{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30891015", "kind": "science-record", "revision": 4, "content_hash": "sha256:96f6de8ed28f8d042da2170573e4f8b169f77b66ed63ec71f63a2aaaeb32dd4b", "created_at": "2026-11-01T15:40:43Z", "updated_at": "2026-11-01T21:22:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Mixotrophic Growth Under Micro-Oxic Conditions in the Purple Sulfur Bacterium \"Thiodictyon syntrophicum\".", "doi": "10.3389/fmicb.2019.00384", "pmid": "30891015", "authors": ["Samuel M Luedin", "Nicola Storelli", "Francesco Danza", "Samuele Roman", "Matthias Wittwer", "Joël F Pothier", "Mauro Tonolla"], "journal": "Frontiers in microbiology", "year": 2019, "abstract": "The microbial ecosystem of the meromictic Lake Cadagno (Ticino, Swiss Alps) has been studied intensively in order to understand structure and functioning of the anoxygenic phototrophic sulfur bacteria community living in the chemocline. It has been found that the purple sulfur bacterium \"Thiodictyon syntrophicum\" strain Cad16T, belonging to the Chromatiaceae, fixes around 26% of all bulk inorganic carbon in the chemocline, both during day and night. With this study, we elucidated for the first time the mode of carbon fixation of str. Cad16T under micro-oxic conditions with a combination of long-term monitoring of key physicochemical parameters with CTD, 14C-incorporation experiments and quantitative proteomics using in-situ dialysis bag incubations of str. Cad16T cultures. Regular vertical CTD profiling during the study period in summer 2017 revealed that the chemocline sank from 12 to 14 m which was accompanied by a bloom of cyanobacteria and the subsequent oxygenation of the deeper water column. Sampling was performed both day and night. CO2 assimilation rates were higher during the light period compared to those in the dark, both in the chemocline population and in the incubated cultures. The relative change in the proteome between day and night (663 quantified proteins) comprised only 1% of all proteins encoded in str. Cad16T. Oxidative respiration pathways were upregulated at light, whereas stress-related mechanisms prevailed during the night. These results indicate that low light availability and the co-occurring oxygenation of the chemocline induced mixotrophic growth in str. Cad16T. Our study thereby helps to further understand the consequences micro-oxic conditions for phototrophic sulfur oxidizing bacteria. The complete proteome data have been deposited to the ProteomeXchange database with identifier PXD010641.", "claims": [{"id": "claim-method", "statement": "Raw data was statistically analyzed using t-tests in Excel (Microsoft Office 2010, v-0.14.0.7168.5000).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30891015", "locator": "sections[7] \"14C-Incubations\" paragraph 3", "quote": "Raw data was statistically analyzed using t-tests in Excel (Microsoft Office 2010, v-0.14.0.7168.5000)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Genomic Data Availability\nThe complete genome of str. Cad16T (Luedin et al., 2018a) is available under the GenBank assembly GCA_002813775.1.\nProteomic Data Availability\nThe complete proteomic data of str. Cad16T have been deposited to the ProteomeXchange Consortium (ProteomeXchange Datasets2) via the PRIDE partner repository (Vizcaíno et al., 2012) under the accession PXD010641 and project DOI 10.6019/PXD010641.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30891015", "locator": "sections[12] \"Genomic Data Availability\" paragraphs 1-2", "quote": "Genomic Data Availability\nThe complete genome of str."}, {"asset": "source:pmid:30891015", "locator": "sections[12] \"Genomic Data Availability\" paragraph 2", "quote": "Cad16T (Luedin et al., 2018a) is available under the GenBank assembly GCA_002813775.1."}, {"asset": "source:pmid:30891015", "locator": "sections[13] \"Proteomic Data Availability\" paragraphs 1-2", "quote": "Proteomic Data Availability\nThe complete proteomic data of str."}, {"asset": "source:pmid:30891015", "locator": "sections[13] \"Proteomic Data Availability\" paragraph 2", "quote": "Cad16T have been deposited to the ProteomeXchange Consortium (ProteomeXchange Datasets2) via the PRIDE partner repository (Vizcaíno et al., 2012) under the accession PXD010641 and project DOI 10.6019/PXD010641."