{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29922265", "kind": "science-record", "revision": 6, "content_hash": "sha256:397c32fdf10265dfc6952943c11ee79ff6a18e1851699d0b287504a569694274", "created_at": "2026-11-01T15:40:35Z", "updated_at": "2026-11-01T21:21:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Induction by Bradyrhizobium diazoefficiens of Different Pathways for Growth in D-mannitol or L-arabinose Leading to Pronounced Differences in CO2 Fixation, O2 Consumption, and Lateral-Flagellum Production.", "doi": "10.3389/fmicb.2018.01189", "pmid": "29922265", "authors": ["Carolina Cogo", "Julieta Pérez-Giménez", "Chandrasekar B Rajeswari", "María F Luna", "Aníbal R Lodeiro"], "journal": "Frontiers in microbiology", "year": 2018, "abstract": "Bradyrhizobium diazoefficiens, a soybean N2-fixing symbiont, constitutes the basic input in one of the most prominent inoculant industries worldwide. This bacterium may be cultured with D-mannitol or L-arabinose as carbon-plus-energy source (C-source) with similar specific growth rates, but with higher biomass production with D-mannitol. To better understand the bacterium's carbon metabolism, we analyzed, by liquid chromatography and tandem mass spectrometry (MS), the whole set of proteins obtained from cells grown on each C-source. Among 3,334 proteins identified, 266 were overproduced in D-mannitol and 237 in L-arabinose, but among these, only 22% from D-mannitol cultures and 35% from L-arabinose cultures were annotated with well defined functions. In the D-mannitol-differential pool we found 19 enzymes of the pentose-phosphate and Calvin-Benson-Bassham pathways and accordingly observed increased extracellular-polysaccharide production by D-mannitol grown bacteria in a CO2-enriched atmosphere. Moreover, poly-3-hydroxybutyrate biosynthesis was increased, suggesting a surplus of reducing power. In contrast, the L-arabinose-differential pool contained 11 enzymes of the L-2-keto-3-deoxyarabonate pathway, 4 enzymes for the synthesis of nicotinamide-adenine dinucleotide from aspartate, with those cultures having a threefold higher O2-consumption rate than the D-mannitol cultures. The stoichiometric balances deduced from the modeled pathways, however, resulted in similar O2 consumptions and ATP productions per C-mole of substrate. These results suggested higher maintenance-energy demands in L-arabinose, which energy may be used partly for flagella-driven motility. Since B. diazoefficiens produces the lateral-flagella system in only L-arabinose, we calculated the O2-consumption rates of a lafR::Km mutant devoid of lateral flagella cultured in L-arabinose or D-mannitol. Contrary to that of the wild-type, the O2-consumption rate of this mutant was similar on both C-sources, and accordingly outcompeted the wild-type in coculture, suggesting that the lateral flagella behaved as parasitic structures under these conditions. Proteomic data are available via ProteomeXchange with identifier PXD008263.", "claims": [{"id": "claim-method", "statement": "For proteomic comparisons, we employed duplicate or triplicate independent cultures (biologic replicates) from each culture medium and each subcellular fraction. With these replicates we constructed volcano plots to compare the samples using the logarithmic values of the ratio of the areas under the peaks along with the statistical significance of those values assessed by the Student-t-test (not shown).