{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33628393", "kind": "science-record", "revision": 8, "content_hash": "sha256:7e39d1a6b3728df20d4192fe52b785a7d39a7f361289ef7f5e78afb5e3e96c68", "created_at": "2026-11-01T15:41:26Z", "updated_at": "2026-11-01T22:46:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Upregulation of Matrix Metalloproteinase-9 Protects against Sepsis-Induced Acute Lung Injury via Promoting the Release of Soluble Receptor for Advanced Glycation End Products.", "doi": "10.1155/2021/8889313", "pmid": "33628393", "authors": ["Hui Zhang", "Yan-Fei Mao", "Ying Zhao", "Dun-Feng Xu", "Yan Wang", "Chu-Fan Xu", "Wen-Wen Dong", "Xiao-Yan Zhu", "Ning Ding", "Lai Jiang", "Yu-Jian Liu"], "journal": "Oxidative medicine and cellular longevity", "year": 2021, "abstract": "Dysregulation of matrix metalloproteinase- (MMP-) 9 is implicated in the pathogenesis of acute lung injury (ALI). However, it remains controversial whether MMP-9 improves or deteriorates acute lung injury of different etiologies. The receptor for advanced glycation end products (RAGE) plays a critical role in the pathogenesis of acute lung injury. MMPs are known to mediate RAGE shedding and release of soluble RAGE (sRAGE), which can act as a decoy receptor by competitively inhibiting the binding of RAGE ligands to RAGE. Therefore, this study is aimed at clarifying whether and how pulmonary knockdown of MMP-9 affected sepsis-induced acute lung injury as well as the release of sRAGE in a murine cecal ligation and puncture (CLP) model. The analysis of GEO mouse sepsis datasets GSE15379, GSE52474, and GSE60088 revealed that the mRNA expression of MMP-9 was significantly upregulated in septic mouse lung tissues. Elevation of pulmonary MMP-9 mRNA and protein expressions was confirmed in CLP-induced mouse sepsis model. Intratracheal injection of MMP-9 siRNA resulted in an approximately 60% decrease in pulmonary MMP-9 expression. It was found that pulmonary knockdown of MMP-9 significantly increased mortality of sepsis and exacerbated sepsis-associated acute lung injury. Pulmonary MMP-9 knockdown also decreased sRAGE release and enhanced sepsis-induced activation of the RAGE/nuclear factor-κB (NF-κB) signaling pathway, meanwhile aggravating sepsis-induced oxidative stress and inflammation in lung tissues. In addition, administration of recombinant sRAGE protein suppressed the activation of the RAGE/NF-κB signaling pathway and ameliorated pulmonary oxidative stress, inflammation, and lung injury in CLP-induced septic mice. In conclusion, our data indicate that MMP-9-mediated RAGE shedding limits the severity of sepsis-associated pulmonary edema, inflammation, oxidative stress, and lung injury by suppressing the RAGE/NF-κB signaling pathway via the decoy receptor activities of sRAGE. MMP-9-mediated sRAGE production may serve as a self-limiting mechanism to control and resolve excessive inflammation and oxidative stress in the lung during sepsis.", "claims": [{"id": "claim-method", "statement": "Statistical significance in experiments comparing only two groups was determined by two-tailed Student's t-test. The comparison among multiple groups was estimated by one-way analysis of variance followed by post hoc analysis using Student-Newman-Keuls test. To determine statistical significance between survival curves, the Kaplan–Meier test was used. All raw data will be available upon request to the corresponding author from this manuscript.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33628393", "locator": "sections[13] \"2.11. Statistical Analysis\" paragraph 2", "quote": "Statistical significance in experiments comparing only two groups was determined by two-tailed Student's t-test."}, {"asset": "source:pmid:33628393", "locator": "sections[13] \"2.11. Statistical Analysis\" paragraph 2", "quote": "The comparison among multiple groups was estimated by one-way analysis of variance followed by post hoc analysis using Student-Newman-Keuls test."}, {"asset": "source:pmid:33628393", "locator": "sections[13] \"2.11. Statistical Analysis\" paragraph 2", "quote": "To determine statistical significance between survival curves, the Kaplan–Meier test was used."}, {"asset": "source:pmid:33628393", "locator": "sections[25] \"Data Availability\" paragraph 2", "quote": "All raw data will be available upon request to the corresponding author from this manuscript."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All raw data will be available upon request to the corresponding author from this manuscript.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33628393", "locator": "sections[25] \"Data Availability\" paragraph 2", "quote": "All raw data will be available upon request to the corresponding author from this manuscript."