{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40951359", "kind": "science-record", "revision": 2, "content_hash": "sha256:253486a70cb3fa8e7f70d7dba9652e49061645eb758f3dd18d190d1bd5b8391c", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Claudin18.2 defines a prognostically distinct subgroup of intrahepatic cholangiocarcinoma via CD8+ T-cell exclusion.", "doi": "10.3389/fonc.2025.1636367", "pmid": "40951359", "authors": null, "journal": "Frontiers in oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 24.1, "unit": "percent", "tolerance": null, "source": "chars 890-986 of source sha256 dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63"}, "evidence": [{"asset": "source:pmid:40951359", "locator": "chars 890-986 of source sha256 dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "quote": "CLDN18.2 was exclusively expressed in 24.1% (20/83) of ICC tissues, absent in non-tumor tissues."}]}], "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:40951359"], "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:40951359", "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:40951359' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40951359", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2025.1636367", "sha256": "sha256:dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2025.1636367", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40951359:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1aab42c1c72036f14bcc3225dfaaaa0f1733eae2b4607332fed0d3eb77230452", "bytes": 2730, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T1", "version": null, "note": "Clinicopathological characteristics and CLDN18.2 expression in ICC patients.", "structure": {"pmcid": "PMC12425741", "section_index": 8, "section_title": "Clinicopathological features of ICC patients", "row_count": 51, "column_count": 6}, "table": {"label": "Table 1", "caption": "Clinicopathological characteristics and CLDN18.2 expression in ICC patients.", "rows": [["Characteristics", "Total (N=83)", "Claudin18.2 expression", "χ2", "P value"], ["Positive", "Negative"], ["Age (years)", "", "", "", "0.019", "0.89"], ["≤ 65", "55 (66.3%)", "13 (65.0%)", "42 (66.7%)", "", ""], [">65", "28 (33.7%)", "7 (35.0%)", "21 (33.3%)", "", ""], ["Sex", "", "", "", "2.29", "0.13"], ["Female", "26 (31.3%)", "9 (45.0%)", "17 (27.0%)", "", ""], ["Male", "57 (68.7%)", "11 (55.0%)", "46 (73.0%)", "", ""], ["Tumor size (cm)", "", "", "", "4.59", "0.032*"], ["≤ 5", "45 (54.2%)", "15 (75.0%)", "30 (47.6%)", "", ""], [">5", "38 (45.8%)", "5 (25.0%)", "33 (52.8%)", "", ""], ["Tumor number", "", "", "", "", "0.032*"], ["1", "70 (83.1%)", "20 (100.0%)", "50 (79.4%)", "", ""], ["≥2", "13 (16.9%)", "0 (0.0%)", "13 (20.6%)", "", ""], ["Histological grade", "", "", "", "H = 0.25", "0.62"], ["Well/Moderate", "64 (77.1%)", "16 (80.0%)", "48 (76.2%)", "", ""], ["Moderate-poor", "9 (10.8%)", "3 (15.0%)", "6 (9.5%)", "", ""], ["Poor", "10 (12.0%)", "1 (5.0%)", "9 (14.3%)", "", ""], ["Lymph node metastasis", "", "", "", "", "0.35"], ["Yes", "18 (21.7%)", "6 (30.0%)", "12 (19.0%)", "", ""], ["No", "65 (78.3%)", "14 (70.0%)", "51 (81.0%)", "", ""], ["AJCC TNM stage", "", "", "", "1.07", "0.30"], ["I/II", "65 (78.3%)", "14 (70.0%)", "51 (81.0%)", "", ""], ["III/IV", "18 (21.7%)", "6 (30.0%)", "12 (19.0%)", "", ""], ["MVI", "", "", "", "1.60", "0.21"], ["M0", "48 (57.8%)", "14 (70.0%)", "34 (54.0%)", "", ""], ["M1/M2", "35 (42.2%)", "6 (30.0%)", "29 (46.0%)", "", ""], ["aCA199", "", "", "", "6.04", "0.026*"], ["Positive", "48 (58.2%)", "15 (83.3%)", "33 (54.1%)", "", ""], ["Negative", "31 (41.8%)", "3 (16.7%)", "28 (45.9%)", "", ""], ["HBV", "", "", "", "2.97", "0.085"], ["Positive", "47 (56.6%)", "8 (40.0%)", "39 (61.9%)", "", ""], ["Negative", "36 (43.3%)", "12 (60.0%)", "24 (38.1%)", "", ""], ["Microbiliary invasion", "", "", "", "0.17", "0.68"], ["Yes", "30 (36.1%)", "8 (40.0%)", "22 (34.9%)", "", ""], ["No", "53 (63.9%)", "12 (60.0%)", "41 (65.1%)", "", ""], ["Perineural invasion", "", "", "", "0.07", "0.78"], ["Yes", "27 (32.5%)", "7 (35.0%)", "20 (31.7%)", "", ""], ["No", "56 (67.5%)", "13 (65.0%)", "43 (68.3%)", "", ""], ["Cirrhosis", "", "", "", "", "0.43"], ["Yes", "10 (12.0%)", "1 (5.0%)", "9 (14.3%)", "", ""], ["No", "73 (88.0%)", "19 (95.0%)", "54 (85.7%)", "", ""], ["aCEA", "", "", "", "0.96", "0.76"], ["Positive", "24 (30.4%)", "6 (33.3%)", "18 (29.5%)", "", ""], ["Negative", "55 (69.6%)", "12 (66.7%)", "43 (70.5%)", "", ""], ["a AFP", "", "", "", "", "0.66"], ["Positive", "7 (8.9%)", "2 (11.1%)", "5 (8.2%)", "", ""], ["Negative", "72 (91.1%)", "16 (88.9%)", "56 (91.8%)", "", ""], ["Recurrence", "", "", "", "", "0.018*"], ["Yes", "57 (68.7%)", "18 (90.0%)", "39 (61.9%)", "", ""], ["No", "26 (31.3%)", "2 (10.0%)", "24 (38.1%)", "", ""]], "row_count": 51, "column_count": 6, "numeric_cells": 136, "header_rows": 2, "locator": "section[8]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:40951359:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b5eb6e48f3679d227f8cf8f4736118d3f4e82b2c446866cf4e8156e23f7e7685", "bytes": 1134, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T2", "version": null, "note": "Univariate analysis of prognostic factors(OS) for ICC.", "structure": {"pmcid": "PMC12425741", "section_index": 11, "section_title": "Prognostic significance of CLDN18.2 in ICC", "row_count": 18, "column_count": 4}, "table": {"label": "Table 2", "caption": "Univariate analysis of prognostic factors(OS) for ICC.", "rows": [["Parameters", "HR", "95% CI", "P value"], ["Age (years) (> 65 vs. ≤ 65)", "0.690", "0.369-1.291", "0.246"], ["Sex (male vs. female)", "0.805", "0.445-1.455", "0.472"], ["HBV", "1.079", "0.609-1.915", "0.794"], ["CA199", "3.487", "1.710-7.110", "0.001*"], ["CEA", "1.638", "0.885-3.032", "0.116"], ["TNM stage (III/IV vs. I/II)", "2.165", "1.129-4.151", "0.020*"], ["Histological grade", "", "", "0.010*"], ["(Moderate-poor vs. poor)", "0.376", "0.124-1.138", "0.083"], ["(Well-Moderate vs. poor)", "0.312", "0.147-0.660", "0.002*"], ["MVI (M1/M2 vs. M0)", "2.600", "1.459-4.635", "0.001*"], ["Lymph node metastasis", "2.165", "1.129-4.151", "0.020*"], ["Bile duct invasion", "1.372", "0.766-2.458", "0.288"], ["Perineural invasion", "1.542", "0.858-2.773", "0.148"], ["Tumor number (≥ 2 vs. 1)", "0.885", "0.396-1.977", "0.766"], ["Tumor size(cm) (> 5 vs. ≤ 5)", "1.594", "0.904-2.811", "0.107"], ["Cirrhosis", "0.739", "0.292-1.868", "0.522"], ["Claudin18.2", "2.545", "1.383-4.682", "0.003*"]], "row_count": 18, "column_count": 4, "numeric_cells": 55, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:40951359:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2a90d93ef13d5c831142a70f6defc9210d5d16a69362d23681f247dadf7a6830", "bytes": 1060, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T3", "version": null, "note": "Cox regression analyses of disease-free survival for ICC.", "structure": {"pmcid": "PMC12425741", "section_index": 11, "section_title": "Prognostic significance of CLDN18.2 in ICC", "row_count": 11, "column_count": 5}, "table": {"label": "Table 3", "caption": "Cox regression analyses of disease-free survival for ICC.", "rows": [["", "Univariable analysis", "Multivariable analysis"], ["Parameters", "HR (95% CI)", "P value", "HR (95% CI)", "P value"], ["CA199", "2.350 (1.311-4.213)", "0.004*", "1.517 (0.789-2.920)", "0.212"], ["TNM stage (III/IV vs. I/II)", "2.594 (1.419-4.742)", "0.002*", "2.612 (1.313-5.197)", "0.006*"], ["Histological grade", "", "0.049*", "", "0.409"], ["(Moderate-poor vs. poor)", "0.637 (0.237-1.716)", "0.373", "0.606 (0.199-1.844)", "0.378"], ["(Well-Moderate vs. poor)", "0.414 (0.199-0.860)", "0.018*", "0.549 (0.228-1.323)", "0.181"], ["MVI (M1/M2 vs. M0)", "2.358 (1.384-4.019)", "0.002*", "2.086 (1.157-3.761)", "0.014*"], ["Lymph node metastasis", "2.594 (1.419-4.742)", "0.002*", "2.612 (1.313-5.197)", "0.006*"], ["Claudin18.2", "1.865 (1.053-3.304)", "0.033*", "2.229 (1.125-4.415)", "0.022*"], ["Tumor size (cm)(> 5 vs. ≤ 5)", "1.832 (1.087-3.087)", "0.023*", "2.443 (1.357-4.400)", "0.003*"]], "row_count": 11, "column_count": 5, "numeric_cells": 39, "header_rows": 2, "locator": "section[11]/table-wrap[2]#T3"}}], "gaps": ["asset:source:pmid:40951359 