{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27200046", "kind": "science-record", "revision": 8, "content_hash": "sha256:408c713eae347beec3f2e643e7fdfbef93ba6b7e1c1c60056e0541d94c665a4b", "created_at": "2026-11-01T15:40:18Z", "updated_at": "2026-11-01T22:42:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comparative Proteomic Analysis of Soybean Leaves and Roots by iTRAQ Provides Insights into Response Mechanisms to Short-Term Salt Stress.", "doi": "10.3389/fpls.2016.00573", "pmid": "27200046", "authors": ["Wei Ji", "Ru Cong", "Sheng Li", "Rui Li", "Zhiwei Qin", "Yanjun Li", "Xiaolin Zhou", "Sixue Chen", "Jing Li"], "journal": "Frontiers in plant science", "year": 2016, "abstract": "Salinity severely threatens land use capability and crop yields worldwide. Understanding the mechanisms that protect soybeans from salt stress will help in the development of salt-stress tolerant leguminous plants. Here we initially analyzed the changes in malondialdehyde levels, the activities of superoxide dismutase and peroxidases, chlorophyll content, and Na(+)/K(+) ratios in leaves and roots from soybean seedlings treated with 200 mM NaCl at different time points. We found that the 200 mM NaCl treated for 12 h was optimal for undertaking a proteomic analysis on soybean seedlings. An iTRAQ-based proteomic approach was used to investigate the proteomes of soybean leaves and roots under salt treatment. These data are available via ProteomeXchange with the identifier PXD002851. In total, 278 and 440 proteins with significantly altered abundances were identified in leaves and roots of soybean, respectively. From these data, a total of 50 proteins were identified in the both tissues. These differentially expressed proteins (DEPs) were from 13 biological processes. Moreover, protein-protein interaction analysis revealed that proteins involved in metabolism, carbohydrate and energy metabolism, protein synthesis and redox homeostasis could be assigned to four high salt stress response networks. Furthermore, semi-quantitative RT-PCR analysis revealed that some of the proteins, such as a 14-3-3, MMK2, PP1, TRX-h, were also regulated by salt stress at the level of transcription. These results indicated that effective regulatory protein expression related to signaling, membrane and transport, stress defense and metabolism all played important roles in the short-term salt response of soybean seedlings.", "claims": [{"id": "claim-method", "statement": "The different letters above columns indicated significant differences among different treatment time of soybean plants based on one-way ANOVA (p < 0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27200046", "locator": "sections[12] \"Physiological changes of soybean plants under salt treatment\" paragraph 5", "quote": "The different letters above columns indicated significant differences among different treatment time of soybean plants based on one-way ANOVA (p < 0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The MS proteomics data have been deposited in the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaino et al., 2013) with the data set identifier PXD002851.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27200046", "locator": "sections[9] \"Data analysis and interpretation\" paragraph 2", "quote": "The MS proteomics data have been deposited in the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaino et al., 2013) with the data set identifier PXD002851."}], "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:27200046"], "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:PXD002851"], "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:PXD002851"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27200046", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fpls.2016.00573", "sha256": "sha256:7f02552c40a382b8d2f1fea3f3ea433733f93e0c3762ee5d4b24a2471661546f", "bytes": 64264, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fpls.2016.00573", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4850148", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002851", "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=PXD002851", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002851", "version": null, "note": "The MS proteomics data have been deposited in the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaino et al., 2013) with the data set identifier PXD002851.