT4, PRL, testosterone, estradiol", "Surgery + RT (n = 20); Chemo + RT (n = 6); Surgery + chemo + RT (n = 25)"], ["Kyriakakis, 2016 [24]", "107,Mean 40 (27–53),52F/55 M", "7", "Glioma (n = 60), Meningioma (n = 22), Medulloblastoma (n = 9), Pinealoma (n = 8), Other primary (n = 7), No histology (n = 1)", "Photons: Mean dose to tumor 54 Gy (n = 101); 30–50 Gy (n = 16), > 50 Gy (n = 83), unknown (n = 2); Protons: 74 Gy (n = 1), 77 Gy (n = 1), unknown dose (n = 2); Photons + protons (n = 1) 71 Gy, SRS (n = 1)", "NA", "NA", "Median 96 months (63–132)", "ITT and GST (ACTH, GH). Basal serum levels LH, FSH, TSH. PRL, IGF-1, fT4, testosterone, estradiol", "Surgery + RT (n = 54); Chemo + RT (n = 5); Surgery + RT + chemo (n = 34),"], ["Ratnasingam, 2015 [26]", "50,Mean 57 (44–69),19F/31 M", "8", "NPC stage I-IV", "Mean dose 66 Gy +/- 3.2 Gy facio-cervical; Mean dose 62 Gy +/- 2.9 Gy anterior neck;Minimum Dpit 40 Gy.", "2 Gy", "Minimum Dpit 80 Gy", "Median 96 months (36–252 months)", "Early-morning (fasting) baseline measurement of cortisol, fT4, TSH, PRL, LH, FSH, estradiol, testosterone, renal function. ITT on second visit", "Chemo + RT (n = 36); RT alone (n = 14);"], ["Appelman-Dijkstra, 2014 [27]", "80,Median 47 (18–89),", "6", "Brain (n = 40, 18F/22 M), NPC (n = 15, 4F/11 M), cerebral metastasis (n = 2), Meningioma (n = 14), other (n = 9)", "Cerebral mean dose 55.8 Gy +/- 4.4 Gy (46–62), NPC mean dose 63 Gy +/- 9.8 Gy (40–70), other mean dose 53 Gy +/- 7 Gy (40–69).Mean Dpit 56.3 Gy (40–70)", "NA", "NA", "Median 72 months (6–420)", "Early-morning (fasting) ITT measurement of IGF-1, GH, TSH, fT4, ACTH, cortisol, LH, FSH, estradiol, testosterone, SHBG, PRL, renal and liver function, CV parameters", "NA"], ["Huang, 2013 [19]", "98, Median 47 (17–70), 28F/70 M", "6", "NPC", "Mean Dpit 51.2 Gy (40–70 Gy)", "NA", "NA", "Median 17 months (6–51)", "Early morning measurements", "Chemo + RT (n = 92)"], ["Hauptman, 2012 [56]", "15, Median 56 (29–74), 7F/8 M", "3", "Chordomas & chondrosarcomas", "SRT 53–84 Gy (n = 10), SRS (n = 5). 1 patient SRT 67.6 Gy at 95 % IDL", "SRT 2 Gy, 1.9 Gy, 2.3 Gy. SRS single fractions of 15, 18, 20, 19, 16 Gy", "NA", "54 months", "NA", "Surgery n = 15; (100 %)"], ["Madaschi, 2011 [22]", "26, Median 39 (33–47),12F/14 M", "6", "Gliomas, meningiomas, neuroectodermal tumors. 26 RT, 6 controls", "RT dose to target volume: 59.4 Gy (50.1–60)Median Dhpa: 41.8 Gy (30.7–49.8 Gy)", "2 Gy", "Median Dhpa 69.67 Gy", "HP-axis dysfunction at median 32 months (12–111)", "GHRH + arginine test: IGF-1, ACTH and cortisol, PRL, TSH, fT4, testosterone, estradiol", "Surgery + RT (n = 15)Surgery + chemo + RT (n = 11)"], ["Löfdahl, 2012 [57]", "15, Median56 (32–66),4F/11 M", "4", "Oropharyngeal cancer (n = 13), epipharyngeal cancer (n = 2)", "Oropharyngeal: mean Dhypo 1.9 Gy (1.5–2.2 Gy), mean Dpit 2.4 Gy (1.8–3.3 Gy). Epipharyngeal: Dhypo 6.0–9.3 Gy, Dpit 33.5–46.1 Gy.", "1.7 Gy twice a day", "Oropharyngeal; mean Dhypo 2.98 Gy, mean Dpit 4.44 Gy. Epipharyngeal; Dhypo 9.40–14.57 Gy, Dpit 61.98–85.29 Gy.", "72 months (48–120)", "Early morning IGF-1, PRL, testosterone, FSH/LH, fT4, TSH, cortisol. ITT for GH", "Chemo + RT (n = 10)"], ["De Marzi, 2015 [17]", "103 adults", "5", "Chordoma and chondrosarcoma", "Mean Dpit with tox 63.5 +/- 6.8 Gy-RBE (34.0–72.8). Mean gEUD pituitary with tox 65 +/- 5 Gy.", "1.8–––2.0 Gy", "Mean Dpit 120.65–127 Gy", "Minimum 26 months", "NA", "Surgery, post-operative RT; 100 %"], ["Ipekci, 2015 [58]", "30, Mean 42 (33–51),10F/20 M", "6", "NPC", "Mean Dpit 46.2 Gy, mean Dhypo 10.3 Gy", "2 Gy", "Mean Dpit 92.40 Gy, mean Dhypo 17.17 Gy", "Single evaluation at 24.4 months (9.8–133) between RT and testing. 13 pts had second evaluation 12.9 +/- 2.4 months after first evaluation", "ITT after 8 h fasting, early-morning: cortisol, GH, ACTH, gonadotropin, testosterone, estradiol, FSH, LH, fT4, TSH, IGF-1, PRL", "Chemo + RT (n = 28)"], ["Shih, 2015 [23]*", "20, Median 37 (22–56),7F/13 M", "7", "Grade II glioma", "Proton therapy up to 54 Gy (RBE) to tumor or surgical bed. 6 pts > 30 Gy to pituitary, 14 pts < 30 Gy to pituitary", "1.8 Gy (RBE)", "TD 30 Gy = BED 57 Gy to pituitary", "Median 60 months.", "Serum levels of prolactin, IGF-1,TSH, fT4, cortisol, cortisol after cosyntropin stimulation, testosterone, LH, FSH, estradiol", "TMZ: 2/20.Surgery: Gross total res 4/20, subtotal 12/20, biopsy 4/20"], ["Tabrizi, 2019 [21]", "20, Median 37 (22–56),7F/13 M", "5", "Grade II glioma", "Proton therapy up to 54 Gy (RBE) to tumor or surgical bed. Dose range above and under 20 Gy to pituitary or hypothalamus reported", "1.8 Gy (RBE)", "NA", "Median 60 months. Deficiency after median 10.9 months (4.8–37.8)", "Serum levels of prolactin, IGF-1,TSH, fT4, cortisol, cortisol after cosyntropin stimulation, testosterone, LH, FSH, estradiol", "TMZ: 2/20. Surgery: Gross total res 4/20, subtotal 12/20, biopsy 4/20"], ["Partoune, 2021 [29]", "48, Median49 (37–61),45F/3 M", "8", "Skull base meningioma", "Median Dpit: 48.9 Gy (6.0–55.1), median Dhypo: 15.8 Gy (2.0–51.1)", "1.8 Gy", "Median Dpit: 92.91 Gy, median Dhypo: 25.28 Gy", "median 90 months (17–217)", "Early-morning after fasting: TSH, fT4, cortisol, ACTH, IGF-1, LH, FSH, PRL, estradiol, testosterone, GH (ITT)", "NA"], ["Vakilian, 2021 [18]", "36, Median58,16F/20 M", "7", "Skull base, different tumor types: NPC, chordomas, primary brain", "Median dose 54 Gy (50.4–70 Gy) to target volume.Dose threshold of 50 Gy (30 Gy mean dose) to pituitary for development of endocrinopathy.", "NA", "NA", "Median 32 months (18–85)", "IGF-1, PRL, fT4, TSH, Early-morning cortisol, ACTH, FSH/LH, testosterone, estradiol/progesterone", "19 pts with hormone deficiencies: 79 % surgery, 21 % chemo.17 pts without deficiencies (controls): 47 % surgery, 47 % chemo"], ["Jensen, 2010 [59]", "6, Median61 (48–70),5F/1 M", "3", "Cavernous sinus meningioma", "IMRS 14.7–15.7 Gy", "IMRS single fraction dose 14.7–15.7 Gy", "NA", "Median 42 months (13–78)", "Serum measurements of TSH, T4, T3, cortisol, IGF-1, GH, ACTH", "Craniotomy n = 4"], ["McDowell, 2018 [31]", "107, 86 for endocrine screening. Median 57 (32–82), 38F/69 M.", "6", "NPC", "70 Gy to target volume", "2 Gy", "NA", "> 48 months, 4 years after RT", "Early-morning, after fasting. PRL, IGF-1, LH, FSH, fT4, TSH, ACTH, cortisol, testosterone", "cChT (n = 100/107), 93 %"], ["Raymond, 2021 [28]", "52, Mean56 (42–70),42F/10 M", "7", "Skull base meningioma", "Mean dose to tumor 54.1 +/- 1.6.Mean Dhpa 47 +/- 9.4 Gy.", "1.8–––2.0 Gy", "Mean Dhpa 75.20–78.33 Gy.", "Median 84 months (60–120)", "Early-morning cortisol, ACTH, LH, FSH, estradiol, testosterone, IGF-1, GH, TSH, fT3, fT4, PRL", "18 (34.6 %) post-operative RT"], ["Minniti, 2011 [33]", "52, Median56 (34–74),35F/17 M", "5", "Skull base meningioma", "FSRT 50 Gy in 30 fractions. Pituitary fossa included in PTV = 50 Gy.", "1.7 Gy", "Pituitary fossa included in PTV = 92.50 Gy.", "Median 36 months", "Basal hormonal assessment and dynamic testing", "18 post-operative FSRT, 7 pts with pre-existing hypopituitarism"], ["Handisurya, 2019 [25]", "436, Median50 (19–83),198F/238 M", "3", "Gliomas", "54–60 Gy to target volume", "2 Gy", "NA", "> 37 months", "Serum concentrations of TSH, T3, T4, fT3, fT4, FSH, LH, testosterone, estradiol and prolactin", "100 % surgery. 100 % cChT, TMZ + adj TMZ"], ["Sharma, 2020 [32]", "27, Median 67 (47–83), 10F/17 M", "7", "Sinonasal cancer", "<= 60 Gy (n = 10), 66 Gy (n = 12), >= 68 Gy (n = 5). Mean Dpit 29.9 (15.0–68.1) Gy.", "2 Gy", "Mean Dpit 59.80 Gy.", "Median 76.8 months (19.2–133.2)", "Serum levels of LH, FSH, testosterone, estradiol, tT3, T4, PRL, IGF-1, plasma levels TSH and cortisol. 12 pts with corticotropin stimulation test", "surgery (n = 20) 74 % concomitant Cisplatin (n = 6), 22 %"], ["Contrera, 2023 [30]", "50, Mean 54 (31–81), 19F/31 M", "7", "NPC (20), sinonasal cancer (30)", "50 pts included, 76 % IMRT, 24 % IMPT. From 41 pts dosimetric data available. Median target dose 64 Gy (45–70 Gy). Normal pituitary function: mean Dpit 40.9 Gy, mean Dhypo 11.3 Gy. Abnormal pituitary function: mean Dpit 52.4 Gy, mean Dhypo 20.3 Gy", "2.06 Gy", "Normal pituitary function: mean Dpit 83.03 Gy, mean Dhypo 19.06 Gy. Abnormal pituitary function: mean Dpit 106.37 Gy, mean Dhypo 34.24 Gy", "Median 20 months (3–145)", "IGF-1, ACTH, total cortisol, fT4, T3, TSH, FSH, LH, total testosterone, estradiol", "70 % concurrent cisplatin or carboplatin (n = 35)"]], "row_count": 23, "column_count": 10, "numeric_cells": 182, "header_rows": 1, "locator": "section[4]/table-wrap[2]#t0010"}}, {"id": "asset:table:pmid:39801827:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ecd6a15b01f2799c0947eeb1327e12a8dec163772312145dd2bb5a6d9b28f121", "bytes": 5008, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t0015", "version": null, "note": "Pituitary insufficiency per axis and insufficiencies of multiple axes. Abbreviations: B: brain, H&N: head and neck; SB: base of skull; NPC: nasopharyngeal carcinoma; Gy: Gray; RT: radiotherapy; gEUD: generalized equivalent uniform dose; LH: luteinizing hormone; FSH: follicle stimulating hormone; TSH: thyroid stimulating hormone; ACTH: adrenocorticotrophic hormone; GH: growth hormone; Dmax : maximal dose; Dpit : dose to pituitary gland; Dhypo : dose to hypothalamus; NA: data not available.", "structure": {"pmcid": "PMC11721507", "section_index": 7, "section_title": "Systematic literature search", "row_count": 24, "column_count": 12}, "table": {"label": "Table 