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:30891015"], "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": "complete", "blocked_on": null, "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": ["data:geo:PXD010641"], "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": ["data:geo:PXD010641"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30891015", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmicb.2019.00384", "sha256": "sha256:aef645a12e76e453fdf9078940565210dc2615039415ad97aa7df7d6e8a5dcd5", "bytes": 58100, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmicb.2019.00384", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6413534", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD010641", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PXD010641", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010641", "version": null, "note": "Genomic Data Availability\nThe complete genome of str. Cad16T (Luedin et al., 2018a) is available under the GenBank assembly GCA_002813775.1.\nProteomic Data Availability\nThe complete proteomic data of str. Cad16T have been deposited to the ProteomeXchange Consortium (ProteomeXchange Datasets2) via the PRIDE partner repository (Vizcaíno et al., 2012) under the accession PXD010641 and project DOI 10.6019/PXD010641.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Genomic Data Availability\nThe complete genome of str. Cad16T (Luedin et al., 2018a) is available under the GenBank assembly GCA_002813775.1.\nProteomic Data Availability\nThe complete proteomic data of str. Cad16T have been deposited to the ProteomeXchange Consortium (ProteomeXchange Datasets2) via the PRIDE partner repository (Vizcaíno et al., 2012) under the accession PXD010641 and project DOI 10.6019/PXD010641.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Anoxygenic Photosynthesis and Dark Carbon Metabolism in the Purple Sulfur Bacterium “Thiodictyon syntrophicum“ nov. strain Cad16T", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30891015:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3d06e00128b7d756c508de4bff996784e42b7def7c7bffac28128a8ee01889de", "bytes": 1592, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T1", "version": null, "note": "Functional categories of “Thiodictyon syntrophicum” strain Cad16T proteins that were identified with LC-MS2.", "structure": {"pmcid": "PMC6413534", "section_index": 20, "section_title": "Proteins Quantified With LC-MS2-LFQ", "row_count": 30, "column_count": 3}, "table": {"label": "Table 1", "caption": "Functional categories of “Thiodictyon syntrophicum” strain Cad16T proteins that were identified with LC-MS2.", "rows": [["COG code", "Description", "No. entries"], ["J", "Translation, ribosomal structure, and biogenesis", "64"], ["K", "Transcription", "15"], ["L", "Replication, recombination and repair", "7"], ["D", "Cell cycle control, Cell division, chromosome partitioning", "5"], ["V", "Defense mechanisms", "3"], ["T", "Signal transduction mechanisms", "19"], ["M", "Cell wall/membrane biogenesis", "28"], ["N", "Cell motility", "1"], ["U", "Intracellular trafficking and secretion", "10"], ["O", "Posttranslational modification, protein turnover, chaperones", "50"], ["C", "Energy production and conversion", "93"], ["G", "Carbohydrate transport and metabolism", "35"], ["E", "Amino acid transport and metabolism", "52"], ["F", "Nucleotide transport and metabolism", "12"], ["H", "Coenzyme transport and metabolism", "27"], ["I", "Lipid transport and metabolism", "18"], ["P", "Inorganic ion transport and metabolism", "37"], ["Q", "Secondary metabolites biosynthesis, transport and catabolism", "6"], ["KEGG FUNCTIONAL CATEGORY"], ["Genetic information processing", "78"], ["Carbohydrate metabolism", "78"], ["Energy metabolism", "41"], ["Metabolism of cofactors and vitamins", "29"], ["Amino acid metabolism", "28"], ["Environmental information processing", "27"], ["Nucleotide metabolism", "17"], ["Metabolism of terpenoids and polyketides", "11"], ["Lipid metabolism", "9"], ["Metabolism of other amino acids", "5"]], "row_count": 30, "column_count": 3, "numeric_cells": 28, "header_rows": 1, "locator": "section[20]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30891015:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:242c308917a4867d2d662ee6153763874e3a363996d627879ce7224f293777c7", "bytes": 1691, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#T2", "version": null, "note": "List of “Thiodictyon syntrophicum” strain Cad16T proteins identified as more abundant in the light period.", "structure": {"pmcid": "PMC6413534", "section_index": 21, "section_title": "Proteins Differentially Expressed", "row_count": 22, "column_count": 5}, "table": {"label": "Table 2", "caption": "List of “Thiodictyon syntrophicum” strain Cad16T proteins identified