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The MS proteomics data have been deposited in the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaino et al., 2013) with the data set identifier PXD002851.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative proteomics reveals an important role of GsCBRLK in salt stress response of soybean", "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:27200046:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:877cade0292f889cecac9e83eeeb27b2a269120e4548da4e2d6ca912aa6a3f76", "bytes": 3569, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T1", "version": null, "note": "Signaling-related proteins differentially expressed under salt stress in soybean leaves and roots.", "structure": {"pmcid": "PMC4850148", "section_index": 14, "section_title": "Functional classification of salt-responsive proteins", "row_count": 32, "column_count": 7}, "table": {"label": "Table 1", "caption": "Signaling-related proteins differentially expressed under salt stress in soybean leaves and roots.", "rows": [["", "Leaves", "Roots"], ["", "Protein ID", "Protein name", "Mean 115/113", "Protein ID", "Protein name", "Mean 119/117"], ["(1) Ca2+ sensor", "UniRef100_C6TNH2", "Calcium sensor", "4.65", "UniRef100_I1K7B7", "Calcium ion binding", "10.92"], ["", "UniRef100_I1K180", "Calcium sensing chloroplastic-like", "3.31", "UniRef100_I1JST7", "Calcium ion binding", "8.91"], ["", "UniRef100_I1K181", "Calcium sensing chloroplastic-like", "3.27", "UniRef100_K7L8B5", "Calcium ion binding", "4.36"], ["", "UniRef100_I1JRM7", "Calcium-binding ef hand family protein", "0.42", "", "", ""], ["", "UniRef100_A0A762", "Calreticulin", "0.28", "", "", ""], ["(2) 14-3-3", "UniRef100_E9KNA6", "14-3-3 Protein", "1.55", "UniRef100_I1K9V8", "14-3-3 Protein", "2.47"], ["", "UniRef100_C6TCD3", "14-3-3 Protein", "1.45", "UniRef100_E9KNA6", "14-3-3 Protein", "2.44"], ["", "UniRef100_C6TGW2", "14-3-3-like Protein", "1.41", "UniRef100_C6TGW2", "14-3-3-like Protein", "2.31"], ["", "UniRef100_C6TBV3", "14-3-3-like Protein d-like", "0.69", "", "", ""], ["(3) Kinases/phosphatases", "UniRef100_I1KIV5", "Serine threonine-protein phosphatase 2a 65 kda regulatory subunit a beta isoform-like", "2.83", "UniRef100_K7LNY2", "Serine threonine-protein kinase sepa-like", "4.97"], ["", "UniRef100_K7MVS5", "Protein kinase", "1.32", "UniRef100_C6TB76", "Serine threonine protein phosphatase pp1", "3.46"], ["", "", "", "", "UniRef100_C6T7X3", "Mitogen-activated protein kinase homolog mmk2-like", "15.79"], ["(4) Probable receptor", "", "", "", "UniRef100_I1LV96", "Probable leucine-rich repeat receptor-like serine threonine-protein kinase at3g14840-like", "3.55"], ["", "", "", "", "UniRef100_K7N5H4", "G-type lectin s-receptor-like serine threonine-protein kinase rlk1-like", "0.07"], ["(5) Small G protein related", "UniRef100_I1KSQ0", "RAB GDP Dissociation inhibitor alpha-like", "5.28", "UniRef100_I1M057", "Guanylate-binding family protein isoform 1", "6.69"], ["", "UniRef100_C6THN1", "RAB GDP Dissociation inhibitor alpha-like", "5.21", "UniRef100_I1L0T1", "GTP-Binding protein sar1a", "4.61"], ["", "UniRef100_C6TJD3", "Guanine nucleotide-binding protein subunit beta-like", "1.69", "UniRef100_K7MNY8", "GTPase obg-like", "4.10"], ["", "UniRef100_I1K5E6", "Guanine nucleotide-binding protein subunit beta-like", "1.64", "UniRef100_I1KX26", "Probable ADP-ribosylation factor GTPase-activating protein agd8-like", "2.68"], ["", "", "", "", "UniRef100_I1K5E6", "Guanine nucleotide-binding protein subunit