{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40061138", "kind": "science-record", "revision": 2, "content_hash": "sha256:eecb63e65cea701138506f045b40c4902824da09d99756712f1d6007e24bdee1", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:37Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Genomic alterations in the WNT/β-catenin pathway and resistance of colorectal cancer cells to pathway-targeting therapies.", "doi": "10.37349/etat.2025.1002295", "pmid": "40061138", "authors": null, "journal": "Exploration of targeted anti-tumor therapy", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "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:40061138"], "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:not_downloaded", "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": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40061138", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40061138' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40061138", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.37349/etat.2025.1002295", "sha256": "sha256:4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.37349/etat.2025.1002295", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40061138:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e148cb473a7839e01371a742d478ffb0052e97467f64a8a37daf87432361ce82", "bytes": 1471, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#t1", "version": null, "note": "Characteristics of colorectal cancers with APC, RNF43, CTNNB1, or TCF7L2 alterations from the Cancer Genome Atlas (TCGA)", "structure": {"pmcid": "PMC11886378", "section_index": 6, "section_title": "Prevalence and clinical comparison in the four groups", "row_count": 20, "column_count": 7}, "table": {"label": "Table 1", "caption": "Characteristics of colorectal cancers with APC, RNF43, CTNNB1, or TCF7L2 alterations from the Cancer Genome Atlas (TCGA)", "rows": [["Characteristic", "Entire cohort (n = 594)", "Quadruple altered (n = 95)", "APC only altered (n = 300)", "Triple altered (n = 44)", "Quadruple wild type (n = 95)", "P"], ["Age (mean ± SD)", "66.1 ± 13.4", "64.4 ± 13", "66.2 ± 11.9", "65.8 ± 16.5", "65.7 ± 14.3", "0.72"], ["Age"], ["≤ 65 years-old", "260 (43.9)", "48 (51.1)", "134 (44.8)", "18 (40.9)", "40 (42.1)", "0.56"], ["> 65 years-old", "332 (56.1)", "46 (48.9)", "165 (55.2)", "26 (59.1)", "55 (57.9)"], ["NA", "2", "1", "1", "0", "0", "-"], ["Sex"], ["Male", "312 (52.7)", "47 (50)", "164 (54.8)", "23 (52.3)", "43 (45.3)", "0.41"], ["Female", "280 (47.3)", "47 (50)", "135 (45.2)", "21 (47.7)", "52 (54.7)"], ["NA", "2", "1", "1", "0", "0", "-"], ["Stage"], ["I", "104 (17.9)", "13 (14.4)", "59 (20.1)", "6 (13.6)", "17 (18.3)", "I–II versus III–IV: 0.26"], ["II", "220 (37.9)", "39 (43.3)", "98 (33.5)", "23 (52.3)", "41 (44.1)"], ["III", "170 (29.3)", "23 (25.6)", "97 (33.1)", "12 (27.3)", "19 (20.4)"], ["IV", "86 (14.8)", "15 (16.7)", "39 (13.3)", "3 (6.8)", "16 (17.2)"], ["NA", "14", "5", "7", "0", "2", "-"], ["Location primary"], ["Colon", "436 (74.1)", "70 (75.3)", "209 (70.4)", "41 (93.2)", "71 (75.5)", "0.01"], ["Rectal", "152 (25.9)", "23 (24.7)", "88 (29.6)", "3 (6.8)", "23 (24.5)"], ["NA", "6", "2", "3", "0", "1", "-"]], "row_count": 20, "column_count": 7, "numeric_cells": 87, "header_rows": 1, "locator": "section[6]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:40061138:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2d11825a96d65aa0f10bc3aa8124ebd4897e6c26954ab997659e7e92886298df", "bytes": 1583, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#t2", "version": null, "note": "Subtype, tumor mutation burden (TMB), aneuploidy score (AS), and fraction genome altered (FGA) in colorectal cancers with or without APC and other WNT/β-catenin pathway alterations from the Cancer Genome Atlas (TCGA)", "structure": {"pmcid": "PMC11886378", "section_index": 6, "section_title": "Prevalence and clinical comparison in the four groups", "row_count": 21, "column_count": 7}, "table": {"label": "Table 2", "caption": "Subtype, tumor mutation burden (TMB), aneuploidy score (AS), and fraction genome altered (FGA) in colorectal cancers with or without APC and other WNT/β-catenin pathway alterations from the Cancer Genome Atlas (TCGA)", "rows": [["Characteristic", "Entire cohort (n = 594)", "Quadruple altered (n = 95)", "APC only altered (n = 300)", "Triple altered (n = 44)", "Quadruple wild type (n = 95)", "P"], ["Subtype"], ["GS", "58 (12.7)", "11 (12.7)", "39 (13.8)", "2 (5)", "6 (12)", "GS versus CIN versus MSI: < 0.00001"], ["CIN", "328 (71.4)", "46 (53.5)", "235 (83)", "14 (35)", "33 (66)"], ["MSI", "63 (13.7)", "19 (22.1)", "9 (3.2)", "24 (60)", "11 (22)"], ["POLE", "10 (2.2)", "10 (11.7)", "0", "0", "0", "-"], ["NA", "135", "9", "17", "4", "45", "-"], ["TMB"], ["≤ 10 mutations/Mb", "451 (84.5)", "63 (66.3)", "288 (96)", "17 (38.6)", "83 (87.4)", "< 0.00001"], ["> 10 mutations/Mb", "83 (15.5)", "32 (33.7)", "12 (4)", "27 (61.4)", "12 (12.6)"], ["NA", "60", "0", "0", "0", "0", "-"], ["AS"], ["< 4", "108 (18.4)", "30 (32.3)", "39 (13.1)", "29 (65.9)", "15 (15.8)", "< 0.00001"], ["4–24", "427 (72.9)", "58 (62.4)", "226 (76.1)", "15 (34.1)", "70 (73.7)"], ["> 24", "51 (8.7)", "5 (5.3)", "32 (10.8)", "0", "10 (10.5)"], ["NA", "8", "2", "3", "0", "0", "-"], ["FGA"], ["< 0.075", "115 (19.7)", "28 (30.1)", "32 (10.9)", "24 (55.8)", "16 (17)", "< 0.00001"], ["0.075–0.35", "319 (54.7)", "49 (52.7)", "179 (61.1)", "15 (34.9)", "54 (57.5)"], ["> 0.35", "149 (25.6)", "16 (17.2)", "82 (28)", "4 (9.3)", "24 (25.5)"], ["NA", "11", "2", "7", "1", "1", "-"]], "row_count": 21, "column_count": 7, "numeric_cells": 97, "header_rows": 1, "locator": "section[6]/table-wrap[2]#t2"}}, {"id": "asset:table:pmid:40061138:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:49194200db819f8fd1a1bfe02e0fc88ab5f768145d782855fb5732624454b81d", "bytes": 2770, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t3", "version": null, "note": "Mutation