{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30158148", "kind": "science-record", "revision": 2, "content_hash": "sha256:72baab59405f81842ce97ba563ba7f50aaebbac1194b7d383f8cefb9f2d052cf", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:31Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Environmental toxic metal contaminants and risk of cardiovascular disease: systematic review and meta-analysis.", "doi": "10.1136/bmj.k3310", "pmid": "30158148", "authors": null, "journal": "BMJ (Clinical research ed.)", "year": 2018, "abstract": null, "claims": [{"id": "claim-1", "statement": "the pooled relative risk of cardiovascular disease for lead comparing top versus bottom thirds of baseline levels", "kind": "quantitative", "state": "complete", "target": {"value": 1.43, "unit": "relative risk", "tolerance": null, "source": "chars 980-1177 of source sha256 9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044"}, "evidence": [{"asset": "source:pmid:30158148", "locator": "chars 980-1177 of source sha256 9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "quote": "Comparing top versus bottom thirds of baseline levels, pooled relative risks for arsenic and lead were 1.30 (95% confidence interval 1.04 to 1.63) and 1.43 (1.16 to 1.76) for cardiovascular disease"}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the pooled relative risk of cardiovascular disease for lead comparing top versus bottom thirds of baseline levels", "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:30158148"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the study data behind the published pooled estimate", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The published estimate cannot be recomputed without the data the review pooled.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the pooled study data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "data:accession_absent", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the study data pooled behind the published estimate in pmid:30158148"], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": ["the study data pooled behind the published estimate in pmid:30158148", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30158148", "role": "manuscript", "format": "txt", "media_type": "text/plain", "uri": "https://doi.org/10.1136/bmj.k3310", "sha256": "sha256:9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "reader_required", "identifier": "10.1136/bmj.k3310", "version": null, "note": "Source read by the package builder: abstract_only.", "structure": {"access_state": "abstract_only"}}, {"id": "materials:the study data pooled behind the published estimate in pmid:30158148", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the study data pooled behind the published estimate in pmid:30158148", "structure": {"material_kind": "dataset", "access_state": "not_identified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "asset:table:pmid:30158148:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:84ef37450277f3e3c9ecffb25f422a1bddafacd666763a36d71bcaa700fa222b", "bytes": 5922, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tbl1", "version": null, "note": "Summary of the studies included in the systematic review", "structure": {"pmcid": "PMC6113772", "section_index": 9, "section_title": "Study level characteristics", "row_count": 54, "column_count": 13}, "table": {"label": "Table 1", "caption": "Summary of the studies included in the systematic review", "rows": [["Study or lead author (Publication year)", "Country", "Population source", "Study design", "Baseline survey", "Mean age", "Male (%)", "Total follow-up (Years)", "No of participants", "", "No of cases"], ["CVD", "CHD", "Stroke"], ["Arsenic"], ["Afridi (2011)31", "Pakistan", "Hospital records", "Case-control", "2007-2008", "45-60 *", "52", "NA", "119", "", "0", "58", "0"], ["Chen (1996)† 2 32", "Taiwan", "General", "Prospective cohort", "1988-1989", "NR", "46", "7", "1760", "", "0", "39", "0"], ["DCH (2017)33", "Denmark", "Cancer register", "Prospectivecohort", "1993-1997", "50-64*", "46.9", "14.8", "53 