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29922265", "locator": "sections[10] \"Statistical Procedures\" paragraph 2", "quote": "For proteomic comparisons, we employed duplicate or triplicate independent cultures (biologic replicates) from each culture medium and each subcellular fraction. With these replicates we constructed volcano plots to compare the samples using the logarithmic values of the ratio of the areas under the peaks along with the statistical significance of those values assessed by the Student-t-test (not shown)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE (Vizcaíno et al., 2016) partner repository with the dataset identifier PXD008263 and 10.6019/PXD008263.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29922265", "locator": "sections[11] \"Data Submission\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE (Vizcaíno et al., 2016) partner repository with the dataset identifier PXD008263 and 10.6019/PXD008263."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The study identified 3,334 proteins by liquid chromatography–tandem mass spectrometry; differential expression was defined by a Student’s t-test with fold changes greater than 2 and p-values below 0.05, and the underlying proteomics dataset was deposited in ProteomeXchange/PRIDE as PXD008263.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:29922265"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29922265", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmicb.2018.01189", "sha256": "sha256:407b673d7ab9cfe4d83860f4cc454d6e47edc314cd6f50c93fc8b4fbd0fd0330", "bytes": 74652, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmicb.2018.01189", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5996035", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:29922265:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ae852e8138abc3c87d7457b196dead6b5c77353c303774b3a97a4c300d9a4c9b", "bytes": 760, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "Summary of the proteins identified by nLC-MS/MS with an Orbitrap instrument in three biological replicas (samples) of B. diazoefficiens growing in the indicated liquid media.", "structure": {"pmcid": "PMC5996035", "section_index": 13, "section_title": "Differential-Protein Profiles", "row_count": 11, "column_count": 5}, "table": {"label": "Table 1", "caption": "Summary of the proteins identified by nLC-MS/MS with an Orbitrap instrument in three biological replicas (samples) of B. diazoefficiens growing in the indicated liquid media.", "rows": [["", "Number of different proteins detected in the fractions"], ["", "HMY-Mtl", "HMY-Ara"], ["Sample #", "Cytoplasm-enriched", "Membrane-enriched", "Cytoplasm-enriched", "Membrane-enriched"], ["1", "407", "597", "1390", "31"], ["2", "1948", "1531", "1797", "1583"], ["3", "1966", "1729", "1784", "1854"], ["", "", "", "", ""], ["Average", "1440", "1286", "1657", "1156"], ["", "", "", "", ""], ["Total", "3008", "", "3018"], ["% Superposition cytoplasm/membrane", "37.7", "", "35.3"]], "row_count": 11, "column_count": 5, "numeric_cells": 23, "header_rows": 3, "locator": "section[13]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:29922265:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4ff0ec6d249b0e192a5fe1f4c1f4387cdd9194267b56d351ffc6e8249071b007", "bytes": 5535, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#T2", "version": null, "note": "Selected proteins from the MtlDP and the AraDP that seemed to play roles in the metabolic pathways and in motility.", "structure": {"pmcid": "PMC5996035", "section_index": 13, "section_title": "Differential-Protein Profiles", "row_count": 64, "column_count": 6}, "table": {"label": "Table 2", "caption": "Selected proteins from the MtlDP and the AraDP that seemed to play roles in the metabolic pathways and in motility.", "rows": [["Gene tag (Rhizobase)", "Protein ID (Uniprot)", "Gene name", "Description", "Fold-change (log2 Mtl area/Ara area)"], ["", "", "", "", "Cytoplasm", "Membrane"], ["", "", "", "Mtl catabolic pathway", "", ""], ["blr0337", "Q89XH7", "", "Putative carbon monoxide dehydrogenase