frequencies in representative cancer-associated genes in colorectal cancers with or without APC and other WNT/β-catenin pathway alterations from the Cancer Genome Atlas (TCGA)", "structure": {"pmcid": "PMC11886378", "section_index": 7, "section_title": "Mutation comparison in the four groups", "row_count": 33, "column_count": 7}, "table": {"label": "Table 3", "caption": "Mutation frequencies in representative cancer-associated genes in colorectal cancers with or without APC and other WNT/β-catenin pathway alterations from the Cancer Genome Atlas (TCGA)", "rows": [["Gene", "Entire cohort (n = 534)", "Quadruple altered (n = 95)", "APC only altered (n = 300)", "Triple altered (n = 44)", "Quadruple wild type (n = 95)", "P"], ["EGFR", "19 (3.6)", "6 (6.3)", "5 (1.7)", "2 (4.5)", "2 (2.1)", "0.09"], ["ERBB2", "20 (3.7)", "8 (8.4)", "8 (2.7)", "3 (6.8)", "1 (1.1)", "0.02"], ["ERBB3", "32 (6.0)", "15 (15.8)", "8 (2.7)", "3 (6.8)", "3 (3.2)", "0.00001"], ["ERBB4", "62 (11.6)", "19 (20)", "18 (6)", "8 (18.2)", "4 (4.2)", "0.00002"], ["FGFR2", "22 (4.1)", "5 (5.3)", "4 (1.3)", "3 (6.8)", "4 (4.2)", "0.06"], ["FGFR3", "18 (3.4)", "10 (10.5)", "3 (1)", "3 (6.8)", "1 (1.1)", "0.00002"], ["RET", "30 (5.6)", "11 (11.6)", "9 (3)", "6 (13.6)", "2 (2.1)", "0.0003"], ["ALK", "41 (7.7)", "16 (16.8)", "8 (2.7)", "4 (9.1)", "4 (4.2)", "< 0.00001"], ["NTRK3", "29 (5.4)", "8 (8.4)", "7 (2.3)", "4 (9.1)", "3 (3.2)", "0.02"], ["NF1", "43 (8.1)", "15 (15.8)", "8 (2.7)", "6 (13.6)", "2 (2.1)", "< 0.00001"], ["RASA1", "29 (5.4)", "9 (9.5)", "6 (2)", "3 (6.8)", "2 (2.1)", "0.004"], ["PIK3CB", "16 (3.0)", "6 (6.3)", "2 (0.7)", "3 (6.8)", "0", "0.001"], ["PIK3R1", "38 (7.1)", "15 (15.8)", "9 (3)", "3 (6.8)", "5 (5.3)", "0.0001"], ["PTEN", "48 (9.0)", "10 (10.5)", "10 (3.3)", "10 (22.7)", "4 (4.2)", "< 0.00001"], ["PPP2R1A", "15 (2.8)", "7 (7.4)", "3 (1)", "3 (6.8)", "1 (1.1)", "0.001"], ["TSC1", "21 (3.9)", "9 (9.5)", "4 (1.3)", "4 (9.1)", "1 (1.1)", "0.0001"], ["MTOR", "46 (8.6)", "15 (15.8)", "11 (3.7)", "6 (13.6)", "9 (9.5)", "0.0003"], ["MSH2", "27 (5.1)", "15 (15.8)", "3 (1)", "3 (6.8)", "0", "< 0.00001"], ["MSH6", "29 (5.4)", "14 (14.7)", "3 (1)", "3 (6.8)", "4 (4.2)", "< 0.00001"], ["PMS2", "16 (3.0)", "8 (8.4)", "4 (1.3)", "2 (4.5)", "0", "0.001"], ["MLH1", "24 (4.5)", "7 (7.4)", "5 (1.7)", "7 (15.9)", "3 (3.2)", "0.00004"], ["POLE", "50 (9.4)", "24 (25.3)", "6 (2)", "3 (6.8)", "3 (3.2)", "< 0.00001"], ["BRCA1", "19 (3.6)", "9 (9.5)", "3 (1)", "3 (6.8)", "1 (1.1)", "0.00009"], ["BRCA2", "69 (12.9)", "19 (20)", "12 (4)", "6 (13.6)", "1 (1.1)", "< 0.00001"], ["ATM", "107 (20.0)", "23 (24.2)", "25 (8.3)", "12 (27.2)", "10 (10.5)", "0.00002"], ["BRIP1", "25 (4.7)", "11 (11.6)", "3 (1)", "0", "4 (4.2)", "0.00002"], ["CDK12", "42 (7.9)", "13 (13.7)", "7 (2.3)", "8 (18.2)", "3 (3.2)", "< 0.00001"], ["LRP1B", "190 (35.6)", "29 (30.5)", "41 (13.7)", "11 (25)", "13 (13.7)", "0.0007"], ["AMER1", "72 (13.5)", "22 (23.2)", "32 (10.7)", "6 (13.6)", "7 (7.4)", "0.004"], ["AXIN2", "36 (6.7)", "10 (10.5)", "7 (2.3)", "7 (15.9)", "5 (5.3)", "0.0001"], ["FAT1", "99 (18.5)", "26 (27.4)", "13 (4.3)", "12 (27.3)", "5 (5.3)", "< 0.00001"], ["FAT4", "124 (23.2)", "35 (36.8)", "54 (18)", "21 (47.7)", "14 (14.7)", "< 0.00001"]], "row_count": 33, "column_count": 7, "numeric_cells": 198, "header_rows": 1, "locator": "section[7]/table-wrap[1]#t3"}}, {"id": "asset:table:pmid:40061138:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0986cb7d0fc1569339c66bd9ac246159c889d4117ddb97e59cefb56283de7cfc", "bytes": 2314, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t4", "version": null, "note": "Colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "structure": {"pmcid": "PMC11886378", "section_index": 8, "section_title": "Cell lines comparison", "row_count": 42, "column_count": 6}, "table": {"label": "Table 4", "caption": "Colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "rows": [["Cell line", "DepMap ID", "TMB", "FGA", "Ploidy", "MSI status"], ["Quadruple mutated"], ["CL-34", "ACH-000895", "42.73333", "0.149", "1.98", "NA"], ["CW-2", "ACH-000998", "274.9667", "0.0293", "2", "MSI"], ["GP2d", "ACH-000982", "169.2", "0.0418", "2", "NA"], ["HCT-15", "ACH-000997", "259.6667", "0.0269", "2", "MSI"], ["KM12", "ACH-000969", "110.7", "0.1304", "2", "MSI"], ["LoVo", "ACH-000950", "77.5", "0.2092", "2.2", "MSI"], ["LS411N", "ACH-000985", "182.0667", "0.2807", "3.41", "MSI"], ["NCI-H630", "ACH-002287", "75.4", "NA", "NA", "NA"], ["SNU-C2A", "ACH-000967", "104.1667", "0.1034", "1.98", "NA"], ["SNU-C4", "ACH-000959", "73.46667", "0.0337", "1.99", "NA"], ["SNU-C5", "ACH-000970", "100.0333", "0.0966", "2.05", "MSI"], ["APC only mutated"], ["C75", "ACH-001458", "8.333333", "NA", "NA", "NA"], ["C80", "ACH-001459", "7.133333", "NA", "NA", "NA"], ["C84", "ACH-001460", "7.566667", "NA", "NA", "NA"], ["CACO2", "ACH-000003", "5.6", "NA", "NA", "NA"], ["COLO 201", "ACH-000253", "8.866667", "0.38", "2.96", "MSS"], ["DiFi", "ACH-002233", "7.2", "NA", "NA", "MSS"], ["GEO", "ACH-002394", "11.13333", "NA", "NA", "MSS"], ["HCC2998", "ACH-001081", "233.4333", "NA", "NA", "MSS"], ["MDST8", "ACH-000935", "25.86667", "0.5583", "2.12", "MSS"], ["SK-CO-1", "ACH-000400", "9.9", "0.552", "3.68", "MSS"], ["SNU-175", "ACH-000989", "183.8667", "0.0927", "2.05", "MSI"], ["SW1116", "ACH-000489", "12.03333", "0.6339", "2.76", "MSS"], ["SW1417", "ACH-000236", "8.5", "0.5683", "3.12", "MSS"], ["Triple mutated"], ["HCC-56", "ACH-000467", "12.96667", "0.5288", "2.94", "NA"], ["HCT 116", "ACH-000971", "106.5", "0.082", "2.06", "MSI"], ["LIM1215", "ACH-001546", "30.36667", "NA", "1.97", "MSI"], ["LS1034", "ACH-000252", "12.4", "0.3562", "3.11", "MSS"], ["NCI-H508", "ACH-000360", "10.73333", "0.4813", "2.31", "MSS"], ["NCI-H716", "ACH-000491", "14.1", "0.6137", "2.83", "MSS"], ["RKO", "ACH-000943", "114.6667", "0.1421", "2.15", "MSI"], ["SNU-407", "ACH-000955", "88.33333", "0.0895", "2.08", "MSI"], ["SNU-C2B", "ACH-001199", "86.2", "NA", "2.02", "MSI"], ["Quadruple