as more abundant in the light period.", "rows": [["Accession", "Name", "COG category", "Cat score", "Lfdr"], ["AUB81546.1", "Cytochrome c1", "C", "5.44", "9.53E-11"], ["AUB83791.1", "NADH-quinone oxidoreductase subunit I", "C", "4.35", "8.32E-05"], ["AUB84560.1", "F0F1 ATP synthase subunit epsilon", "C", "3.51", "2.26E-04"], ["AUB83997.1", "Acetolactate synthase small subunit", "E", "2.88", "1.23E-02"], ["AUB81260.1", "Glucose-6-phosphate isomerase", "G", "3.63", "2.26E-04"], ["AUB83261.1", "Starch synthase", "G", "4.48", "2.53E-06"], ["AUB79823.1", "Thiazole synthase", "H", "2.74", "2.93E-02"], ["AUB81699.1", "Dihydroneopterin aldolase", "H", "3.41", "1.29E-03"], ["AUB83078.1", "DNA topoisomerase I", "L", "2.98", "3.81E-03"], ["AUB84659.1", "Outer membrane lipoprotein carrier protein LolA", "M", "5.43", "2.03E-10"], ["AUB82245.1", "HflK protein", "O", "6.34", "1.24E-13"], ["AUB82609.1", "ATP-dependent protease ATP-binding subunit ClpX", "O", "3.38", "1.29E-03"], ["AUB84025.1", "Molecular chaperone DnaJ", "O", "6.17", "1.24E-13"], ["AUB79510.1", "Hypothetical protein", "S", "2.84", "1.23E-02"], ["AUB81403.1", "Hypothetical protein", "S", "3.53", "2.26E-04"], ["AUB82197.1", "Hypothetical protein", "S", "3.54", "2.26E-04"], ["AUB82687.1", "Hypothetical protein", "S", "3.96", "1.21E-04"], ["AUB83592.1", "Histidine kinase", "S", "3.51", "1.29E-03"], ["AUB84052.1", "Host attachment protein", "S", "3.51", "2.26E-04"], ["AUB84690.1", "Hypothetical protein", "U", "3.02", "3.81E-03"], ["AUB80231.1", "Multidrug ABC transporter ATP-binding protein", "V", "3.83", "1.21E-04"]], "row_count": 22, "column_count": 5, "numeric_cells": 64, "header_rows": 1, "locator": "section[21]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:30891015:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5bebfe0e34b2546626959158c88b3e16f64e94c8adf4e2731b79e80dead2b664", "bytes": 2907, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[2]#T3", "version": null, "note": "List of “Thyodictyon syntrophicum” strain Cad16T proteins identified as more abundant in the dark period.", "structure": {"pmcid": "PMC6413534", "section_index": 21, "section_title": "Proteins Differentially Expressed", "row_count": 40, "column_count": 5}, "table": {"label": "Table 3", "caption": "List of “Thyodictyon syntrophicum” strain Cad16T proteins identified as more abundant in the dark period.", "rows": [["Accession", "Name", "COG category", "cat score", "lfdr"], ["AUB80187.1", "Isocitrate dehydrogenase (NADP)", "C", "2.94", "3.81E-03"], ["AUB81294.1", "Oxidoreductase", "C", "3.54", "2.26E-04"], ["AUB82371.1", "Adenylylsulfate reductase alpha subunit", "C", "3.03", "3.81E-03"], ["AUB83156.1", "NADH dehydrogenase NAD(P)H nitroreductase", "C", "3.03", "3.81E-03"], ["AUB84003.1", "Rubrerythrin", "C", "2.54", "4.44E-02"], ["AUB80125.1", "Cell division protein FtsZ", "D", "2.67", "2.93E-02"], ["AUB79575.1", "Extracellular solute-binding protein, family 3", "E", "2.62", "4.44E-02"], ["AUB81750.1", "Decarboxylase", "E", "2.63", "2.93E-02"], ["AUB83785.1", "4-hydroxy-tetrahydrodipicolinate synthase", "E", "2.94", "4.18E-03"], ["AUB84954.1", "acetolactate synthase", "E", "2.76", "1.95E-02"], ["AUB84325.1", "Proline iminopeptidase", "E", "2.91", "4.18E-03"], ["AUB82337.1", "Adenylosuccinate synthase", "F", "2.54", "4.44E-02"], ["AUB79762.1", "Ubiquinone biosynthesis regulatory protein kinase UbiB", "H", "2.86", "1.23E-02"], ["AUB80927.1", "uBA THIF-type NAD FAD binding", "H", "2.64", "2.93E-02"], ["AUB83525.1", "Synthase", "I", "5.36", "6.66E-10"], ["AUB81024.1", "Lysyl-tRNA synthetase", "J", "3.31", "1.29E-03"], ["AUB79657.1", "OmpA MotB", "M", "5.26", "9.24E-09"], ["AUB80121.1", "Cell wall formation (By similarity)", "M", "3.04", "3.81E-03"], ["AUB83127.1", "Choloylglycine hydrolase", "M", "2.98", "3.81E-03"], ["AUB83783.1", "Conserved repeat domain protein", "M", "2.58", "4.44E-02"], ["AUB83066.1", "Twitching motility protein", "N, U", "3.14", "3.81E-03"], ["AUB79946.1", "Heat-shock protein", "O", "2.65", "2.93E-02"], ["AUB82608.1", "Endopeptidase La", "O", "5.02", "1.01E-07"], ["AUB85620.1", "DnaK-related protein", "O", "2.78", "1.23E-02"], ["AUB81090.1", "Protein of unknown function (DUF971)", "S", "3.55", "2.26E-04"], ["AUB82842.1", "Dinitrogenase iron-molybdenum cofactor biosynthesis protein", "S", "3.30", "3.81E-03"], ["AUB83253.1", "Nitrogen fixation protein", "S", "2.96", "3.81E-03"], ["AUB83860.1", "Tellurite resistance protein TehB", "S", "2.76", "1.23E-02"], ["AUB83943.1", "Short-chain dehydrogenase reductase