medium chain.", "1.1132", "NS"], ["bll1419", "Q89UJ7", "metF", "Methylenetetrahydrofolate reductase.", "In only Mtl", "NS"], ["bll1521", "Q89U96", "", "Putative fructose-1.6-bisphosphate aldolase protein.", "1.9439", "NS"], ["blr2168", "Q89T82", "", "Putative transketolase alpha subunit protein.", "In only Mtl", "-"], ["blr2581", "Q8GKS1", "fbp", "Fructose-1.6-bisphosphatase class 1.", "In only Mtl", "-"], ["blr2582", "H7C6I1", "cbbP", "Phosphoribulokinase.", "In only Mtl", "-"], ["blr2583", "H7C6U6", "cbbT", "Transketolase.", "In only Mtl", "In only Mtl"], ["blr2584", "H7C7W4", "cbbA", "Fructose-bisphosphate aldolase.", "In only Mtl", "In only Mtl"], ["blr2585", "Q9ZI34", "cbbL", "Ribulose bisphosphate carboxylase large chain.", "In only Mtl", "In only Mtl"], ["blr2586", "Q9ZI33", "cbbS", "Ribulose bisphosphate carboxylase small chain.", "In only Mtl", "In only Mtl"], ["blr2588", "Q89S24", "cbbE", "Ribulose-phosphate 3-epimerase.", "In only Mtl", "-"], ["blr2815", "Q89RF7", "", "Putative transketolase family protein. Pyruvate dehydrogenase E1 component.", "In only Mtl", "In only Mtl"], ["blr3224", "Q89QA6", "", "ABC transporter ATP-binding protein. Putative sorbitol/mannitol transport system.", "In only Mtl", "NS"], ["blr3225", "Q89QA5", "", "Oxidoreductase. Similar to putative Glucose/ribitol oxidoreductase.", "5.0927", "In only Mtl"], ["blr3226", "Q89QA4", "", "Ribitol kinase", "3.9234", "-"], ["blr3227", "Q89QA3", "", "Putative fructokinase.", "In only Mtl", "-"], ["bll3754", "Q89NT0", "gph", "Phosphoglycolate phosphatase.", "In only Mtl", "NS"], ["bll6549", "Q89FZ9", "", "D-3-phosphoglycerate:NAD+ oxidoreductase", "In only Mtl", "-"], ["blr7063", "Q89EL0", "", "Probable 2-ketogluconate reductase.", "2.5998", "-"], ["", "", "", "Ara catabolic pathway", "", ""], ["bll1188", "Q89V68", "atpB", "ATP synthase subunit a.", "-", "In only Ara"], ["blr2316", "Q89ST4", "", "Probable NADH-ubiquinone oxidoreductase chain F.", "In only Ara", "-"], ["blr2929", "Q89R43", "", "Hydroxypyruvate isomerase.", "NS", "In only Ara"], ["blr2974", "Q89QZ8", "", "Dehydratase. Similar to a putative D-galactarate dehydratase.", "-1.2323", "-"], ["bll3156", "Q89QH2", "frc", "Formyl-CoA:oxalate CoA-transferase.", "-2.1294", "In only Ara"], ["bll3157", "Q89QH1", "oxc", "Oxalyl-CoA carboxy-lyase.", "-2.3829", "NS"], ["blr3166", "Q89QG2", "gcl", "Glyoxylate carboligase.", "In only Ara", "In only Ara"], ["blr3167", "Q89QG1", "hyi", "Hydroxypyruvate isomerase.", "In only Ara", "In only Ara"], ["blr3168", "Q89QG0", "", "Tartronate semialdehyde reductase.", "In only Ara", "In only Ara"], ["blr3205", "Q89QC3", "", "Dehydrogenase. Similar to Galactose 1-dehydrogenase.", "-", "-3.3450"], ["blr3207", "Q89QC1", "", "L-arabinonolactonase.", "-4.7706", "In only Ara"], ["bll7287", "Q89E00", "dgoA", "2-dehydro-3-deoxyphosphogalactonate aldolase.", "-1.4610", "-"], ["", "", "", "NAD and FAD production", "", ""], ["blr0430", "Q89X84", "nadD", "Probable nicotinate-nucleotide adenylyltransferase.", "-1.3324", "-"], ["bll2541", "Q89S64", "nadB", "L-aspartate oxidase.", "In only Ara", "-1.7782"], ["bll4547", "Q89LJ7", "nadE", "Glutamine-dependent NAD(+) synthetase.", "-1.2616", "-"], ["bll7452", "Q89DI7", "ribH2", "6,7-dimethyl-8-ribityllumazine synthase 2.", "In only Ara", "-"], ["blr8123", "Q89BM5", "", "MutT/nudix family protein.", "-1.3450", "NS"], ["", "", "", "PHB synthesis and degradation", "", ""], ["bll0225", "Q89XT2", "phaB", "Acetoacetyl CoA reductase.", "2.7381", "NS"], ["blr0227", "Q89XT0", "phaR", "Transcriptional regulator of polyhydroxybutirate synthesis.", "1.6828", "NS"], ["blr0908", "Q89VY7", "", "Hypothetical protein. Similar to PHB depolymerase.", "In only Ara", "-2.0085"], ["bll4360", "Q89M33", "phaC1", "Poly-3-hydroxybutyrate