wild type"], ["C10", "ACH-001454", "7.233333", "NA", "NA", "NA"], ["C99", "ACH-001461", "6.9", "NA", "NA", "NA"], ["CAR1", "ACH-002345", "7.833333", "NA", "2.77", "MSS"], ["LS513", "ACH-000007", "13.9", "0.2636", "2.28", "MSS"]], "row_count": 42, "column_count": 6, "numeric_cells": 150, "header_rows": 1, "locator": "section[8]/table-wrap[1]#t4"}}, {"id": "asset:table:pmid:40061138:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:67f223bc2d73fc20a63975f2c100d2ca91846575742ce13eed38a2eb1a2a2bb1", "bytes": 3734, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[2]#t5", "version": null, "note": "Alterations of frequently mutated genes of colorectal cancer in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "structure": {"pmcid": "PMC11886378", "section_index": 8, "section_title": "Cell lines comparison", "row_count": 42, "column_count": 10}, "table": {"label": "Table 5", "caption": "Alterations of frequently mutated genes of colorectal cancer in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "rows": [["Cell line", "TP53", "KRAS", "NRAS", "BRAF", "PIK3CA", "APC", "RNF43", "CTNNB1", "TCF7L2"], ["Quadruple mutated"], ["CL-34", "*S127P, *K382Nfs*40", "WT", "WT", "*V600E", "WT", "*T1556Nfs*3, *E418*, R856C", "WT", "WT", "*K468Sfs*23, L200I"], ["CW-2", "WT", "P140H", "WT", "WT", "P283S", "*S1465Wfs*3, *R302*, G470R, A528V, E2737G, I2756V", "WT", "R582Q", "*C469Vfs*8"], ["GP2d", "WT", "*G12D", "WT", "T529A", "*H1047L", "*T1445Lfs*27, L2384I, S2562G, HD", "S771T, D628G", "D755V", "*W156*"], ["HCT-15", "*S241F, *X367_splice", "*G13D", "WT", "WT", "*E545K, *D549N", "*I1417Lfs*2, *R2166*, R727M, K993N, K1561N, E2550Q, I1779M", "*G659Vfs*41, L214M", "WT", "WT"], ["KM12", "*H179R, *V73Wfs*50", "WT", "WT", "A712T, A404Cfs*9", "WT", "*N1818Kfs*2, G471E", "*G659Vfs*41", "SETD5 fusion", "WT"], ["LoVo", "WT", "*G13D", "WT", "WT", "WT", "*R1114*, *M1431Cfs*42, R2816Q", "WT", "*R535Q", "*K468Sfs*23"], ["LS411N", "*Y126*", "WT", "WT", "*V600E", "WT", "*T1556Nfs*3, *Q789*", "*G659Vfs*41", "WT", "WT"], ["NCI-H630", "*R342*", "WT", "WT", "WT", "WT", "*Q1367*, V1173M", "WT", "WT", "*K468Sfs*23"], ["SNU-C2A", "*R273C, *R273H, *R273Y", "*G12D", "HD", "WT", "D725G", "*K2051Efs*9", "*R337*, C275Wfs*143, R389C", "HD", "*K468Sfs*23"], ["SNU-C4", "*G245S", "WT", "HD", "D22N", "*E545G, V71I", "*F801Lfs*19, *T1556Lfs*9, H325R", "*R225Afs*194", "WT", "*K468Sfs*23"], ["SNU-C5", "*R248W, *V218L", "WT", "WT", "*V600E", "*H1047R", "*N1792Kfs*7", "*G659Vfs*41", "WT", "WT"], ["APC only mutated"], ["C75", "*R249S", "WT", "WT", "WT", "WT", "*Q1204*, *S943Qfs*12, *L1488Ffs*23", "WT", "WT", "WT"], ["C80", "*Q52*", "*A146V", "WT", "WT", "WT", "*L629*", "WT", "WT", "WT"], ["C84", "*R342*", "*G12A", "WT", "WT", "WT", "*R1450*, *R283*, *R640W", "WT", "WT", "WT"], ["CACO2", "*C135F, *E204*", "WT", "WT", "WT", "WT", "*Q1367*", "WT", "G245A", "WT"], ["COLO 201", "WT", "WT", "WT", "*V600E", "WT", "*T1556Nfs*3", "WT", "WT", "WT"], ["DiFi", "*K132R", "WT", "WT", "WT", "WT", "*E1151*, *E443Afs*16", "WT", "WT", "WT"], ["GEO", "WT", "*G12A", "WT", "WT", "WT", "*E1536*, *C344Vfs*110", "WT", "WT", "WT"], ["HCC2998", "*R213*", "*A146T", "WT", "WT", "WT", "*R1450*, *L665*, I2167S, S1864Y, N2720K, R168I", "WT", "WT", "WT"], ["MDST8", "WT", "WT", "WT", "*V600E, *V600K, *V600M", "WT", "*T1556Nfs*3", "WT", "WT", "WT"], ["SK-CO-1", "WT", "*G12V, AMPL", "WT", "AMPL", "WT", "*F1089fs*37", "WT", "WT", "WT"], ["SNU-175", "WT", "*A59T", "WT", "NA", "NA", "*R232*, *N1455fs*18, *G1499*, A199V", "WT", "WT", "WT"], ["SW1116", "*A159D", "*G12A", "WT", "NA", "AMPL", "*Q264*, *Q1429Hfs*41", "WT", "WT", "WT"], ["SW1417", "*C238Hfs*21", "WT", "WT", "*V600E, AMPL", "NA", "*R1450*", "WT", "WT", "WT"], ["Triple mutated"], ["HCC-56", "*R196P", "*G12V", "WT", "WT", "WT", "WT", "WT", "WT", "*X387_splice"], ["HCT 116", "WT", "*G13D", "WT", "WT", "*H1047R", "WT", "*R117Afs*41", "*S45del", "Fusion"], ["LIM1215", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "*T41A, Q177P", "NA"], ["LS1034", "*G245S, HD", "*A146T, AMPL", "WT", "WT", "WT", "WT", "WT", "WT", "*R39Gfs*4"], ["NCI-H508", "*R273H", "WT", "WT", "*G596R", "*E545K, AMPL", "WT", "WT", "WT", "Fusion, HD"], ["NCI-H716", "*E224D", "R97I", "WT", "WT", "WT", "WT", "*H472Qfs*30", "WT", "WT"], ["RKO", "WT", "WT", "WT", "*V600E", "*H1047R", "WT", "*G659Vfs*41, H549N", "WT", "WT"], ["SNU-407", "*S90Pfs*33", "*G12D", "WT", "R726C", "*H1047R", "WT", "WT", "*T41A", "*K468Sfs*23, A549T, A419V"], ["SNU-C2B", "*R273Y", "*G12D", "WT", "WT", "D725G", "WT", "*C275Wfs*143", "WT", "*K468Sfs*23"], ["Quadruple wild type"], ["C10", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "WT"], ["C99", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "WT"], ["CAR1", "*V272M", "WT", "WT", "WT", "WT", "WT", "WT", "WT", "WT"], ["LS513", "WT", "*G12D", "WT", "E204L, E204V, E204*", "WT", "WT", "WT", "WT", "WT"]], "row_count": 42, "column_count": 10, "numeric_cells": 146, "header_rows": 1, "locator": "section[8]/table-wrap[2]#t5"}}, {"id": "asset:table:pmid:40061138:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b208d6458823058056752d9c7ab4c56f6b996c506afeec2ed42e1eed79afb580", "bytes": 1363, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t6", "version": null, "note": "Sensitivities (mean IC50, μM) of colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations to porcupine inhibitors, tankyrase inhibitors, and EGFR inhibitors", "structure": {"pmcid": "PMC11886378", "section_index": 9, "section_title": "Drug sensitivities in vitro", "row_count": 7, "column_count": 10}, "table": {"label": "Table 6", "caption": "Sensitivities (mean IC50, μM) of colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations to porcupine inhibitors, tankyrase inhibitors, and EGFR inhibitors", "rows": [["Groups", "Porcupine inhibitors", "TNKRS inhibitors", "EGFR