2b", "caption": "Pituitary insufficiency per axis and insufficiencies of multiple axes. Abbreviations: B: brain, H&N: head and neck; SB: base of skull; NPC: nasopharyngeal carcinoma; Gy: Gray; RT: radiotherapy; gEUD: generalized equivalent uniform dose; LH: luteinizing hormone; FSH: follicle stimulating hormone; TSH: thyroid stimulating hormone; ACTH: adrenocorticotrophic hormone; GH: growth hormone; Dmax : maximal dose; Dpit : dose to pituitary gland; Dhypo : dose to hypothalamus; NA: data not available.", "rows": [["First author, year of publication, [Ref.]", "Localization", "Pituitary insufficiency per axis", "Number of axes involved"], ["", "", "Any", "ACTH", "TSH", "GH", "Hyperprolactinemia", "FSH/LH", "1 axis", "2 axis", "3 axis", "≥ 4 axis"], ["Gebauer, 2020 [55]", "B", "50 % (13/26)", "4.8 % (1/21)", "5.0 % (1/20)", "8 % (2/25)", "26.9 % (7/26)", "37.5 % (9/24)", "35 %", "8 %", "8 %", "NA"], ["Kyriakakis, 2019 [20]", "B", "84.5 % (49/58)", "19.0 % (11/58)", "6.9 % (4/58)", "82.8 % (48/58)", "10.3 % (6/58)", "20.7 % (12/58)", "47 %", "NA", "NA", "38 %"], ["Kyriakakis, 2016 [24]", "B", "88.8 % (95/107)", "23.4 % (25/107)", "11.2 % (12/107)", "86.9 % (93/107)", "15.0 %", "34.6 % (37/107)", "41 %", "33 %", "10 %", "5 %"], ["Ratnasingam, 2015 [26]", "NPC", "82 % (41/50)", "40 % (20/50)", "4 % (2/50)", "78 % (39/50)", "30 % (15/50)", "22 % (11/50)", "30 %", "28 %", "18 %", "6 %"], ["Appelman-Dijkstra, 2014 [27]", "Mixed", "62 %, 47 % after 5 years, 60 % after 10 years, 89 % after 15 years", "31 % (25/80)", "14 % (11/80)", "33 % (27/80)", "21 % (17/80)", "25 % (20/80)", "NA", "NA", "NA", "NA"], ["Huang, 2013 [19]", "NPC", "54.1 % (53/98)", "1.0 % (1/98)", "33.7 % (33/98)", "NA", "11.2 % (11/98)", "20.4 % (20/98) and 0 % (0/98)", "NA", "NA", "NA", "NA"], ["Hauptman, 2011 [56]", "SB", "6.7 % (n = 1)", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA"], ["Madaschi, 2011 [22]", "B", "38 % (10/26)", "19 % (5/26)", "12 % (3/26)", "27 % (7/26)", "0 % (0/26)", "4 % (1/26)", "23 % (6/26)", "8 % (2/26)", "8 % (2/26)", "NA"], ["Löfdahl, 2012 [57]", "H&N", "NA", "NA", "normal", "normal", "NA", "NA", "NA", "NA", "NA", "NA"], ["De Marzi, 2015 [17]", "SB", "gEUD > 65 Gy. 44 % (45/103)", "NA", "gEUD 60 +/- 8 (52–71) Gy. 11 % (5/45)", "NA", "gEUD 63 +/- 9 (34–72) Gy. 29 % (13/45)", "NA", "NA", "NA", "NA", "gEUD 66 +/- 4 (59–75) Gy. 38 % (17/45)"], ["Ipekci, 2015 [58]", "NPC", "93.3 % (28/30)", "73.3 % (22/30)", "26.7 % (8/30)", "76.7 % (23/30)", "43.3 % (13/30)", "6.7 % (2/30)", "20 % (6/30)", "73.3 % (22/30)", "NA", "NA"], ["Shih, 2015 [23]", "B", "NA", "20 % (4/20)", "17 % (3/18)", "0 % (0/16)", "0 % (0/7)", "15 % (2/13)", "NA", "NA", "NA", "NA"], ["Tabrizi, 2019 [21]", "B", "42 % (5/12) at Dmax > 20 Gy, 13 % (1/8) at Dmax < 20 Gy. 30 % (6/20)", "20 % (4/20)", "17 % (3/18)", "NA", "NA", "15 % (2/13)", "NA", "NA", "NA", "NA"], ["Partoune, 2021 [29]", "SB", "Dpit < 45 Gy: 5 %, Dpit > 45 Gy: 61 %, Dhypo < 20 Gy: 28 %, Dhypo > 20 Gy 53 %. 38 % (18/46)", "Dpit < 45 Gy: 0 %, Dpit > 45 Gy: 25 %, Dhypo < 20 Gy: 7 %, Dhypo > 20 Gy: 26 %. 15 % (7/48)", "Dpit < 45 Gy: 7 %, Dpit > 45 Gy: 46 %, Dhypo < 20 Gy: 17 %, Dhypo > 20 Gy: 53 %. 