856", "", "0", "2707", "0"], ["HEALS34", "Bangladesh", "General", "Prospective cohort", "2000-2002", "18-75*", "43", "9", "11 109", "", "192", "101", "82"], ["Liao (2012)† 2 35", "Taiwan", "General", "Case-control", "2002", "61", "43", "7", "676", "", "10", "0", "0"], ["NHSCS36", "USA", "Cancer register", "Prospective Cohort", "1993-1995", "59", "56", "20", "3939", "", "312", "154", "43"], ["Ruiz-Navarro (1998)37", "Spain", "Hospital records", "Case-control", "NR", "NR", "39", "NA", "78", "", "0", "29", "0"], ["SHS38", "USA", "Health survey", "Prospective Cohort", "1989-1991", "45-74*", "40", "19", "3575", "", "1184", "846", "264"], ["SLVDS39", "USA", "Hospital based", "Case-cohort", "1984-1998", "57‡", "48", "14", "555", "", "0", "96", "0"], ["Sohel (2009)40", "Bangladesh", "Health survey", "Prospective cohort", "1991-2000", ">15", "50", "9", "115 903", "", "1211", "639", "572"], ["Wade (2015)41", "China", "Hospital records", "Case-control", "NR", "21-70*", "69", "NA", "533", "", "277", "0", "0"], ["Wu (2010)†1 42", "Taiwan", "Household records", "Prospective cohort", "1991-1994", ">40", "47", "11", "504", "", "22", "0", "0"], ["Lead"], ["ABLES43", "USA", "Health survey", "Prospective cohort", "1987-2005", "39", "100", "17", "58 368", "", "692", "569", "123"], ["BRHS44", "UK", "Registers", "Prospective cohort", "1978-1980", "40-59", "100", "7", "7379", "", "382", "316", "66"], ["McElvenny (2015)45", "UK", "Health survey", "Prospective cohort", "1975-1979", "35", "85", "36", "9122", "", "941", "792", "149"], ["Moller (1992)46", "Denmark", "Hospital records", "Prospective cohort", "1976", "40", "48", "14", "1045", "", "54", "40", "0"], ["NHANES II47", "USA", "Health survey", "Prospective cohort", "1976-1980", "54", "47", "16", "4190", "", "424", "0", "0"], ["NHANES III†4 48", "USA", "Health survey", "Prospective cohort", "1988-1994", "58", "48", "12", "9757", "", "1189", "0", "0"], ["NHANES III†4 49", "USA", "Health survey", "Prospective cohort", "1988-1994", "44", "47", "12", "13 946", "", "0", "367", "141"], ["NHANES III†4 50", "USA", "Health Survey", "Prospective cohort", "1999-2010", "58", "47.6", "12", "18602", "", "985", "0", "0"], ["SOF51", "USA", "General", "Prospective cohort", "1990-1991", "70", "0", "13", "533", "", "54", "23", "21"], ["VA-NAS52", "USA", "Health screening", "Prospective cohort", "1991-1999", "67", "100", "16", "1235", "", "185", "82", "0"], ["Earlier randomised26", "Netherlands", "Health survey", "Prospective cohort", "1977-1978", "57-76*", "100", "8", "146", "", "64", "39", "18"], ["Cadmium"], ["CadmiBel53", "Belgium", "Population registers", "Prospective cohort", "1985-1989", "47", "45", "22", "956", "", "88", "56", "21"], ["HPFS54", "USA", "Health professionals", "Nested case-control", "1987", "62‡", "100", "5", "884", "", "0", "442", "0"], ["Li (2011)55", "Japan", "Health survey", "Prospective cohort", "1981-1982", ">50", "45", "22", "3119", "", "267", "0", "217"], ["MDCS56", "Sweden", "Health study", "Prospective cohort", "1991-1994", "46-67*", "41", "17", "4819", "", "713", "377", "336"], ["NHANES (1999-2004)† 3 57", "USA", "Health survey", "Prospective cohort", "1999-2004", ">20", "48", "7", "8989", "", "191", "88", "0"], ["NHANES III58", "USA", "Health survey", "Prospective cohort", "1988-1994", ">20", "47", "12", "13 958", "", "769", "367", "0"], ["NHANES III50", "USA", "Health survey", "Prospective cohort", "1999-2010", "58", "48", "12", "18602", "", "985", "0", "0"], ["SHS59", "USA", "Health survey", "Prospective cohort", "1989-1991", "56", "40", "19", "3348", "", "1010", "766", "244"], ["Mercury"], ["EURAMIC60", "Multinational", "Population registers and hospital records", "Case-control", "1991-1992", "≤70", "100", "NA", "1408", "", "0", "684", "0"], ["Gothenburg61", "Sweden", "Health study", "Prospective cohort", "1968-1969", "38-60*", "0", "32", "1391", "", "301", "128", "173"], ["Hallgren (2001)†5 62", "Sweden", "Health survey", "Nested case-control", "1985-1994", "55", "79", "9", "234", "", "0", "78", "0"], ["HPFS and NHS63", "USA", "Health professionals", "Nested case-control", "1976 and 1986", "56", "35", "15.3", "6854", "", "3427", "2363", "1064"], ["KIHD†6 