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33628393"], "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:GSE15379"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE15379"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33628393", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/8889313", "sha256": "sha256:b2f731b19fbbc412adf0e0fd5af33522648e78deaa0d77995f7a48ffceb5e837", "bytes": 32492, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/8889313", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7889353", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15379", "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=GSE15379", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15379", "version": null, "note": "All raw data will be available upon request to the corresponding author from this manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All raw data will be available upon request to the corresponding author from this manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM385823", "GSM385824", "GSM385825", "GSM385826", "GSM385827", "GSM385828", "GSM385829", "GSM385830", "GSM385831", "GSM385832", "GSM385833", "GSM385834"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Expression data from lung of septic PPTA knockout mouse", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE52474", "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=GSE52474", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52474", "version": null, "note": "All raw data will be available upon request to the corresponding author from this manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All raw data will be available upon request to the corresponding author from this manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1267502", "GSM1267503", "GSM1267504", "GSM1267505", "GSM1267506", "GSM1267507", "GSM1267508", "GSM1267509", "GSM1267510", "GSM1267511", "GSM1267512", "GSM1267513", "GSM1267514", "GSM1267515", "GSM1267516", "GSM1267517", "GSM1267518", "GSM1267519", "GSM1267520", "GSM1267521", "GSM1267522", "GSM1267523", "GSM1267524", "GSM1267525", "GSM1267526", "GSM1267527", "GSM1267528", "GSM1267529", "GSM1267530", "GSM1267531", "GSM1267532", "GSM1267533", "GSM1267534", "GSM1267535", "GSM1267536", "GSM1267537", "GSM1267538", "GSM1267539", "GSM1267540", "GSM1267541", "GSM1267542", "GSM1267543", "GSM1267544", "GSM1267545", "GSM1267546", "GSM1267547", "GSM1267548", "GSM1267549", "GSM1267550", "GSM1267551", "GSM1267552", "GSM1267553", "GSM1267554", "GSM1267555", "GSM1267556", "GSM1267557", "GSM1267558", "GSM1267559", "GSM1267560", "GSM1267561", "GSM1267562", "GSM1267563", "GSM1267564", "GSM1267565", "GSM1267566", "GSM1267567", "GSM1267568", "GSM1267569", "GSM1267570", "GSM1267571", "GSM1267572", "GSM1267573", "GSM1267574", "GSM1267575", "GSM1267576", "GSM1267577", "GSM1267578", "GSM1267579", "GSM1267580", "GSM1267581", "GSM1267582", "GSM1267583", "GSM1267584", "GSM1267585", "GSM1267586", "GSM1267587", "GSM1267588", "GSM1267589", "GSM1267590", "GSM1267591", "GSM1267592", "GSM1267593", "GSM1267594", "GSM1267595", "GSM1267596", "GSM1267597", "GSM1267598", "GSM1267599", "GSM1267600", "GSM1267601", "GSM1267602", "GSM1267603", "GSM1267604", "GSM1267605", "GSM1267606", "GSM1267607", "GSM1267608", "GSM1267609", "GSM1267610", "GSM1267611", "GSM1267612", "GSM1267613", "GSM1267614", "GSM1267615", "GSM1267616", "GSM1267617", "GSM1267618", "GSM1267619", "GSM1267620", "GSM1267621", "GSM1267622", "GSM1267623", "GSM1267624", "GSM1267625", "GSM1267626", "GSM1267627", "GSM1267628", "GSM1267629", "GSM1267630", "GSM1267631", "GSM1267632", "GSM1267633", "GSM1267634", "GSM1267635", "GSM1267636", "GSM1267637", "GSM1267638", "GSM1267639", "GSM1267640", "GSM1267641", "GSM1267642", "GSM1267643", "GSM1267644", "GSM1267645", "GSM1267646", "GSM1267647", "GSM1267648", "GSM1267649", "GSM1267650", "GSM1267651", "GSM1267652", "GSM1267653", "GSM1267654", "GSM1267655"], "sample_count": 154, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Late Multiple Organ Surge in Interferon-regulated Target Genes Characterizes Staphylococcal Enterotoxin B Lethality", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE60088", "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=GSE60088", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE60088", "version": null, "note": "All raw data will be available upon request to the corresponding author from this manuscript.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All raw data will be available upon request to the corresponding author from this manuscript.