32 % (12/38)", "Dpit < 45 Gy: 5 %, Dpit > 45 Gy: 56 %, Dhypo < 20 Gy: 23 %, Dhypo > 20 Gy: 53 %. 35 % (16/46)", "11 % (5/39)", "Dpit < 45 Gy: 0 %, Dpit > 45 Gy: 46 %, Dhypo < 20 Gy: 16 %, Dhypo > 20 Gy: 50 %28 % (11/39)", "9 % (4/46)", "13 % (6/46)", "4 % (2/46)", "13 % (6/46)"], ["Vakilian, 2021 [18]", "SB", "Mean Dpit < 30 Gy: 0 %; 40 Gy: 11 %; 50 Gy: 21 %; 60 + Gy: 68 %. 53 %", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA"], ["Jensen, 2010 [59]", "SB", "0 %", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA", "NA"], ["McDowell, 2018 [31]", "NPC", "NA", "Low in 3 % (3/86)", "NA", "Low in 55 % (47/86) and elevated in 3 % (3/86).", "Elevated in 15 % (13/86)", "FSH elevated in 7 % (6/86). LH elevated in 5 % (4/86)", "NA", "NA", "1 % (1/86)", "NA"], ["Raymond, 2021 [28]", "SB", "3 years: 19.2 % (10/52), 5 years 31.5 % (16/39), 10 years 60.2 % (22/26)", "3 years: 13.5 % (7/52), 5 years 15.4 % (8/37), 10 years 15.4 % (8/17)", "3 years: 5.8 % (3/52), 5 years 14.0 % (7/35), 10 years 28.0 % (10/18)", "3 years: 5.8 % (3/52), 5 years 9.8 % (5/35), 10 years 13.4 % (6/16)", "3 years: 1.9 % (1/52), 5 years 10.1 % (5/35), 10 years 18.5 % (7/17)", "3 years: 9.6 % (5/52), 5 years 17.8 % (9/37), 10 years 36.9 % (13/20)", "NA", "21 % at 10 years (11/52)", "8 % at 10 years (4/52)", "13 % at 10 years (7/52)"], ["Minniti, 2011 [33]", "SB", "19 % (10/52)", "NA", "NA", "NA", "NA", "NA", "NA", "21 % (11/52)", "NA", "NA"], ["Handisurya, 2019 [25]", "B", "NA", "NA", "10.9 % (22/202)", "NA", "30 % (25/84)", "FSH: 17 % (14/83), LH: 11 % (9/83)", "NA", "NA", "NA", "NA"], ["Sharma, 2020 [32]", "H&N", "22 % (6/27)", "4 % (1/27)", "11 % (3/27)", "15 % (4/27)", "4 % (1/27)", "15 % (4/27)", "7 % (2/27) at mean dose of 23.5 Gy", "11 % (3/27) at mean dose of 36.0 Gy", "NA", "4 % (1/27) at dose of 68.1 Gy"], ["Contrera, 2023 [30]", "NPC, SN", "46 % (23/50)", "2 % (1/50)", "8 % (4/50)", "0 % (0/50)", "30 % (15/50)", "6 % (3/50)", "34 % (17/50)", "22 % (11/50)", "4 % (2/50)", "NA"]], "row_count": 24, "column_count": 12, "numeric_cells": 154, "header_rows": 2, "locator": "section[7]/table-wrap[1]#t0015"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:39801827 not verified", "asset:source:pmid:39801827 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "meta_analysis", "specific": "random effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": ["random_effects_pool"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.7, "band": "medium", "quote": "Literature search of the PubMed database was performed for HP dysfunction after radiotherapy in adult patients. A risk of bias assessment was performed to rate the quality of the included papers. Besides clinical and treatment variables, reported insufficiencies for adrenocorticotrophic hormone, thyroid stimulating hormone, growth hormone, prolactin and follicle stimulating hormone and luteinizing hormone and for insufficiency of any axis were extracted. The prevalence for hormonal insufficiency per axis and for multiple axes was calculated using a random effects meta-regression with a random effect at the study level."