synthase.", "2.7271", "NS"], ["bll6073", "Q89HC1", "phaC2", "Polyhydroxybutirate synthase PhaC2.", "In only Ara", "NS"], ["", "", "", "Biotin synthesis", "", ""], ["blr2097", "H7C6S8", "bioF", "8-amino-7-oxononanoate synthase.", "-", "In only Mtl"], ["blr2098", "Q9AMS4", "bioD", "ATP-dependent dethiobiotin synthetase.", "In only Mtl", "-"], ["blr2099", "H7C6S2", "bioA", "Adenosylmethionine-8-amino-7-oxononanoate aminotransferase.", "In only Mtl", "-"], ["blr2221", "Q89T29", "bioA", "Adenosylmethionine-8-amino-7-oxononanoate aminotransferase", "1.1619", "-"], ["bll6273", "Q89GS2", "", "Probable biotin sulfoxide reductase.", "In only Ara", "-"], ["", "", "", "Cell motility and chemotaxis", "", ""], ["blr2343", "Q89SQ7", "cheA", "Chemotaxis two-component sensor histidine kinase.", "NS", "-1.8082"], ["blr2344", "Q89SQ6", "cheWII", "CheWII protein.", "In only Ara", "NS"], ["blr2345", "Q89SQ5", "mcpK", "Methyl-accepting chemotaxis protein.", "NS", "-1.8623"], ["blr2346", "Q89SQ4", "cheW", "CheW protein.", "In only Ara", "-"], ["blr2347", "Q89SQ3", "", "Methyl-accepting chemotaxis protein.", "NS", "-1.5919"], ["blr2349", "Q89SQ1", "cheB", "Chemotaxis response regulator protein-glutamate methylesterase of group 3 operon.", "-", "In only Ara"], ["blr2931", "Q89R41", "", "Putative methyl-accepting chemotaxis protein.", "-", "In only Ara"], ["bll6858", "Q89F43", "flgEL", "Lateral flagellar hook protein", "In only Ara", "-"], ["bll6865", "Q89F36", "lafA2", "Lateral flagellin 2", "In only Ara", "In only Ara"], ["bll6866", "Q89F35", "lafA1", "Lateral flagellin 1", "In only Ara", "In only Ara"]], "row_count": 64, "column_count": 6, "numeric_cells": 143, "header_rows": 2, "locator": "section[13]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:29922265:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:031aeb549704844d4d55c1152d4dba141461c659e34823c5e3eba01591289193", "bytes": 651, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#T3", "version": null, "note": "Stoichiometric balances for maximal ATP production, O2 consumption, and pyruvate production before this intermediate enters the TCA cycle.", "structure": {"pmcid": "PMC5996035", "section_index": 15, "section_title": "Stoichiometric Balances of ATP and Pyruvate Production and of O2 Consumption", "row_count": 9, "column_count": 5}, "table": {"label": "Table 3", "caption": "Stoichiometric balances for maximal ATP production, O2 consumption, and pyruvate production before this intermediate enters the TCA cycle.", "rows": [["C-source", "Proposed pathwaya", "Production/consumption (mole.C-mole of substrate-1)"], ["", "", "ATP", "O2", "Pyruvate"], ["Mtl", "PP", "6.7", "1.1", "0.2"], ["", "CBB (O-OXA)", "4.2", "1.2", "0.1"], ["", "CBB (O-THF)", "4.4", "1.2", "0.3"], ["", "CBB (CO-OXA)", "5.3", "1.2", "0.2"], ["", "CBB (CO-THF)", "5.4", "1.1", "0.3"], ["", "CBB (C)", "6.4", "1.1", "0.3"], ["Ara", "L-KDA", "5.2", "1.1", "0.3"]], "row_count": 9, "column_count": 5, "numeric_cells": 22, "header_rows": 2, "locator": "section[15]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:29922265:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f6ace422dd230774f11480d3dca08e3b74275b3bffe573be8e7203512d1d98bf", "bytes": 922, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T4", "version": null, "note": "Specific rates (±SD) of substrate consumption, product formation, and growth yields of B. diazoefficiens growing in batch cultures in the exponential growth phase.", "structure": {"pmcid": "PMC5996035", "section_index": 20, "section_title": "Analysis of Growth and O2-Consumption Rates", "row_count": 7, "column_count": 7}, "table": {"label": "Table 4", "caption": "Specific rates (±SD) of substrate consumption, product formation, and growth yields of B. diazoefficiens growing in batch cultures in the exponential growth phase.", "rows": [["Propertya", "Wild-type", "lafR::Km mutant"], ["", "HMY-Mtl", "HMY-Ara", "Ratio Ara/Mtl", "HMY-Mtl", "HMY-Ara", "Ratio Ara/Mtl"], ["μmax (h-1)", "0.04 ± 0.01", "0.04 ± 0.02", "1.0", "0.03 ± 0.01", "0.03 ± 0.01", "1.0"], ["qO2max (mmol.g-1.h-1)", "0.86 ± 0.02", "2.53 ± 0.11", "2.9", "1.26 ± 0.12", "1.63 ± 0.07", "1.3"], ["yx/s (C-mole.C-mole-1)", "0.50 ± 0.10", "0.27 ± 0.08", "0.5", "0.52 ± 0.13", "0. 