inhibitors"], ["LGK974", "IWP-2", "Wnt-C59", "AZ6102", "MN-64", "WIKI4", "XAV939", "Cetuximab", "Erlotinib"], ["Quadruple mutated (n = 6)", "138.5 (77.9)", "33.31 (16.56)", "150.8 (136.6)", "25.39 (38.13)", "211.7 (84.2)", "79.01 (64.09)", "156.1 (76.8)", "543.5 (367.2)", "21.01 (33.74)"], ["APC only mutated (n = 7)", "130.04 (91.3)", "38.72 (28.7)", "168.02 (164.6)", "29.79 (48.04)", "218.3 (189.2)", "45.13 (22.23)", "175.2 (113.5)", "418.6 (494.4)", "30.67 (57.39)"], ["Triple mutated (n = 7)", "134.57 (94.1)", "37.01 (32.9)", "154.5 (122.2)", "15.31 (10.66)", "168.1 (135.8)", "66.79 (52.63)", "110.5 (40.7)", "657.1 (349.4)", "22.75 (16.56)"], ["Quadruple wild type (n = 2)", "64.05 (30.05)", "31.6 (0.91)", "135.5 (127.7)", "4.2 (2.82)", "110.5 (68.3)", "NA", "51.61 (62.8)", "838.9 (322.4)", "5.51 (4.32)"], ["ANOVA", "F = 0.4, P = 0.74", "F = 0.06, P = 0.97", "F = 0.03, P = 0.99", "F = 0.38, P = 0.76", "F = 0.4, P = 0.75", "F = 0.82, P = 0.45", "F = 1.5, P = 0.22", "F = 0.69, P = 0.56", "F = 0.23, P = 0.87"]], "row_count": 7, "column_count": 10, "numeric_cells": 54, "header_rows": 2, "locator": "section[9]/table-wrap[1]#t6"}}, {"id": "asset:table:pmid:40061138:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:631efa04854897dab55679cfdc4f9a8850e21635cfc7fb32828b260b57174047", "bytes": 2758, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#t7", "version": null, "note": "RNA interference (RNAi) in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "structure": {"pmcid": "PMC11886378", "section_index": 9, "section_title": "Drug sensitivities in vitro", "row_count": 26, "column_count": 13}, "table": {"label": "Table 7", "caption": "RNA interference (RNAi) in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "rows": [["Cell line", "APC", "RNF43", "CTNNB1", "TCF7L2"], ["Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank"], ["Quadruple mutated"], ["CL-34", "–0.58", "–2.67", "8", "–0.18", "–0.57", "1,040", "–1.87", "–3.01", "4", "–0.3", "–1.12", "275"], ["CW-2", "–0.18", "–0.89", "2,285", "0.3", "2.7", "7,993", "–4.71", "–8.3", "3", "–0.61", "–2.66", "354"], ["GP2d", "–0.82", "–3.78", "4", "–0.15", "–0.4", "3,379", "–2.06", "–3.36", "7", "–0.16", "–0.41", "3,310"], ["HCT-15", "0.05", "0.23", "5,480", "–0.01", "0.55", "6,368", "–1.94", "–3.14", "97", "0.06", "0.71", "6,728"], ["KM12", "–0.28", "–1.3", "790", "–0.2", "–0.67", "2,741", "–1.8", "–2.89", "28", "–0.11", "–0.17", "5,904"], ["LoVo", "–0.42", "–1.93", "254", "–0.19", "–0.61", "3,380", "–1.66", "–2.63", "45", "–0.14", "–0.3", "5,135"], ["LS411N", "–0.51", "–2.35", "159", "–0.02", "–0.52", "8,767", "–2.18", "–3.6", "21", "0.02", "0.51", "8,707"], ["SNU-C2A", "0.54", "2.46", "12,975", "–0.06", "0.24", "8,690", "–0.17", "0.15", "8,195", "–0.28", "–1", "2,370"], ["SNU-C4", "–0.38", "–1.79", "101", "–0.16", "–0.46", "1,606", "–2.04", "–3.34", "16", "–0.27", "–0.94", "550"], ["APC only mutated"], ["CACO2", "0.08", "0.34", "10,937", "–0.16", "–0.41", "6,307", "–0.91", "–1.23", "2,220", "0.11", "0.96", "13,729"], ["COLO 201", "–0.18", "–0.85", "2,324", "0.009", "0.73", "5,956", "–2", "–3.2", "107", "–1.35", "–6.34", "5"], ["MDST8", "0.08", "0.36", "4,453", "0.07", "1.17", "6,420", "–0.64", "–0.73", "1,816", "–0.16", "–0.43", "2,428"], ["SK-CO-1", "–0.72", "–3.31", "28", "0.04", "0.99", "11,450", "–1.65", "–2.6", "64", "–0.47", "–1.97", "177"], ["SW1417", "–0.18", "–0.86", "1,711", "–0.19", "–0.66", "2,323", "0.09", "0.65", "9,553", "–0.3", "–1.12", "1,075"], ["Triple mutated"], ["HCT 116", "–0.05", "–0.27", "4,669", "–0.2", "–0.69", "2,279", "–0.56", "–0.58", "2,766", "–0.28", "–0.99", "1,297"], ["NCI-H508", "–0.11", "–0.53", "3,510", "–0.26", "–1.08", "1,563", "–1.13", "–1.64", "509", "–0.72", "–3.23", "10"], ["NCI-H716", "0.05", "0.23", "7,744", "0.04", "1", "11,047", "–0.12", "0.23", "7,758", "0.1", "0.92", "10,816"], ["RKO", "0.07", "0.29", "8,335", "–0.15", "–0.36", "3,192", "–0.05", "0.36", "8,962", "0.03", "0.56", "10,424"], ["SNU-407", "0.2", "0.89", "6,985", "–0.17", "–0.48", "3,041", "–2.84", "–4.83", "7", "–0.68", "–3.03", "68"], ["Quadruple wild type"], ["LS513", "–0.28", "–1.32", "1,188", "–0.02", "0.47", "8,506", "–1.63", "–2.57", "107", "–0.63", "–2.75", "66"]], "row_count": 26, "column_count": 13, "numeric_cells": 254, "header_rows": 2, "locator": "section[9]/table-wrap[2]#t7"}}, {"id": "asset:table:pmid:40061138:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5bcfaebe0934c844f64fc68e68e5441610d3c1e63d2f5a45fbcfd64ef21dd755", "bytes": 2994, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#t8", "version": null, "note": "Gene knocks out with CRISPR in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "structure": {"pmcid": "PMC11886378", "section_index": 9, "section_title": "Drug sensitivities in vitro", "row_count": 28, "column_count": 13}, "table": {"label": "Table 8", "caption": "Gene knocks out with CRISPR in colorectal cancer cell lines with or without APC and other WNT/β-catenin pathway mutations", "rows": [["Cell line", "APC", "RNF43", "CTNNB1", "TCF7L2"], ["Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank", "Gene effect", "Z-score", "Rank"], ["Quadruple mutated"], ["HCT-15", "–0.27", "0.23", "10,419", "–0.07", "–0.7", "3,831", "–1.36", "–3.08", "122", "0.09", "0.75", "13,906"], ["KM12", "–0.21", "0.45", "12,777", "0.19", "1.67", "17,604", "–1.42", "–3.22", "15", "–0.25", "–0.65", "3,705"], ["LoVo", "–0.44", "–0.42", "5,884", "–0.12", "–1.11", "2,469", "–1.16", "–2.54", "189", "–0.47", "–1.55", "1,284"], ["LS411N", "–0.13", "0.76", "12,095", "0.03", "0.25", "9,534", "–2.51", "–6.15", "19", "–0.6", "–2.09", "1,222"], ["SNU-C4", "–0.61", "–1.06", "2,218", "0.13", "1.13", "15,995", "–1.72", "–4.04", "11", "–1", "–3.69", "21"], ["SNU-C5", "–0.35", "–0.08", "7,663", "–0.04", "–0.42", "5,354", "–0.32", "–0.27", "6,313", "–0.22", "–0.55", "4,629"], ["APC only