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1464822", "GSM1464823", "GSM1464824", "GSM1464825", "GSM1464826", "GSM1464827", "GSM1464828", "GSM1464829", "GSM1464830", "GSM1464831", "GSM1464832", "GSM1464833", "GSM1464834", "GSM1464835", "GSM1464836", "GSM1464837", "GSM1464838", "GSM1464839", "GSM1464840", "GSM1464841", "GSM1464842", "GSM1464843", "GSM1464844", "GSM1464845", "GSM1464846", "GSM1464847", "GSM1464848"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Transcriptional Profiling  in Sepsis-induced Experimental Multiple Organ Dysfunction Syndrome", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE15379 not downloaded", "asset:data:geo:GSE15379 licence not read", "asset:data:geo:GSE52474 not downloaded", "asset:data:geo:GSE52474 licence not read", "asset:data:geo:GSE60088 not downloaded", "asset:data:geo:GSE60088 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "reordered", "quote": "Statistical significance in experiments comparing only two groups was determined by two-tailed Student's t-test. The comparison among multiple groups was estimated by one-way analysis of variance followed by post hoc analysis using Student-Newman-Keuls test. To determine statistical significance between survival curves, the Kaplan–Meier test was used. All raw data will be available upon request to the corresponding author from this manuscript."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "analysis of variance"}}, {"id": "method-3", "family": "image_quantification", "specific": "densitometry", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "densitometr"}}], "targets": [], "gaps": ["method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE15379", "GSE52474", "GSE60088"], "resolved_accessions": ["GSE15379", "GSE52474", "GSE60088"], "statements": ["All raw data will be available upon request to the corresponding author from this manuscript."], "basis": "The paper names GSE15379, GSE52474, GSE60088 in Gene Expression Omnibus (GEO) databases and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33628393", "data:geo:GSE15379"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15379"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:18Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 25077, "completion_tokens": 1610, "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:33628393", "type": "paper", "label": "pmid:33628393"}, {"id": "source:pmid:33628393", "type": "manuscript", "label": "PMID 33628393 full text"}, {"id": "data:geo:GSE15379", "type": "dataset", "label": "GEO GSE15379"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33628393", "type": "paper", "label": "pmid:33628393"}, {"id": "source:pmid:33628393", "type": "manuscript", "label": "PMID 33628393 full text"}, {"id": "data:geo:GSE15379", "type": "dataset", "label": "GEO GSE15379"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33628393", "type": "extraction", "used": ["source:pmid:33628393"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15379", "type": "accession_resolution", "used": ["data:geo:GSE15379"], "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:33628393", "parent_hash": "sha256:d8d2535ded0d3df7985e82c01e448e6b2953a0a8889050a32fa0ae4ab9c95e73", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE15379 licence not read", "asset:data:geo:GSE15379 not downloaded", "asset:data:geo:GSE52474 licence not read", "asset:data:geo:GSE52474 not downloaded", "asset:data:geo:GSE60088 licence not read", "asset:data:geo:GSE60088 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["imed at clarifying whether and how pulmonary knockdown of MMP-9 affected sepsis-induced acute lung", "MP-9 expression. It was found that pulmonary knockdown of MMP-9 significantly increased mortality o", "ssociated acute lung injury. Pulmonary MMP-9 knockdown also decreased sRAGE release and enhanced se", "psis model. Intratracheal injection of MMP-9 siRNA resulted in an approximately 60% decrease in"], "order_basis": "paper_text_order:728", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["injury as well as the release of sRAGE in a murine cecal ligation and puncture (CLP) model. The", "nd puncture (CLP) model. The analysis of GEO mouse sepsis datasets GSE15379, GSE52474, and GSE6", "MP-9 was significantly upregulated in septic mouse lung tissues. Elevation of pulmonary MMP-9 m", "ein expressions was confirmed in CLP-induced mouse sepsis model. Intratracheal injection of MMP"], "order_basis": "paper_text_order:827", "id": "assay:2"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["rials Table S1: primer sequences used in the real-time quantitative PCR. Table S2: small interfering RNA sequences u"], "order_basis": "paper_text_order:3393", "id": "assay:3"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["expression level of MMP-9 was determined by western blot analysis. Relative densitometry of the MMP-9"], "order_basis": "paper_text_order:3801", "id": "assay:4"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Statistical significance in experiments comparing only two groups was determined by two-tailed Student's t-test. The comparison among multiple groups was estimated by one-way analysis of variance followed by post hoc analysis using Student-Newman-Keuls test. To determine statistical significance between survival curves, the Kaplan–Meier test was used. All raw data will be available upon request to the corresponding author from this manuscript."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T02:26:58+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}}}