{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32483281", "kind": "science-record", "revision": 6, "content_hash": "sha256:1cbde98a6cf8825ecdbd2b8c53eb7264259d69fb21c83a7f624565e8b950ea1b", "created_at": "2026-11-01T15:41:02Z", "updated_at": "2026-11-01T21:23:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteome and transcriptome reveal the involvement of heat shock proteins and antioxidant system in thermotolerance of Clematis florida.", "doi": "10.1038/s41598-020-65699-2", "pmid": "32483281", "authors": ["Changhua Jiang", "Yuke Bi", "Jianbin Mo", "Ruyao Zhang", "Mingnan Qu", "Shucheng Feng", "Jemaa Essemine"], "journal": "Scientific reports", "year": 2020, "abstract": "Clematis florida Thun (CfT) is an ornamental and medicinal plant. It is a cold resistant but heat sensitive species and deserves to be further investigated to improve its adaptability to heat stress. Exploring the molecular mechanism potential via an omic-analysis constitutes a promising approach towards improving heat tolerance of CfT. Two CfT lines, heat resistance (HR) and heat sensitive (HS), with differential thermotolerance capacities were used for the integrative analyses of proteomics and transcriptomes. Transcriptomes analysis showed that various pathways were significantly enriched including plant hormone signal transduction and carbon fixation pathways in prokaryotes. Proteomics study revealed the enrichment of some other pathways comprising antioxidant activity and carbohydrates metabolism. Based on combined transcriptomes and proteomics analyses and following heat stress treatment, a total of 1724 annotated genes were overlapped between both CfT lines. Particularly, 84 differential expressed genes (DEGs) were overlapped in both CfT lines. Fifteen out of these 84 genes were up-regulated solely for HR line (PS) but not for HS one (SG). This strongly suggests a potential prominent role for these genes in the thermotolerance process in PS line. We corroborate that two Hsps (Hsp18 and Hsp70) out of 20 detected proteins with higher expression levels in PS than in SG based on either global transcripts or proteins levels. According to the transcriptomes and proteomics analyses, 6 proteins and their corresponding genes were found to be significantly abundant in HR line (PS). Data are available via ProteomeXchange with identifier PXD018192. The expressions levels of these 6 genes were checked also for both CfT lines to evaluate their potential contributions in the heat tolerance process. Thus, their expression levels were approximately 2~4 times higher in HR than in HS line. We provided as well a representative schematic model to highlight the key genes involved in ROS scavenging and photorespiratory pathway in CfT. This model could be helpful also in understanding the mechanism of heat tolerance in CfT.", "claims": [{"id": "claim-method", "statement": "The resulting adjusted P-values, according to the Benjamini and Hoch-berg’s approach, were used to monitor the false discovery rate (FDR).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32483281", "locator": "sections[11] \"Identification of differentially expressed genes (DEGs)\" paragraph 2", "quote": "The resulting adjusted P-values, according to the Benjamini and Hoch-berg’s approach, were used to monitor the false discovery rate (FDR)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32483281", "locator": "sections[7] \"RNA extraction and library preparation for transcriptome analysis\" paragraph 2", "quote": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804."}, {"asset": "source:pmid:32483281", "locator": "sections[10] \"LC-MS/MS and data analysis\" paragraph 2", "quote": "The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192."}], "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:32483281"], "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:PXD018192"], "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:PXD018192"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32483281", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-020-65699-2", "sha256": "sha256:2320edec89a9631a835a033e363894920bc69ef23d3f0bbe50701e8d8a95b121", "bytes": 52236, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-020-65699-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7264250", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD018192", "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=PXD018192", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD018192", "version": null, "note": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic dataset for clematis in respose to heat stress", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRP108804", "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=SRP108804", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP108804", "version": null, "note": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32483281:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eb794d2a216b98bed6571969e04de7e51389d8327de24e549e335e113b362de0", "bytes": 394, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab1", "version": null, "note": "SOD activities of two CfT lines (PS and SG) exposed to heat stress treatments.", "structure": {"pmcid": "PMC7264250", "section_index": 15, "section_title": "Physiological profiling in both CfT lines in response to heat stress", "row_count": 3, "column_count": 4}, "table": {"label": "Table 1", "caption": "SOD activities of two CfT lines (PS and SG) exposed to heat stress treatments.", "rows": [["CfT lines", "Control (%/g. FW)", "Heat stress (%/g. FW)", "Differences (%)"], ["PS", "22.24 ± 0.72", "50.96 ± 0.56", "129"], ["SG", "29.66 ± 1.12", "29.93 ± 1.03", "0.91"]], "row_count": 3, "column_count": 4, "numeric_cells": 6, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32483281:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:597e9dec1cf2fc4d2ffe9f1096f8415ff804465fa8d826dea2374a307f6cbec2", "bytes": 