beta-like", "2.12"], ["", "", "", "", "UniRef100_C6TJD3", "Guanine nucleotide-binding protein subunit beta-like", "2.11"], ["", "", "", "", "UniRef100_K7MYR4", "Ras GTPase-activating protein-binding protein", "1.30"], ["", "", "", "", "UniRef100_C6SY78", "Rab6-interacting golgin-like isoform x2", "1.35"], ["", "", "", "", "UniRef100_C6TB49", "Rab6-interacting golgin-like isoform x2", "1.31"], ["(6) Phospholipase", "UniRef100_I1JI90", "Phospholipase c", "2.31", "UniRef100_I1K784", "Phosphatidylinositol 4-kinase alpha", "0.08"], ["(7) Other", "UniRef100_K7KLE6", "Auxilin-like protein", "4.61", "UniRef100_I1J8S5", "Auxilin-related protein 2-like", "4.09"], ["", "UniRef100_K7K6L6", "Auxilin-related protein 2-like", "2.13", "UniRef100_I1L847", "ATP binding", "3.34"], ["", "", "", "", "UniRef100_K7L5V1", "Signal recognition particle 72 kda", "2.32"], ["", "", "", "", "UniRef100_I1M322", "DJ-1 family protein", "2.23"], ["", "", "", "", "UniRef100_K7MIT8", "RJ2 Protein", "2.20"], ["", "", "", "", "UniRef100_K7LS27", "COP1-Interacting protein 4", "1.59"]], "row_count": 32, "column_count": 7, "numeric_cells": 115, "header_rows": 2, "locator": "section[14]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:27200046:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b4897613267386335de6248a0b98478bff734b44865c31589ecc34a04005616", "bytes": 3600, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T2", "version": null, "note": "Membrane and transport-related proteins differentially expressed under salt stress in soybean leaves and roots.", "structure": {"pmcid": "PMC4850148", "section_index": 14, "section_title": "Functional classification of salt-responsive proteins", "row_count": 34, "column_count": 7}, "table": {"label": "Table 2", "caption": "Membrane and transport-related proteins differentially expressed under salt stress in soybean leaves and roots.", "rows": [["", "Leaves", "Roots"], ["", "Protein ID", "Protein name", "Mean 115/113", "Protein ID", "Protein name", "Mean 119/117"], ["(1) ABC transporter", "UniRef100_Q8W1S2", "ABC Transporter f family member 3-like", "8.80", "UniRef100_Q8W1S2", "ABC Transporter f family member 3-like", "0.43"], ["", "", "", "", "UniRef100_I1NEA8", "ABC Transporter f family member 3-like", "0.05"], ["", "", "", "", "UniRef100_K7M3S0", "ABC Transporter g family member 36-like", "0.03"], ["(2) Other transporter", "UniRef100_C6TJX8", "29 kda Chloroplastic-like", "7.14", "UniRef100_I1LNP0", "Cytosolic factor", "8.95"], ["", "UniRef100_I1KYL0", "Web family protein at5g55860-like", "3.17", "UniRef100_C6TBK9", "ER Membrane protein complex subunit 2-like", "6.17"], ["", "UniRef100_I1KDU7", "Proton pump-interactor 1-like", "2.82", "UniRef100_I1KWA0", "Cytosolic factor", "4.32"], ["", "UniRef100_I1MGI7", "Importin subunit alpha-1-like", "1.58", "UniRef100_C6TDM9", "Membrane-associated 30 kda chloroplastic-like", "4.22"], ["", "UniRef100_I1L0U6", "Importin subunit alpha-1-like", "1.53", "UniRef100_I1KFG3", "Outer envelope protein chloroplastic-like", "4.02"], ["", "UniRef100_C6TL60", "Probable plastid-lipid-associated protein chloroplastic-like", "0.67", "UniRef100_C6TH54", "Probable plastid-lipid-associated protein chloroplastic-like", "3.31"], ["", "", "", "", "UniRef100_I1KYL0", "Web family protein at5g55860-like", "2.43"], ["", "", "", "", "UniRef100_I1LB65", "Importin subunit alpha-1-like", "1.32"], ["(3) ATPase", "", "", "", "UniRef100_I1KPH2", "V-type proton ATPase subunit e-like", "7.42"], ["", "", "", "", "UniRef100_I1KG34", "V-Type proton ATPase catalytic subunit a-like", "2.23"], ["", "", "", "", "UniRef100_I1KVU0", "V-Type proton ATPase catalytic subunit a-like", "2.17"], ["", "", "", "", "UniRef100_D7EYG6", "V-Type proton ATPase catalytic subunit a-like", "2.17"], ["(4) Ion channel", "UniRef100_K7L7I9", "Potassium channel", "1.40", "UniRef100_I1JFN3", "Copper transport protein atox1", "1.55"], ["", "UniRef100_I1JH50", "k(+) h(+) Antiporter", "0.65", "", "", ""], ["(5) Vesicle trafficking", "UniRef100_I1MZ13", "Clathrin