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:40951359", "asset:table:pmid:40951359:1", "asset:table:pmid:40951359:2", "asset:table:pmid:40951359:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40951359"]}, "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": "16b66414b037ad691896559f070f892472d0e188eead0adfd5147723f1499e86", "source_hash": "dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "raw_response_sha256": "sha256:cbb5aedcdc7c06c9d206d8b65a11029776642d8c3620ee0f079eaea72308dc39", "raw_response_chars": 5984}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "c81b3b92a26c17b1ceae580cb44e96f55b1ada2f7e644c1048fc94c99a37ee44", "source_hash": "dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "raw_response_sha256": "sha256:41fcda48ce2069e44282c23664441b539095a2203098363e259bb8b87f588cfd", "raw_response_chars": 63518}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "cdddd4a80760e7ead5577e92fb1cb6854de83a6a1040d2f9a3fcc5c9a7c48e3c", "source_hash": "dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "raw_response": "{\"parent_value\":24.1,\"unit\":\"%\",\"evidence\":\"CLDN18.2 was exclusively expressed in 24.1% (20/83) of ICC tissues, absent in non-tumor tissues.\",\"target_result\":\"CLDN18.2 expression in 24.1% of intrahepatic cholangiocarcinoma tissues.\",\"number_stated\":true}", "reading": {"parent_value": 24.1, "unit": "%", "evidence": "CLDN18.2 was exclusively expressed in 24.1% (20/83) of ICC tissues, absent in non-tumor tissues.", "target_result": "CLDN18.2 expression in 24.1% of intrahepatic cholangiocarcinoma tissues.", "number_stated": true, "source_locator": "chars 890-986 of source sha256 dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63"}, "recorded_at": "2026-10-31T15:36:01.124635+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "8aad65e79d0263eb42a9b8816ad5b720de49f1d2f267dd6107d71ce38e1cc77f", "source_hash": "dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63", "raw_response": "<think>We need answer JSON object only. Need interpret target \"headline numerical result paper states for its main finding\" likely 24.1% expression? Need identify single numerical result replication registered target. Paper title/main finding CLDN18.2 defines subgroup via CD8 exclusion. Headline numerical result perhaps CLDN18.2 exclusively expressed in 24.1% (20/83) of ICC tissues. The wording conclusion: \"this study establishes CLDN18.2 as a tumor-specific biomarker in ICC, expressed in 24.1% of ICC patients with absent normal tissue expression.\" They ask headline number only, value paper itself states, unit paper prints. Evidence exact contiguous quote contains number, if linked by wording quote whole clause. Need choose number and unit. parent_value number 24.1, unit \"%\" likely. Evidence exact contiguous quotation: \"CLDN18.2 was exclusively expressed in 24.1% (20/83) of ICC tissues, absent in non-tumor tissues.\" This is exact sentence, contains attribution and main result. target_result perhaps concise \"24.1%\" or \"CLDN18.2 was exclusively expressed in 24.1% of ICC tissues.\" Since headline number only maybe parent_value 24.1, unit \"%\". target_result could \"24.1%\" or descriptive. Need not include converted count. Evidence whole clause due linked directly. Need ensure quote exact contiguous source. Yes.\n\nCould registered target instead be HR 2.555 for reduced OS, the headline numerical result for main finding? Need reason. They explicitly define target as \"the headline numerical result the paper states for its main finding.\" In source, first result and conclusion emphasize expression prevalence 24.1%. Main title finding includes prognostic subgroup and CD8 exclusion, but no single exact headline beyond 24.1%. The instruction likely asks extraction benchmark where target generic, identify main numerical result. Usually abstracts have one headline number. Here likely 24.1% because conclusion repeats it. Need perhaps evidence quote whole conclusion clause: \"In conclusion, this study establishes CLDN18.2 as a tumor-specific biomarker in ICC, expressed in 24.1% of ICC patients with absent normal tissue expression.