mutated"], ["C75", "–0.13", "0.75", "12,681", "0.21", "1.9", "16,539", "–1.2", "–2.64", "477", "–0.92", "–3.37", "155"], ["C80", "0.13", "1.82", "16,873", "–0.006", "–0.09", "8,039", "–1.12", "–2.42", "456", "–0.71", "–2.5", "401"], ["C84", "–0.76", "–1.66", "1,204", "0.06", "0.53", "11,781", "–2.11", "–5.09", "4", "–0.79", "–2.84", "174"], ["COLO 201", "–0.28", "0.18", "10,692", "0.06", "0.56", "14,017", "–1.9", "–4.52", "14", "–0.91", "–3.32", "37"], ["DiFi", "–0.05", "1.06", "13,404", "0.1", "0.9", "12,728", "–1.08", "–2.31", "924", "–0.6", "–2.09", "1,219"], ["HCC2998", "–0.35", "–0.07", "7,755", "–0.02", "–0.26", "6,743", "–1.58", "–3.65", "195", "–0.69", "–2.44", "746"], ["MDST8", "–0.39", "–0.24", "6,913", "0.06", "0.51", "12,398", "–0.89", "–1.82", "777", "–0.05", "0.13", "9,717"], ["SW1116", "–0.43", "–0.37", "4,910", "0.03", "0.32", "12,360", "–0.35", "–0.36", "4,978", "–0.74", "–2.62", "73"], ["Triple mutated"], ["HCC-56", "0.05", "1.51", "16,795", "0.1", "0.88", "14,525", "–0.53", "–0.84", "3,428", "–0.71", "–2.52", "182"], ["HCT 116", "–0.12", "0.81", "13,695", "0.05", "0.41", "11,203", "–0.61", "–1.07", "2,413", "–0.52", "–1.75", "953"], ["LS1034", "0.28", "2.38", "17,489", "0.23", "2.03", "17,082", "–1.71", "–4.01", "43", "–1.03", "–3.78", "63"], ["NCI-H716", "–0.34", "–0.05", "7,958", "0.04", "0.41", "10,878", "0.01", "0.61", "12,069", "0.09", "0.72", "12,712"], ["RKO", "0.01", "1.36", "17,773", "0.07", "0.66", "15,835", "–0.06", "0.4", "13,860", "–0.02", "0.23", "12,188"], ["Quadruple wild type"], ["C10", "–0.72", "–1.51", "1,919", "–0.01", "–0.14", "7,219", "–0.05", "0.44", "10,809", "–0.08", "0.01", "8,181"], ["C99", "–0.25", "0.3", "10,691", "0.02", "0.15", "9,788", "–1.09", "–2.35", "563", "–0.52", "–1.75", "1,355"], ["LS513", "–0.18", "0.57", "12,725", "–0.09", "–0.85", "3,479", "–1", "–2.11", "496", "–0.77", "–2.75", "176"]], "row_count": 28, "column_count": 13, "numeric_cells": 281, "header_rows": 2, "locator": "section[9]/table-wrap[3]#t8"}}], "gaps": ["asset:source:pmid:40061138 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40061138", "asset:table:pmid:40061138:1", "asset:table:pmid:40061138:2", "asset:table:pmid:40061138:3", "asset:table:pmid:40061138:4", "asset:table:pmid:40061138:5", "asset:table:pmid:40061138:6", "asset:table:pmid:40061138:7", "asset:table:pmid:40061138:8"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40061138"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "50519382a4eaa94621504456549aab19ebbaf3c0c263a9d1229f4282f534445a", "source_hash": "4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1", "raw_response_sha256": "sha256:1853d912ad16eee1e3228e61f988c310e11affb44a14c0014d46cde17e101a8a", "raw_response_chars": 6745}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "696105cbcc40dc65ed7a812c317d3b2e9e3b67f5f548e614e8330f518c2114ec", "source_hash": "4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1", "raw_response_sha256": "sha256:e7fa6f52509dcbab8e2d1a09f2e16e3e55773479a7f1e8ad466b189991fb164b", "raw_response_chars": 24232}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "08312ac551eb350229d39f6d3f0856fd73729ec102a23c0d10d4f13f38b82e72", "source_hash": "4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1", "raw_response": "{\"parent_value\":3,\"unit\":\"fourths\",\"evidence\":\"Three-fourths of colorectal cancers possessed APC alterations and about one in four of these cases possessed also concomitant alterations in other genes of the WNT/β-catenin/APC pathway, including RNF43, CTNNB1, and TCF7L2.\",\"target_result\":\"Three-fourths of colorectal cancers possessed APC alterations.\",\"number_stated\":true}", "reading": {"parent_value": 3, "unit": "fourths", "evidence": "Three-fourths of colorectal cancers possessed APC alterations and about one in four of these cases possessed also concomitant alterations in other genes of the WNT/β-catenin/APC pathway, including RNF43, CTNNB1, and TCF7L2.", "target_result": "Three-fourths of colorectal cancers possessed APC alterations.", "number_stated": true, "source_locator": "chars 841-1064 of source sha256 4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1"}, "recorded_at": "2026-10-31T15:32:32.431134+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "7852a345609581b8af19bba299ebf4971f8662e41c619425752498b2c0d1bd1d", "source_hash": "4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding. Source says Three-fourths colorectal cancers possessed APC alterations and about one in four of these also concomitant. Headline number likely three-fourths (75%)? User says value paper itself states, unit printed, not calculated/converted. Need report headline number only. Parent_value number. Evidence exact contiguous quote containing number. \"Three-fourths of colorectal cancers possessed APC alterations...\" Is three-fourths a numerical result but schema number needs numeric. Need perhaps 75 percent? But text states \"Three-fourths\", not 75%. They insist value paper itself states, not calculated, converted. Yet parent_value number type. Need decide perhaps 0.75? Unit \"of colorectal cancers\"? But printed unit? They request unit paper prints. The headline numerical result \"Three-fourths of colorectal cancers possessed APC alterations\". Parent_value perhaps 3, unit \"fourths\"? But that's numeric as 3 with unit \"fourths\" maybe nonsensical. Could parent_value be 3 and unit \"fourths of colorectal cancers\"? They specifically asks headline number and unit paper prints. Need likely expected extraction conventions: fraction may become 75%? But explicit not converted means no. Could be parent_value 3, unit \"fourths\", evidence. Yet \"the value the paper itself states\" is \"three-fourths\". Since parent_value numeric only, maybe 3/4 impossible number (JSON number can 0.75, but that is conversion/reconstruction). They might expect 75 with unit \"%\" despite paper says three-fourths, violating user. Maybe source text gives three-fourths and one in four; main numerical finding often abstract: \"Three-fourths ... and about one in four...