64", "Finland", "General", "Prospective cohort", "1984-1989", "52", "100", "17.8", "1871", "", "414", "282", "0"], ["KIHD (2016)† § 6 65", "Finland", "General", "Prospective cohort", "1984-1989", "42-60*", "100", "21.2", "2682", "", "0", "0", "202"], ["NSHDS†§ 5 66", "Sweden", "Health surveys", "Nested case-control", "1994-1999", "NR", "75", "5", "930", "", "0", "431", "0"], ["NSHDS†§ 5 67", "Sweden", "Health surveys", "Nested case-control", "1985-2000", "55", "60", "15", "2271", "", "878", "0", "369"], ["PREDIMED68", "Spain", "Primary care centres", "Nested case-control", "2003-2009", "55-80*", "59", "4.8", "414", "", "147", "0", "0"], ["Copper"], ["EPOZ69", "Netherlands", "Health survey", "Nested case-control", "1975-1978", "68", "53", "9", "186", "", "62", "0", "0"], ["KIHD70", "Finland", "General", "Prospective cohort", "1984-1988", "52", "100", "5.75", "1666", "", "0", "51", "0"], ["Marniemi (2005)71", "Finland", "Health survey", "Prospective cohort", "1986-1987", "65-99*", "48", "10", "660", "", "200", "130", "70"], ["NHANES II72", "USA", "Health survey", "Prospective cohort", "1976-1980", "48", "46", "12", "4574", "", "0", "151", "0"], ["PPS II73", "France", "Public employees", "Prospective cohort", "1980-1985", "43", "100", "21", "4035", "", "56", "0", "0"], ["Reunanen (1996)74", "Finland", "Screening programme", "Nested case-control", "1981", "15-69*", "100", "10", "504", "", "220", "160", "30"], ["Overall total¶", "", "", "", "", "", "", "", "348 259", "", "15 274", "13 033", "4205"]], "row_count": 54, "column_count": 13, "numeric_cells": 409, "header_rows": 2, "locator": "section[9]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:30158148:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:52b3e54f8821696b55c96d07dbe5887d71ccc146767d5549706b6fe8a8ceadd8", "bytes": 1750, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#tbl2", "version": null, "note": "Newcastle-Ottawa scale for assessing cohort study quality", "structure": {"pmcid": "PMC6113772", "section_index": 9, "section_title": "Study level characteristics", "row_count": 33, "column_count": 5}, "table": {"label": "Table 2", "caption": "Newcastle-Ottawa scale for assessing cohort study quality", "rows": [["Author, year (Pubmed ID)", "Selection(Max=4)", "Comparability(Max=2)", "Outcome(Max=3)", "Overall quality score (Max=9)"], ["Aoki, 2016 (26735529)", "3", "2", "3", "8"], ["Barregard, 2015 (26517380)", "3", "2", "3", "8"], ["Bergdahl, 2013 (22350276)*", "2", "2", "3", "7"], ["Chen, 2011 (21546419)", "3", "2", "3", "8"], ["Chen, 1996 (8624771)", "1", "2", "3", "6"], ["Chowdhury, 2014 (24769120)", "1", "1", "3", "5"], ["Daneshmand. 2016 (26991769)*", "3", "2", "3", "8"], ["Farzan, 2015 (26048586)", "2", "2", "3", "7"], ["Ford, 2000 (10905530)", "4", "2", "3", "9"], ["Khalil, 2009 (19344498)", "2", "2", "3", "7"], ["Kromhout 1988, (3203644)", "3", "2", "1", "7"], ["Leone, 2006 (16570028)", "2", "2", "2", "6"], ["Li, 2011 (22340168)*", "3", "1", "3", "7"], ["Liao, 2012 (22569360)", "1", "2", "2", "5"], ["Lustberg, 2002 (12437403)", "3", "2", "3", "8"], ["Marniemi, 2005 (15955467)", "3", "2", "2", "7"], ["McElvenny, 2015 (25872777)", "2", "1", "2", "5"], ["Menke 2006, (16982939)", "3", "2", "3", "8"], ["Menke, 2009 (19270787)", "4", "2", "3", "9"], ["Moller, 1992 (1462969)", "4", "2", "1", "7"], ["Monrad, 2017 (28157645)", "2", "2", "2", "6"], ["Moon, 2013 (24061511)", "3", "2", "3", "8"], ["Nawrot, 2008 (19079711)", "3", "2", "3", "8"], ["Pocock, 1988 (3203640)", "3", "1", "3", "7"], ["Salonen, 1991 (1877585)", "3", "2", "2", "7"], ["Schober, 2006 (17035139)", "3", "2", "2", "7"], ["Sohel, 2009 (19797964)", "2", "1", "1", "4"], ["Tellez-Plaza, 2013 (23514838)", "3", "2", "3", "8"], ["Tellez-Plaza, 2012 (22472185)", "3", "2", "1", "6"], ["Virtanen, 2005 (15539625)", "4", "2", "3", "9"], ["Weisskopf, 2009 (19738141)", "2", "2", "2", "6"], ["Wu, 2010 (20708634)", "1", "2", "3", "6"]], "row_count": 33, "column_count": 5, "numeric_cells": 164, "header_rows": 