SDR", "S", "2.91", "4.18E-03"], ["AUB84318.1", "Transposase", "S", "2.99", "3.81E-03"], ["AUB84331.1", "Dienelactone hydrolase", "S", "2.91", "4.18E-03"], ["AUB85354.1", "Protein of unknown function (DUF2868)", "S", "3.78", "2.26E-04"], ["AUB82296.1", "Ppx GppA phosphatase", "T", "2.79", "1.23E-02"], ["AUB82910.1", "YciI-like protein", "T", "2.63", "2.93E-02"], ["AUB79943.1", "General secretion pathway protein G", "U", "2.96", "3.81E-03"], ["AUB80110.1", "Hypothetical protein", "–", "3.21", "3.81E-03"], ["AUB81753.1", "ATPase", "–", "4.76", "1.20E-06"], ["AUB82624.1", "Hypothetical protein", "–", "2.81", "1.23E-02"], ["AUB82926.1", "Hypothetical protein", "–", "2.99", "3.81E-03"]], "row_count": 40, "column_count": 5, "numeric_cells": 121, "header_rows": 1, "locator": "section[21]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:30891015:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9d9944580ff0581a49d139f7cb719b905533bf248e01e56ede4a1f7996f00c5b", "bytes": 667, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#T4", "version": null, "note": "Absolute carbon uptake rates of the microbial community in the Lake Cadagno chemocline.", "structure": {"pmcid": "PMC6413534", "section_index": 22, "section_title": "Discussion", "row_count": 9, "column_count": 6}, "table": {"label": "Table 4", "caption": "Absolute carbon uptake rates of the microbial community in the Lake Cadagno chemocline.", "rows": [["", "Conditions", "", ""], ["", "Light", "Dark", "", ""], ["Photosynthesis", "Oxygenic", "Anoxygenic", "", "Depth [m]", "References"], ["Carbon Uptake Rates [nM h−1]", "3,825", "4,175", "7,608", "11.5", "Camacho et al., 2001"], ["", "1,200", "–", "11.5", "Musat et al., 2008"], ["", "85", "25", "12.5", "Halm et al., 2009"], ["", "6,187", "4,812", "12.0", "Storelli et al., 2013"], ["", "987", "–", "11.4", "Berg et al., 2016"], ["", "757", "587", "14.0", "This study"]], "row_count": 9, "column_count": 6, "numeric_cells": 23, "header_rows": 3, "locator": "section[22]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:PXD010641 not downloaded", "asset:data:geo:PXD010641 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Raw data was statistically analyzed using t-tests in Excel (Microsoft Office 2010, v-0.14.0.7168.5000)."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (t-test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": "R1", "reachable": true, "accessions": ["PXD010641"], "resolved_accessions": ["PXD010641"], "statements": ["Genomic Data Availability\nThe complete genome of str. Cad16T (Luedin et al., 2018a) is available under the GenBank assembly GCA_002813775.1.\nProteomic Data Availability\nThe complete proteomic data of str. Cad16T have been deposited to the ProteomeXchange Consortium (ProteomeXchange Datasets2) via the PRIDE partner repository (Vizcaíno et al., 2012) under the accession PXD010641 and project DOI 10.6019/PXD010641."], "basis": "The paper names PXD010641 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30891015", "data:geo:PXD010641", "asset:table:pmid:30891015:1", "asset:table:pmid:30891015:2", "asset:table:pmid:30891015:3", "asset:table:pmid:30891015:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD010641"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "reordered"}, "calls": 3, "usage": {"prompt_tokens": 46007, "completion_tokens": 1536, "cached_tokens": 792}}, "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:30891015", "type": "paper", "label": "pmid:30891015"}, {"id": "source:pmid:30891015", "type": "manuscript", "label": "PMID 30891015 full text"}, {"id": "data:geo:PXD010641", "type": "dataset", "label": "GEO PXD010641"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30891015", "type": "paper", "label": "pmid:30891015"}, {"id": "source:pmid:30891015", "type": "manuscript", "label": "PMID 30891015 full text"}, {"id": "data:geo:PXD010641", "type": "dataset", "label": "GEO PXD010641"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30891015", "type": "extraction", "used": ["source:pmid:30891015"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD010641", "type": "accession_resolution", "used": ["data:geo:PXD010641"], "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:30891015", "parent_hash": "sha256:a994c432bd96c2c6693c8edeed0c88e513499bbf532303c4e96141c53a221810", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:PXD010641 licence not read", "asset:data:geo:PXD010641 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"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":"2026-11-04T01:25:23+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}}}