\" This explicitly labels main finding. Better than result sentence. They demand \"When that is how text links them, quote whole clause so reader can check attribution.\" We can quote entire exact sentence. Does evidence need only clause containing number? Exact contiguous. Use conclusion sentence. Unit printed \"%\" embedded. parent_value 24.1. target_result perhaps \"24.1% of ICC patients\" (headline number only asks report headline number only, perhaps target_result should just \"24.1%\"). JSON schema target_result string. We can say \"24.1%\" to comply headline number only, while evidence quote. They ask \"Report the headline number only: the value...\" So target_result likely \"24.1%\". Other fields required. Let's formulate.\n\nNeed valid JSON no markdown. Ensure Unicode okay. Evidence exact:\n\"In conclusion, this study establishes CLDN18.2 as a tumor-specific biomarker in ICC, expressed in 24.1% of ICC patients with absent normal tissue expression.\"\nYes source exact. Could unit \"%\" and parent_value 24.1. number_stated true.\n\nLet's answer.</think>\n\n{\"parent_value\":24.1,\"unit\":\"%\",\"evidence\":\"In conclusion, this study establishes CLDN18.2 as a tumor-specific biomarker in ICC, expressed in 24.1% of ICC patients with absent normal tissue expression.\",\"target_result\":\"24.1%\",\"number_stated\":true}", "reading": {"parent_value": 24.1, "unit": "%", "evidence": "In conclusion, this study establishes CLDN18.2 as a tumor-specific biomarker in ICC, expressed in 24.1% of ICC patients with absent normal tissue expression.", "target_result": "24.1%", "number_stated": true, "source_locator": "chars 5176-5333 of source sha256 dcb877d871ba2b34be8a8c832ec4e28918193a4d85570cb6f3d69ec264ad7b63"}, "recorded_at": "2026-10-31T15:36:06.297212+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "CLDN18.2 expression was an independent prognostic factor for reduced overall survival (OS: HR = 2.555, 95% CI = 1.250–5.223, P = 0.01).", "minimax_alt": "Multivariable analysis identified CLDN18.2 as an independent prognostic factor for reduced overall survival (OS: HR = 2.555, 95% CI = 1.250–5.223, P = 0.01) and disease-free survival (DFS: HR = 2.229, 95% CI = 1.125–4.415, P = 0.022).", "decisive": false}, "physical_methods": {"minimax": ["Tissue microarray immunohistochemistry (IHC)", "CD8+ tumor-infiltrating lymphocyte (TIL) quantification"], "minimax_alt": ["Immunohistochemistry (IHC) on tissue microarray sections from 83 ICC and 47 matched non-tumor tissues", "CD8+ tumor-infiltrating lymphocyte (TIL) quantification"], "decisive": false}, "analysis_methods": {"minimax": ["Single-sample gene set enrichment analysis (ssGSEA)", "TIMER method in the IOBR R package", "Kaplan-Meier method", "Log-rank test", "Cox proportional hazards regression"], "minimax_alt": ["Single-sample gene set enrichment analysis (ssGSEA)", "TIMER method in the IOBR R package", "Wilcoxon rank-sum test", "chi-square test", "Fisher's exact test", "one-sample t-test", "one-way ANOVA", "Kaplan-Meier method", "log-rank test", "univariate and multivariate Cox proportional hazards regression"], "decisive": false}, "statistical_method": {"minimax": "Cox proportional hazards regression", "minimax_alt": "Multivariable Cox proportional hazards regression", "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:91c5e09e7a2593656663c98008024767d70a37641cfa6f2fcea7a8dc302a67fd", "type": "sep_package", "label": "SEP v1 package for pmid:40951359"}], "activities": [{"id": "activity:conversion:pmid:40951359", "type": "conversion", "used": ["package:91c5e09e7a2593656663c98008024767d70a37641cfa6f2fcea7a8dc302a67fd"], "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:40951359", "parent_hash": "sha256:bd7d6a92ad049c3211250ad193d8dc223da4165687ec8a7670c0474b8acd8c8e", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40951359 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:40951359' 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":"2026-11-04T01:48:34+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}}}