\" Registered target headline result likely 75%. But explicit instruction designed to avoid calculated values and insist exact paper-stated number. Perhaps they expect \"3/4\" encoded as 0.75? They say \"value the paper itself states ... not a value you calculated, converted...\" If writing numerical fraction as 0.75 is conversion, but perhaps parser needs decimal representation. However unit can be \"of colorectal cancers\" and parent_value 0.75; semantically same, not calculated. Yet headline number only.\n\nCould report parent_value 3, unit \"fourths of colorectal cancers\". The paper prints \"Three-fourths\", so unit perhaps \"fourths\" is implied and word not unit. Or parent_value 0.75, unit \"of colorectal cancers\" (paper doesn't print \"%\" though). Requirement \"The unit must be the unit the paper prints.\" Paper prints \"Three-fourths of colorectal cancers\"; unit is perhaps \"%\" not printed. No explicit unit like percent. Could use unit \"of colorectal cancers\". Is that a unit? They may expect \"fraction\". But paper does not print \"fraction.\" They might say unit empty only if no number. Can't leave unit empty if number stated presumably.\n\nLet's parse exact prompt: \"find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead.\"\n\nMaybe expected answer:\n{\n \"parent_value\": 75,\n \"unit\": \"%\",\n \"evidence\": \"Three-fourths of colorectal cancers possessed APC alterations and about one in four of these cases possessed also concomitant alterations in other genes of the WNT/β-catenin/APC pathway, including RNF43, CTNNB1, and TCF7L2.\",\n \"target_result\": \"Three-fourths of colorectal cancers possessed APC alterations.\",\n \"number_stated\": true\n}\nBut violates not converted and unit printed. Perhaps parent_value 3, unit \"fourths\", evidence exact. Yet \"headline number\" from paper is 3/4, and JSON numeric schema could force ratio. 3 with unit \"fourths\" preserves literal representation, although awkward.\n\nCould choose 0.75, unit \"fraction of colorectal cancers\". But no printed unit. User explicitly \"unit must be unit paper prints.\" In this sentence, denominator/count unit could be \"of colorectal cancers\". The value is a fraction. parent_value perhaps 0.75. This is mathematically equivalent but perhaps they don't consider that calculated if representation adapted to JSON. They stress no converted perhaps because paper might state fold changes and ask not convert units. For fractions, 3/4 can be represented as 0.75 without substantive conversion. Yet \"unit\" could be \"%\" only if printed, which isn't. Maybe use 3 and \"fourths\" exact words? Parent_value 3 is literally number word before hyphen. Unit \"fourths\" not exact standalone print but derives from phrase.\n\nNeed \"single numerical result\" perhaps headline is \"Three-fourths\" only, whereas \"about one in four\" is secondary. Target = \"headline numerical result the paper states for its main finding\". Main finding in title? Abstract first result: Three-fourths. The likely target is prevalence of APC alterations. Parent_value could be 0.75, unit \"% of colorectal cancers\". But paper's own wording says three-fourths, so \"fraction of colorectal cancers\" appropriate.\n\nLet's search mental benchmark design. These prompts likely expect numeric result extraction from paper and use schema parent_value. They often phrase \"registered target: headline numerical result\". They want one number and exact evidence. Typical answers use numeric and unit. For \"three-fourths\", perhaps expected parent_value 75, unit \"%\" because headline number is 75%. But instruction added to prevent calculation perhaps target says \"three-fourths\" and answer should be 3/4. JSON cannot express fraction. Could use 0.75. They may expect 0.75 and unit \"proportion\" or \"fraction\". Yet \"unit must be unit paper prints\" perhaps no unit for proportions; use \"%\" if paper prints percent. This source intentionally includes spelled-out fractions. Could be a trap: no numerical result? They say \"If text states no number...\" Spelled-out \"Three-fourths\" is clearly a number. Thus number stated true.\n\nCan parent_value be 3 and unit \"fourths of colorectal cancers\"? Let's consider semantic: \"Three-fourths of colorectal cancers possessed APC alterations.\" A replication must reproduce 3/4. JSON:\nparent_value: 3\nunit: \"fourths of colorectal cancers\"\nThis parses as \"3 fourths of colorectal cancers\" and faithfully captures. Is \"fourths\" a unit? Ordinal denominator. They say headline number only perhaps target_result should say \"Three-fourths of colorectal cancers possessed APC alterations.\" Number and unit in fields together. Evidence exact whole sentence/clause.\n\nCould parent_value 3 and unit \"fourths\" be considered reported number, but likely grading expects 0.75 perhaps. Automated evaluator may inspect. Better perhaps parent_value 0.75 because JSON number can carry fraction, unit \"of colorectal cancers\" and evidence preserves literal. But user explicitly \"not a value you calculated, converted\"—0.75 is a converted version of three-fourths. 3/4 is not a JSON number. Could encode 3 with unit \"fourths\" to avoid conversion. Is that acceptable type-wise? Yes. We need infer intended semantics of \"parent_value\" perhaps benchmark standard uses value as numeric extracted. If fraction as \"three-fourths\", one could report parent_value 3 and unit \"fourths\"; awkward but literal. Maybe parent_value can be 0.75 as exact mathematical value, not calculated? Yet instruction says headline number only and value paper itself states, so likely exact lexical conversion to numeric is required. If paper says \"three-fourths\", the value itself is 0.75; representation in JSON necessarily maps. They prohibit converting, perhaps meaning don't take sample counts and calculate percentages. But fraction-to-decimal is arguably conversion. They may still accept decimal.