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 0.61, "unit": "prevalence", "tolerance": null, "state": "complete"}], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"axis": "method", "tier": "R1", "blocker": null, "detail": {"outcome": "determined", "family": "meta_analysis", "specific_method": "random_effects", "required_operations": ["random_effects_pool"], "basis": "Every DSL operation this method needs already exists."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": ["random_effects_pool"], "assets": ["source:pmid:39801827", "asset:table:pmid:39801827:1", "asset:table:pmid:39801827:2", "asset:table:pmid:39801827:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": [], "data_gaps": ["source:pmid:39801827", "materials:the source data behind the published result in pmid:39801827", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "334acf27f818d2949aef8894fd3cca6d66e2450b101c394cdcfe0530eb2acaac", "source_hash": "f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "raw_response_sha256": "sha256:6d0a79ab8b7922e1115fe291152da399ae0c2452d39cc9a92d5f7ff8d73f664e", "raw_response_chars": 4040}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "04be012a1e19261d22f87ae8cba02d0b35ae6c98f7d6aca1f073af311580f873", "source_hash": "f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "raw_response_sha256": "sha256:92f4b87d6dc51f8d80e8b54247651dbd131489304dab3b0f6df73efc80180c70", "raw_response_chars": 5240}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "71ede2bc093d2691f039e490993347ff2c2d914fdd52d2cdb78e66212c506ae5", "source_hash": "f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "raw_response": "{\"parent_value\":0.61,\"unit\":\"prevalence\",\"evidence\":\"By means of random effects meta-regression, a prevalence of 0.61 (95 % CI 0.44–0.75) for insufficiency on any axis was calculated.\",\"target_result\":\"Pooled prevalence of hypothalamic-pituitary axis dysfunction after radiotherapy for brain, head and neck and skull base tumours\",\"number_stated\":true}", "reading": {"parent_value": 0.61, "unit": "prevalence", "evidence": "By means of random effects meta-regression, a prevalence of 0.61 (95 % CI 0.44–0.75) for insufficiency on any axis was calculated.", "target_result": "Pooled prevalence of hypothalamic-pituitary axis dysfunction after radiotherapy for brain, head and neck and skull base tumours", "number_stated": true, "source_locator": "chars 19696-19826 of source sha256 f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755"}, "recorded_at": "2026-10-31T14:40:46.300616+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3b681f4a473c06d51bafd951c198ca0dd57c271b837a2d425bb0cc90a361ba2c", "source_hash": "f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755", "raw_response": "{\"parent_value\":0.61,\"unit\":\"\",\"evidence\":\"By means of random effects meta-regression, a prevalence of 0.61 (95 % CI 0.44–0.75) for insufficiency on any axis was calculated.\",\"target_result\":\"Pooled prevalence of hypothalamic-pituitary axis insufficiency on any axis was 0.61.