heavy chain 1-like", "2.42", "UniRef100_I1JKB3", "Remorin family protein", "10.42"], ["", "UniRef100_Q39834", "Clathrin heavy chain 1-like", "2.27", "UniRef100_I1K8U2", "Clathrin assembly protein at2g25430-like", "3.89"], ["", "UniRef100_I1LNP0", "Cytosolic factor", "1.80", "UniRef100_Q39834", "Clathrin heavy chain 1-like", "2.65"], ["", "UniRef100_C6TJF6", "Annexin-like protein", "1.52", "UniRef100_I1JIA0", "Clathrin heavy chain 1-like", "1.88"], ["", "UniRef100_K7LQG2", "Aquaporin pip2-7", "1.31", "UniRef100_I1MZ13", "Clathrin heavy chain 1-like", "1.83"], ["", "UniRef100_I1M8Y5", "Clathrin interactor epsin 1-like", "0.66", "UniRef100_I1N727", "Nuclear pore membrane glycoprotein 210-like", "1.39"], ["", "", "", "", "UniRef100_I1M7W9", "Aquaporin protein pip11", "0.07"], ["", "", "", "", "UniRef100_K7M2D8", "Trafficking protein particle complex subunit 10-like", "0.03"], ["", "", "", "", "UniRef100_C6TMQ6", "Stomatin-like protein", "13.32"], ["(6) Other", "", "", "", "UniRef100_C6TKQ1", "Gem-like protein 1-like", "11.09"], ["", "", "", "", "UniRef100_I1N0D7", "Protein to RNADo 1-like", "9.53"], ["", "", "", "", "UniRef100_K7KMV4", "Endonuclease or glycosyl hydrolase", "3.74"], ["", "", "", "", "UniRef100_I1KIU7", "Protein CASP-like", "1.38"], ["", "", "", "", "UniRef100_I1JV52", "Gem-like protein 1-like", "0.59"], ["", "", "", "", "UniRef100_I1LJG0", "Nucleotide-diphospho-sugar transferase family protein", "0.02"]], "row_count": 34, "column_count": 7, "numeric_cells": 127, "header_rows": 2, "locator": "section[14]/table-wrap[2]#T2"}}], "gaps": ["asset:data:geo:PXD002851 not downloaded", "asset:data:geo:PXD002851 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The different letters above columns indicated significant differences among different treatment time of soybean plants based on one-way ANOVA (p < 0.05)."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "targets": [], "gaps": []}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["PXD002851"], "resolved_accessions": ["PXD002851"], "statements": ["The MS proteomics data have been deposited in the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaino et al., 2013) with the data set identifier PXD002851."], "basis": "The paper names PXD002851 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:27200046", "data:geo:PXD002851", "asset:table:pmid:27200046:1", "asset:table:pmid:27200046:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002851"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:08:03Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 48070, "completion_tokens": 1761, "cached_tokens": 648}}, "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:27200046", "type": "paper", "label": "pmid:27200046"}, {"id": "source:pmid:27200046", "type": "manuscript", "label": "PMID 27200046 full text"}, {"id": "data:geo:PXD002851", "type": "dataset", "label": "GEO PXD002851"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27200046", "type": "paper", "label": "pmid:27200046"}, {"id": "source:pmid:27200046", "type": "manuscript", "label": "PMID 27200046 full text"}, {"id": "data:geo:PXD002851", "type": "dataset", "label": "GEO PXD002851"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27200046", "type": "extraction", "used": ["source:pmid:27200046"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002851", "type": "accession_resolution", "used": ["data:geo:PXD002851"], "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:27200046", "parent_hash": "sha256:431fbb2e4b6166abcc8d97c91a887e2d5be36207b50dbdc342f0589557ca7fe7", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD002851 licence not read", "asset:data:geo:PXD002851 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The different letters above columns indicated significant differences among different treatment time of soybean plants based on one-way ANOVA (p < 0.05)."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T02:11:08+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}}}