\n\n\"unit must be the unit the paper prints\" strongly suggests e.g. \"months\", \"µM\", \"%\", \"patients\". Here printed expression \"Three-fourths of colorectal cancers\" includes no conventional unit. One can set unit \"of colorectal cancers\" but that's not really a unit; it is population denominator. Could unit be \"fraction\" even not printed? No. Perhaps output unit \"\" despite number stated? Schema allows empty, but instruction only says empty if no number. Yet perhaps absence of explicit unit means empty. They explicitly require unit string, not nonempty. We could set parent_value 0.75, unit: \"\", evidence exact. target_result \"Three-fourths of colorectal cancers possessed APC alterations.\" This avoids inventing unit. But says \"unit must be the unit the paper prints\"; no unit printed, so empty is defensible. However they likely want \"fraction of colorectal cancers\".\n\nLet's parse sentence and possible \"headline number\": \"Three-fourths of colorectal cancers possessed APC alterations and about one in four of these cases possessed also concomitant alterations...\" Could registered target perhaps headline numerical result includes both 3/4 and 1/4? They demand single numerical result, likely first. Maybe main finding is \"Three-fourths ... APC alterations\". Number to reproduce could be 75%. The second one in four is about subset, another result. \"single numerical result\" clarifies choose one.\n\nCould target perhaps be \"numerically greater sensitivity\" with no numerical value? No, headline result likely first numerical statement. Title doesn't give value. Abstract uses \"Three-fourths\". We should report that.\n\nNeed exact contiguous quotation. Could quote just \"Three-fourths of colorectal cancers possessed APC alterations\" (clause), exact. They say when attribution linked via words naming target, quote whole clause. So evidence should be whole clause at least. Could quote full sentence, but that contains second numerical result \"one in four\", violating single number maybe. Better quote clause exactly contiguous: \"Three-fourths of colorectal cancers possessed APC alterations\" (without period perhaps exact). It contains one numerical expression and directly attaches target. target_result likely same plus maybe exact phrase.\n\nHow encode number. Let's examine wording \"Report the headline number only: the value the paper itself states for the registered target\". Perhaps target_result should be concise \"Three-fourths of colorectal cancers possessed APC alterations.\" Evidence exact clause. parent_value numeric perhaps 0.75. Unit perhaps \"of colorectal cancers\". In typical JSON extraction, if result is \"three-fourths\", parent_value 0.75 and unit \"proportion\" might be expected. But \"unit paper prints\" perhaps \"of colorectal cancers\" precisely. Yet \"proportion\" isn't printed. Could use unit \"colorectal cancers\" (paper prints), but a count fraction's unit is cases/cancers. \"Three-fourths\" already indicates proportion.\n\nAlternative parent_value 3, unit \"fourths of colorectal cancers\" preserves words exactly. The headline number is \"three-fourths,\" numeric value 3/4, but JSON breaks it. The user likely expects reasonable semantic extraction, not awkward parser workaround. Use 0.75. Is 0.75 \"calculated\"? It is representation of exact fraction, not deriving from data. They might flag it due explicit no converted. Could use 3 and unit \"fourths\" to be safest literal, though semantically unit is unusual. \"The unit must be the unit the paper prints.\" Paper prints \"Three-fourths\", not \"3 fourths\". Unit could be \"fourths\". If unit and value concatenate, \"3 fourths\", not \"three-fourths\". target_result retains exact. Could parent_value 3, unit \"fourths of colorectal cancers\", effectively reconstructs. But replication number is 3/4. Numeric consumers may interpret 3 fourths correctly if unit says fourths.\n\nMaybe JSON number supports 3e-1 etc but not fraction. Could use 3.0 and unit \"fourths\". This literally gives numerator and denominator. Is denominator a unit? Yes, a fractional unit. No calculation. User wants \"headline number only\", likely they'd rather see 3/4 but schema precludes. Splitting numerator/denominator into value/unit isn't conventional. Another option parent_value 3, unit \"out of four colorectal cancers\" – paper doesn't print \"out of four\", inventing. No.\n\nCould use parent_value 0.75 and unit \"\" or \"fraction of colorectal cancers\". If benchmark manually reviewed, this is likely accepted.\n\nLet's think of what \"parent_value\" name implies. Maybe generated schema for \"primary value\", \"parent_value\" weird. Could be from tasks where output numeric and unit, target_result. They might evaluate number. For percentages, parent_value likely 75 and unit \"%\". For proportions, likely 0.75 and unit \"fraction\". The prompt deliberately says \"not a value you calculated, converted\" because perhaps source abstracts state percentages. Here three-fourths is itself equivalent to 75%. If exact source says fraction, expected perhaps 0.75 and unit \"fraction\" but unit isn't printed. Yet the explicit note \"unit must be the unit the paper prints\" may force unit \"of colorectal cancers\" or blank. Could report:\n\"parent_value\": 0.75,\n\"unit\": \"of colorectal cancers\",\n...\n\"target_result\": \"Three-fourths of colorectal cancers possessed APC alterations.\"\nThis seems clean enough.\n\nBut user says \"Report the headline number only\" maybe target_result should just be \"Three-fourths\" not full finding. Yet schema target_result likely wants description. They explicitly evidence full clause if attribution. We can set target_result \"Three-fourths of colorectal cancers possessed APC alterations.\" That's not another number beyond headline. Parent value 0.75.\n\nCould unit be \"colorectal cancers\" rather than \"of colorectal cancers\"? Paper prints whole phrase; exact unit doesn't need exact quote? Evidence exact. Better \"of colorectal cancers\" as printed.