\",\"number_stated\":true}", "reading": {"parent_value": 0.61, "unit": "", "evidence": "By means of random effects meta-regression, a prevalence of 0.61 (95 % CI 0.44–0.75) for insufficiency on any axis was calculated.", "target_result": "Pooled prevalence of hypothalamic-pituitary axis insufficiency on any axis was 0.61.", "number_stated": true, "source_locator": "chars 19696-19826 of source sha256 f82a98f608a4a1c4bb9a8f9c7a9620ca126272a8524771ea928075935ecf0755"}, "recorded_at": "2026-10-31T14:41:09.298269+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "Pooled prevalence of insufficiency on any hypothalamic-pituitary axis after radiotherapy: 0.61 (95% CI 0.44–0.75), equivalent to 61%.", "minimax-m3": "After adult radiotherapy for brain, head-and-neck, or skull-base tumors, the pooled prevalence of insufficiency on any hypothalamic-pituitary axis was 0.61 (95% CI 0.44–0.75; 61%). Site-specific pooled prevalences were 0.68 (95% CI 0.45–0.85) for nasopharyngeal carcinoma and other head-and-neck tumors, 0.60 (95% CI 0.28–0.85) for intracerebral tumors, and 0.50 (95% CI 0.23–0.76) for skull-base tumors.", "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Random-effects meta-analysis with random effects at the study level", "Logit transformation of study-level proportions", "Random-effects meta-regression with tumor site as a covariate", "Maximum-likelihood estimation for meta-regression", "Pearson correlation tests", "Newcastle-Ottawa Scale risk-of-bias assessment", "Biologically Equivalent Dose calculation"], "minimax-m3": ["Study-specific calculation of endocrine insufficiency proportions", "Logit transformation of proportions to effect sizes", "Random-effects meta-analysis with a study-level random effect", "Random-effects meta-regression with tumor site as a covariate", "Maximum likelihood estimation for meta-regression", "Newcastle-Ottawa Scale risk-of-bias assessment"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["The meta-analysis estimated the pooled prevalence of insufficiency on any hypothalamic-pituitary axis using a random-effects model.", "The pooled prevalence of insufficiency on any axis was 0.61 (95% CI 0.44–0.75).", "The highest pooled prevalence was for NPC and other head-and-neck tumors at 0.68 (95% CI 0.45–0.85), followed by intracerebral tumors at 0.60 (95% CI 0.28–0.85) and skull-base tumors at 0.50 (95% CI 0.23–0.76).", "Study-level proportions were calculated from the number of patients with insufficiency divided by the number tested, logit-transformed, and pooled using a random-effects meta-analysis.", "A significant positive correlation was observed between insufficiency on any axis and follow-up time (Pearson R = 0.57, p = 0.015).", "No significant correlation was found between dose to the hypothalamic-pituitary region and insufficiency on any axis (Pearson R = 0.16, p = 0.535).", "The review included 22 publications and 1,462 patients, with heterogeneous prospective and retrospective cohorts.", "The effects of surgery and chemotherapy on hypothalamic-pituitary functioning were not included in the meta-analysis results.", "Generalizability was limited by cohort heterogeneity, possible selection bias, multimodal treatment, and incomplete follow-up information."], "minimax-m3": ["The random-effects meta-regression