41 ± 0.07", "0.8"], ["qS max (mC-mole.g-1 .h-1)", "2.81 ± 0.46", "7.66 ± 0.47", "2.7", "2.17 ± 0.34", "2.90 ± 0.64", "1.3"], ["qCO2max (mmole.g-1 .h-1)", "0.67 ± 0.03", "2.39 ± 0.05", "3.6", "0.60 ± 0.01", "1.05 ± 0.08", "1.7"]], "row_count": 7, "column_count": 7, "numeric_cells": 35, "header_rows": 2, "locator": "section[20]/table-wrap[1]#T4"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-2", "family": null, "specific": null, "label": "Student-t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For proteomic comparisons, we employed duplicate or triplicate independent cultures (biologic replicates) from each culture medium and each subcellular fraction. With these replicates we constructed volcano plots to compare the samples using the logarithmic values of the ratio of the areas under the peaks along with the statistical significance of those values assessed by the Student-t-test (not shown)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["ols_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ols."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": ["PXD008263 and 10.6019/PXD008263"], "resolved_accessions": [], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE (Vizcaíno et al., 2016) partner repository with the dataset identifier PXD008263 and 10.6019/PXD008263."], "basis": "The paper names PXD008263 and 10.6019/PXD008263, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["ols_fit"], "assets": ["source:pmid:29922265", "asset:table:pmid:29922265:1", "asset:table:pmid:29922265:2", "asset:table:pmid:29922265:3", "asset:table:pmid:29922265:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:54Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 157117, "completion_tokens": 3890, "cached_tokens": 40217}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:29922265", "type": "paper", "label": "pmid:29922265"}, {"id": "source:pmid:29922265", "type": "manuscript", "label": "PMID 29922265 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29922265", "type": "paper", "label": "pmid:29922265"}, {"id": "source:pmid:29922265", "type": "manuscript", "label": "PMID 29922265 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29922265", "type": "extraction", "used": ["source:pmid:29922265"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:29922265", "parent_hash": "sha256:8c3cca5d400ab08bb6c887a8181b2bd812b5eebb7aff7714681a2acdc3f68543", "fork_of": null, "generation": 5}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["industries worldwide. This bacterium may be cultured with D-mannitol or L-arabinose as carbon-plus-ene", "a lafR::Km mutant devoid of lateral flagella cultured in L-arabinose or D-mannitol. Contrary to that"], "order_basis": "paper_text_order:334", "id": "assay:1"}, {"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["nalyzed, by liquid chromatography and tandem mass spectrometry (MS), the whole set of proteins obtained fro", "parasitic structures under these conditions. Proteomic data are available via ProteomeXchange with"], "order_basis": "paper_text_order:606", "id": "assay:2"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["ols_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["linear regression"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T05:13:24+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}}}