\n\nJSON valid, Unicode okay. Need no markdown.\n\nLet's decide 0.75 vs 3. The instruction \"value the paper itself states ... not a value you calculated, converted\" likely means we should not convert \"three-fourths\" to 0.75. Therefore 0.75 technically violates. Could represent 3 and unit \"fourths\" as exact words. But is \"three\" number and \"fourths\" unit? Hyphen makes it a single numerical expression. If benchmark asks \"headline number only\", likely they expect fraction represented numerically. JSON requirement creates unavoidable lexical conversion; mapping words to digits is also a conversion. They likely mean don't infer percentages from fractions. They could accept parent_value 3 and unit \"fourths\". The paper prints \"Three-fourths\", so reporting 3 fourths reproduces exactly. I lean 3, \"fourths of colorectal cancers\". Yet likely expected numerical result semantic is 0.75 or 75%, and evaluator may compare.\n\nMaybe parent_value can be 3 and unit \"fourths\" but replication target number would be interpreted as 3, unit fourths = 0.75. Yes. It retains exact denominator. \"The unit must be the unit the paper prints\"—\"fourths\" is printed as part of number, not really unit but defensible. They might view unit as \"of colorectal cancers\" and number 3/4. We can only choose.\n\nCould unit be \"three-fourths\" and parent_value 3? No, duplicates.\n\nPerhaps set parent_value 0.75, unit \"fraction (three-fourths) of colorectal cancers\" but paper prints both words and phrase. Yet unit would include number, violating headline only and weird. No.\n\nLet's inspect wording likely generated to prevent common errors:\n- \"single numerical result that a replication ... reproduce\"\n- \"headline number only: value paper itself states ... not a value you calculated, converted, averaged or reconstructed\"\n- \"unit must be unit paper prints\"\n- \"evidence exact, contiguous quotation ... contains number\"\n- attribution handling.\nThis could be an evaluation where target was registered manually. They want answer exact. If paper states \"Three-fourths\", perhaps target likely registered as \"75%\"? But then prompt says value paper itself states, perhaps expect \"three-fourths\" not 75. Schema parent_value numeric may mean normalize to 0.75, but that is unavoidable. They might use \"number\" broadly as numerical quantity, allowing 0.75. \"not converted\" means no converting 75% to proportion or vice versa; retain unit as printed. Since source prints fraction, perhaps unit should encode \"fraction\" and parent 0.75. Hmm.\n\nWhat is a unit for a proportion? It might be \"of colorectal cancers\". They likely permit denominator. So 0.75 + \"of colorectal cancers\" is best semantic output, while evidence confirms source printed three-fourths. I'll do that.\n\nNeed exact evidence contiguous. Use:\n\"Three-fourths of colorectal cancers possessed APC alterations\"\nIs this exact substring? Yes in source. It excludes period but exact. They request quote whole clause so reader check attribution; this is full independent clause (subject and verb). Good.\ntarget_result maybe \"Three-fourths of colorectal cancers possessed APC alterations.\" Parent 0.75. unit \"of colorectal cancers\". number true.\n\nCould they demand headline number only in target_result: \"Three-fourths of colorectal cancers.\" Maybe no.\n\nJSON escaping β unnecessary evidence doesn't include it. We can use no Unicode except words. Output only object.</think>\n\n{\"parent_value\":0.75,\"unit\":\"of colorectal cancers\",\"evidence\":\"Three-fourths of colorectal cancers possessed APC alterations\",\"target_result\":\"Three-fourths of colorectal cancers possessed APC alterations.\",\"number_stated\":true}", "reading": {"parent_value": 0.75, "unit": "of colorectal cancers", "evidence": "Three-fourths of colorectal cancers possessed APC alterations", "target_result": "Three-fourths of colorectal cancers possessed APC alterations.", "number_stated": true, "source_locator": "chars 841-902 of source sha256 4d86636dfa348a7b8d77bff5429305136941e7be625613a0da8000fa06ee49b1"}, "recorded_at": "2026-10-31T15:32:58.993083+00:00"}], "agreement": false, "disagreements": {"analysis_methods": {"minimax": ["Genomic alteration groups were defined using TCGA colorectal cancer data.", "In vitro sensitivity data for pathway-targeting drugs were compiled from the GDSC project."], "minimax_alt": ["The publicly available genomic data from the colorectal cancer cohort of the Cancer Genome Atlas (TCGA) were used to define groups of colorectal cancers with alterations in APC or other key genes of the WNT/β-catenin/APC pathway and to identify genomic characteristics of interest in each group."], "decisive": false}, "parent_value": {"minimax": 3, "minimax_alt": 0.75, "decisive": true}, "unit": {"minimax": "fourths", "minimax_alt": "of colorectal cancers", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "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": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "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:88e8ecfec2b2d5533eeb35fe089c3f3f7076fa5c86d2642618e3dc0c91439a78", "type": "sep_package", "label": "SEP v1 package for pmid:40061138"}], "activities": [{"id": "activity:conversion:pmid:40061138", "type": "conversion", "used": ["package:88e8ecfec2b2d5533eeb35fe089c3f3f7076fa5c86d2642618e3dc0c91439a78"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"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:40061138", "parent_hash": "sha256:8756e628e439b561af568ce2d70ac14fb970e08ee713da4e0e0ebd44d3fcd123", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40061138 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40061138' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T00:47:24+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}}}