2077, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#Tab2", "version": null, "note": "Up-regulated 15 genes in CfT PS line in both transcriptomes and proteomics analyses.", "structure": {"pmcid": "PMC7264250", "section_index": 16, "section_title": "Integrative analysis of transcriptomes and proteomics in both CfT lines", "row_count": 16, "column_count": 4}, "table": {"label": "Table 2", "caption": "Up-regulated 15 genes in CfT PS line in both transcriptomes and proteomics analyses.", "rows": [["Protein", "Transcript", "Abbre", "Description"], ["cdsTRINITY_DN115825_c1_g2_m58122", "ORTHOMCL14236", "GLUST", "Glutathione-S-transferase tau 1 (Hevea brasiliensis)"], ["cdsTRINITY_DN117586_c0_g2_m50305", "ORTHOMCL16012", "GO1", "Gglycolate oxidase1, chloroplastic-like (Fragaria vesca subsp Vesca)"], ["cdsTRINITY_DN108848_c1_g2_m66744", "ORTHOMCL7824", "RPE3", "Ribulose-phosphate 3-epimerase, cytoplasmic isoform (Malus domestica)"], ["cdsTRINITY_DN111615_c0_g1_m847", "ORTHOMCL10183", "R5PI", "Ribose-5-phosphate isomerase 3, chloroplastic (Cucumis melo)"], ["cdsTRINITY_DN108758_c3_g1_m45874", "ORTHOMCL7756", "rbcS", "Ribusco small subunit (Panax ginseng)"], ["cdsTRINITY_DN117844_c1_g1_m47440", "ORTHOMCL16305", "POD4", "Peroxidase 4 (Vitis vinifera)"], ["cdsTRINITY_DN113183_c1_g1_m25469", "ORTHOMCL11612", "HSP18", "18 kDa class II heat shock protein-like (Malus domestica)"], ["cdsTRINITY_DN105472_c0_g1_m18350", "ORTHOMCL5475", "HSP70", "Heat shock cognate 70 kDa protein 2-like (Cucumis melo)"], ["cdsTRINITY_DN94901_c0_g1_m31462", "ORTHOMCL18094", "PRP1", "Putative pathogenesis-related protein 1 (Vitis hybrid cultivar)"], ["cdsTRINITY_DN102906_c0_g1_m54008", "ORTHOMCL4000", "EP1-like", "Epidermis-specific secreted glycoprotein EP1-like (Solanum tuberosum)"], ["cdsTRINITY_DN111577_c2_g1_m15214", "ORTHOMCL10140", "Pru2A", "Putative allergen Pru du 201 A (Prunus dulcis x Prunus persica)"], ["cdsTRINITY_DN106744_c0_g1_m25289", "ORTHOMCL6285", "tNFTR", "Tyramine N-feruloyltransferase 4/11-like (Fragaria vesca subsp Vesca)"], ["cdsTRINITY_DN115453_c0_g1_m64076", "ORTHOMCL13846", "EUTSA", "Hypothetical protein EUTSA_v10008067mg (Eutrema salsugineum)"], ["cdsTRINITY_DN107522_c0_g1_m23602", "ORTHOMCL6831", "21 kDa", "21 kDa protein-like (Fragaria vesca subsp Vesca)"], ["cdsTRINITY_DN111222_c2_g1_m34930", "ORTHOMCL9814", "RPT1A", "Regulatory particle triple-A 1A (Theobroma cacao)"]], "row_count": 16, "column_count": 4, "numeric_cells": 45, "header_rows": 1, "locator": "section[16]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:PXD018192 not downloaded", "asset:data:geo:PXD018192 licence not read", "asset:data:geo:SRP108804 not downloaded", "asset:data:geo:SRP108804 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Benjamini–Hochberg false discovery rate adjustment", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The resulting adjusted P-values, according to the Benjamini and Hoch-berg’s approach, were used to monitor the false discovery rate (FDR)."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["SRP108804", "PXD018192"], "resolved_accessions": ["PXD018192"], "statements": ["The raw data are available in the national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) under accession number SRP108804. The mass spectrometry proteomics data has been deposited to the ProteomeXchange Consortium via the PRIDE16 partner repository with the dataset identifier PXD018192."], "basis": "The paper names PXD018192 in national center for biotechnology information sequence read archive (www.ncbi.nlm.nih.gov/Trace/sra) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:32483281", "data:geo:PXD018192", "asset:table:pmid:32483281:1", "asset:table:pmid:32483281:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD018192"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "reordered"}, "calls": 3, "usage": {"prompt_tokens": 39149, "completion_tokens": 1685, "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:32483281", "type": "paper", "label": "pmid:32483281"}, {"id": "source:pmid:32483281", "type": "manuscript", "label": "PMID 32483281 full text"}, {"id": "data:geo:PXD018192", "type": "dataset", "label": "GEO PXD018192"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32483281", "type": "paper", "label": "pmid:32483281"}, {"id": "source:pmid:32483281", "type": "manuscript", "label": "PMID 32483281 full text"}, {"id": "data:geo:PXD018192", "type": "dataset", "label": "GEO PXD018192"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32483281", "type": "extraction", "used": ["source:pmid:32483281"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD018192", "type": "accession_resolution", "used": ["data:geo:PXD018192"], "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:32483281", "parent_hash": "sha256:6e90fe2a7bd4896bdd86517de28436b22850ce010ee6489ee76f655bfa4eded0", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD018192 licence not read", "asset:data:geo:PXD018192 not downloaded", "asset:data:geo:SRP108804 licence not read", "asset:data:geo:SRP108804 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["of Hsp70 and Hsp18 were further confirmed by qPCR (Fig. 4B). The differences in expressions of", "y expressed genes between PS and SG based on qPCR experiments. Each bar data is the average of", "and proteomics analyses in PS line based on qPCR experiments. Each bar data is the average of", "e performed qRT-PCR analysis. Therefore, the qPCR results reflect no significant difference in"], "order_basis": "paper_text_order:13386", "id": "assay:1"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["principal component analysis"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:06:55+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}}}