1, "locator": "section[9]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:30158148:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2cbd2bda1e22752290f9288e45aa21d3a2eb085d6d7d540e77baf6fee939cbb1", "bytes": 923, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#tbl3", "version": null, "note": "Newcastle-Ottawa scale for assessing case-control study quality", "structure": {"pmcid": "PMC6113772", "section_index": 9, "section_title": "Study level characteristics", "row_count": 14, "column_count": 5}, "table": {"label": "Table 3", "caption": "Newcastle-Ottawa scale for assessing case-control study quality", "rows": [["Author, year (Pubmed ID)", "Selection(Max=4)", "Comparability(Max=2)", "Exposure(Max=3)", "Overall quality score (Max=9)"], ["Afridi, 2011 (20480400)", "4", "1", "2", "7"], ["Downer, 2016 (28056794)", "4", "2", "3", "9"], ["Guallar, 2005 (11570992)", "2", "2", "2", "6"], ["Hallgren, 2001 (11572934)", "3", "2", "3", "8"], ["James, 2015 (25350952)", "4", "2", "2", "8"], ["Kok, 1988 (3394701)", "3", "2", "3", "8"], ["Mozaffarian, 2011 (21428767)", "3", "2", "3", "8"], ["Reunanen, 1996 (8862478)", "2", "2", "3", "7"], ["Ruiz-Navarro, 1998 (9618928)*", "1", "1", "2", "4"], ["Wade, 2015 (25889926)", "2", "2", "2", "7"], ["Wennberg, 2007 (17537290)*", "4", "2", "3", "9"], ["Wennberg, 2011 (21048056)", "4", "2", "3", "9"], ["Yoshizawa, 2002 (12456851)*", "4", "2", "3", "9"]], "row_count": 14, "column_count": 5, "numeric_cells": 69, "header_rows": 1, "locator": "section[9]/table-wrap[3]#tbl3"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the study data pooled behind the published estimate in pmid:30158148 not verified", "asset:source:pmid:30158148 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "meta_analysis", "specific": "random_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": ["random_effects_pool"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 0.7, "band": "medium", "quote": "random effects"}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 1.43, "unit": "relative risk", "tolerance": null, "state": "complete"}], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"axis": "method", "tier": "R1", "blocker": null, "detail": {"outcome": "determined", "family": "meta_analysis", "specific_method": "random_effects", "required_operations": ["random_effects_pool"], "basis": "Every DSL operation this method needs already exists."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": ["random_effects_pool"], "assets": ["asset:table:pmid:30158148:1", "asset:table:pmid:30158148:2", "asset:table:pmid:30158148:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["txt", "unknown"], "capabilities": [], "data_gaps": ["source:pmid:30158148", "materials:the study data pooled behind the published estimate in pmid:30158148", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "ff94837e99f0214d447b7d69f0e90c8a723400925103320500cfc3a449b47cc9", "source_hash": "9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "raw_response_sha256": "sha256:6065345760f884d4b0bb529f96b2f7208f7fe59d840ddc5d0f0de89decbc32cc", "raw_response_chars": 1050}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "ca7124c68013f6f74db1369642b267353a0f0e6ea1f544de0f9a8e3d78021855", "source_hash": "9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "raw_response_sha256": "sha256:ca903b6591a56793cb25e0efbca19f5c8c796e56ad4829368c273e8dd267e6f9", "raw_response_chars": 1509}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "9241c18f88bec221537ac006f71aad7c81480b945b866c3bacdc1328c19c4873", "source_hash": "9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "raw_response": "{\"parent_value\":1.43,\"unit\":\"relative risk\",\"evidence\":\"Comparing top versus bottom thirds of baseline levels, pooled relative risks for arsenic and lead were 1.30 (95% confidence interval 1.04 to 1.63) and 1.43 (1.16 to 1.76) for cardiovascular disease\",\"target_result\":\"The pooled relative risk of cardiovascular disease for lead comparing top versus bottom thirds of baseline levels was 1.43 (1.16 to 1.76).