estimated a prevalence of 0.61 (95% CI 0.44–0.75) for insufficiency on any hypothalamic-pituitary axis.", "Pooled prevalence differed by tumor site: 0.68 for NPC and other head-and-neck tumors, 0.60 for intracerebral tumors, and 0.50 for skull-base tumors.", "The synthesis included 22 publications and 1,462 patients, with eligibility requiring adult age at radiotherapy and radiotherapy for brain tumors, cerebral metastases, head-and-neck malignancies, or skull-base malignancies.", "The authors used a random-effects model because of expected clinical heterogeneity and included tumor site as a meta-regression covariate.", "The effects of surgery and chemotherapy were not incorporated into the meta-analysis results, limiting attribution of endocrine insufficiency specifically to radiotherapy.", "The authors identified cohort heterogeneity, insufficient confounder data for multivariate correction, probable selection bias, and inadequate loss-to-follow-up information as limitations."], "decisive": false}, "unit": {"minimax-m3-1-flash": "prevalence", "minimax-m3": "", "decisive": false, "resolution": "One reader left the unit blank. The other named 'prevalence', and the paper carries that unit in its own text, so the source settles the difference.", "support": ["Keywords: Hypothalamic-pituitary dysfunction, Insufficiency, Endocrine, Brain, Head and neck, Skull base, Tumor, Radiotherapy, Adults, Prevalence, Hypothalamus, Pituitary gland\nINTRODUCTION\nRadiotherapy is a widely applied modality in the treatment of primary brain tumors, brain metastasis, head & neck (HN) and skull base (SB) malignancies.", "By means of the meta-analysis, reporting of the prevalence for any insufficiency, insufficiency per axis and insufficiency for multiple axes was possible.", "In this context, prevalence can be defined as the number of existing cases (patients with an insufficiency) at a specific time point (end of follow-up) within a specific population (patients tested) [16]."]}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "Both readers returned the same number from the same sentence. The only difference was that one reader left the unit blank; the paper's own text carries the unit the other reader named, so the source resolved it.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:940269a88645f2aff3c449edb5b0699ba6f85fac69729423432f78f88575d68f", "type": "sep_package", "label": "SEP v1 package for pmid:39801827"}], "activities": [{"id": "activity:conversion:pmid:39801827", "type": "conversion", "used": ["package:940269a88645f2aff3c449edb5b0699ba6f85fac69729423432f78f88575d68f"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39801827", "parent_hash": "sha256:ddc50dc0be8f21643d2bca782022e96582d06189bbafdf3137137ba92a607b6c", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:39801827 not verified", "asset:source:pmid:39801827 not verified", "authors", "data:accession_absent", "execution.not_run", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on data:accession_absent"]},"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":"2026-11-04T04:15:27+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}}}