\",\"number_stated\":true}", "reading": {"parent_value": 1.43, "unit": "relative risk", "evidence": "Comparing top versus bottom thirds of baseline levels, pooled relative risks for arsenic and lead were 1.30 (95% confidence interval 1.04 to 1.63) and 1.43 (1.16 to 1.76) for cardiovascular disease", "target_result": "The pooled relative risk of cardiovascular disease for lead comparing top versus bottom thirds of baseline levels was 1.43 (1.16 to 1.76).", "number_stated": true, "source_locator": "chars 980-1177 of source sha256 9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044"}, "recorded_at": "2026-10-31T13:25:07.232571+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "1188aa3d8ecca090596475a05abf8f4604d13dbcfb61031df7c69447d7358c51", "source_hash": "9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044", "raw_response": "{\"parent_value\":1.43,\"unit\":\"relative risk\",\"evidence\":\"Comparing top versus bottom thirds of baseline levels, pooled relative risks for arsenic and lead were 1.30 (95% confidence interval 1.04 to 1.63) and 1.43 (1.16 to 1.76) for cardiovascular disease\",\"target_result\":\"1.43\",\"number_stated\":true}", "reading": {"parent_value": 1.43, "unit": "relative risk", "evidence": "Comparing top versus bottom thirds of baseline levels, pooled relative risks for arsenic and lead were 1.30 (95% confidence interval 1.04 to 1.63) and 1.43 (1.16 to 1.76) for cardiovascular disease", "target_result": "1.43", "number_stated": true, "source_locator": "chars 980-1177 of source sha256 9a0e95b40d40b800a3e0cebc2f1c9b42e8aa9be9f09a2f65bfaf0d0124045044"}, "recorded_at": "2026-10-31T13:25:11.182472+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax-m3-1-flash": "Pooled relative risk 1.43 (95% confidence interval 1.16 to 1.76) for cardiovascular disease when comparing lead levels in the top versus bottom thirds at baseline.", "minimax-m3": "Pooled relative risk of cardiovascular disease for lead comparing top versus bottom thirds of baseline levels: 1.43 (95% confidence interval 1.16 to 1.76).", "decisive": false}, "work_type": {"minimax-m3-1-flash": "analysis_only_for_target", "minimax-m3": "review_or_method_without_reexecutible_result", "decisive": true}, "analysis_methods": {"minimax-m3-1-flash": ["Random-effects meta-analysis", "Standardisation of reported relative risks to a common scale"], "minimax-m3": ["Systematic review and meta-analysis of epidemiological studies", "Standardization of relative risks to a common scale", "Random-effects meta-analysis pooled across studies for each marker", "Comparison of top versus bottom thirds of baseline exposure levels"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["Comparing top versus bottom thirds of baseline levels, the pooled relative risk for lead was 1.43 (95% confidence interval 1.16 to 1.76) for cardiovascular disease.", "Relative risks were standardised to a common scale and pooled across studies for each marker using random effects meta-analyses."], "minimax-m3": ["Comparing top versus bottom thirds of baseline levels, the pooled relative risk for lead was 1.43 (95% confidence interval 1.16 to 1.76) for cardiovascular disease.", "Relative risks were standardized to a common scale and pooled across studies using random-effects meta-analyses."], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "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:6ea829fb81f595cea12e1eaaccfbaabe80d255be10cc34571a58cdc1955a50d1", "type": "sep_package", "label": "SEP v1 package for pmid:30158148"}], "activities": [{"id": "activity:conversion:pmid:30158148", "type": "conversion", "used": ["package:6ea829fb81f595cea12e1eaaccfbaabe80d255be10cc34571a58cdc1955a50d1"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:30158148", "parent_hash": "sha256:c031daa10963d4dd9a069be9a2513004370e362335b23bc22eed8c9f91d6a109", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the study data pooled behind the published estimate in pmid:30158148 not verified", "asset:source:pmid:30158148 not verified", "authors", "data:accession_absent", "execution.not_run", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on data:accession_absent"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:34:32+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}}}