{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38214344", "kind": "science-record", "revision": 4, "content_hash": "sha256:42cff2c06e49338b28bc202eca4b387d62b3b4dcd9dc0e2b5d63d94efa2072c9", "created_at": "2026-11-01T19:20:07Z", "updated_at": "2026-11-01T22:53:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Regulator of G protein signalling 18 promotes osteocyte proliferation by activating the extracellular signal‑regulated kinase signalling pathway.", "doi": "10.3892/ijmm.2024.5346", "pmid": "38214344", "authors": ["Yong Meng", "Si-Qiang Qiu", "Qiang Wang", "Jin-Liang Zuo"], "journal": "International journal of molecular medicine", "year": 2024, "abstract": "Osteocyte function is critical for metabolism, remodelling and regeneration of bone tissue. In the present study, the roles of regulator of G protein signalling 18 (RGS18) were assessed in the regulation of osteocyte proliferation and bone formation. Target genes and signalling pathways were screened using the Gene Expression Omnibus (GEO) database and Gene Set Enrichment Analysis (GSEA). The function of RGS18 and the associated mechanisms were analysed by Cell Counting Kit 8 assay, 5‑ethynyl‑2'‑deoxyuridine assay, flow cytometry, reverse transcription‑quantitative PCR, western blotting and immunostaining. Overlap analysis of acutely injured subjects (AIS) and healthy volunteers (HVs) from the GSE93138 and GSE93215 datasets of the GEO database identified four genes: KIAA0825, ANXA3, RGS18 and LIPN. Notably, RGS18 was more highly expressed in peripheral blood samples from AIS than in those from HVs. Furthermore, RGS18 overexpression promoted MLO‑Y4 and MC3T3‑E1 cell viability, proliferation and S‑phase arrest, but inhibited apoptosis by suppressing caspase‑3/9 cleavage. Silencing RGS18 exerted the opposite effects. GSEA of GSE93138 revealed that RGS18 has the ability to regulate MAPK signalling. Treatment with the MEK1/2 inhibitor PD98059 reversed the RGS18 overexpression‑induced osteocyte proliferation, and treatment with the ERK1/2 activator 12‑O‑tetradecanoylphorbol‑13‑acetate reversed the effects of RGS18 silencing on osteocyte proliferation. In conclusion, RGS18 may contribute to osteocyte proliferation and bone fracture healing via activation of ERK signalling.", "claims": [{"id": "claim-method", "statement": "Statistical differences between two groups were measured using unpaired Student's t-test, and differences among three or more groups were analysed using one-way or two-way ANOVA followed by the Bonferroni post hoc test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38214344", "locator": "sections[13] \"Statistical analysis\" paragraph 2", "quote": "Statistical differences between two groups were measured using unpaired Student's t-test, and differences among three or more groups were analysed using one-way or two-way ANOVA followed by the Bonferroni post hoc test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38214344", "locator": "sections[24] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "RGS18 may contribute to osteocyte proliferation and bone fracture healing by activating ERK signalling.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38214344", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In conclusion, RGS18 may contribute to osteocyte proliferation and bone fracture healing via activation of ERK signalling."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "RGS18 may contribute to osteocyte proliferation and bone fracture healing by activating ERK signalling.", "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:38214344"], "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:GSE93138"], "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:GSE93138"], "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:38214344", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2024.5346", "sha256": "sha256:5b129c407b246fe918774b320119fe26ec88d2bda4f12e7d030951f876b1cb43", "bytes": 24880, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2024.5346", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10836495", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE93138", "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=GSE93138", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93138", "version": null, "note": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2445319", "GSM2445320", "GSM2445321", "GSM2445322", "GSM2445323", "GSM2445324", "GSM2445325", "GSM2445326", "GSM2445327", "GSM2445328", "GSM2445329", "GSM2445330"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "809094 Biomarker Identification in Fracture Healing (experiment #3244 performed 2010 Feb)", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE93215", "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=GSE93215", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93215", "version": null, "note": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2448684", "GSM2448685", "GSM2448686", "GSM2448687", "GSM2448688", "GSM2448689", "GSM2448690", "GSM2448691", "GSM2448692", "GSM2448693", "GSM2448694", "GSM2448695", "GSM2448696", "GSM2448697", "GSM2448698", "GSM2448699", "GSM2448700", "GSM2448701", "GSM2448702", "GSM2448703", "GSM2448704", "GSM2448705", "GSM2448706", "GSM2448707", "GSM2448708", "GSM2448709", "GSM2448710", "GSM2448711"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "809094 Biomarker Identification in Fracture Healing (experiment #3341 performed 2010 Jun) [mRNA]", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE93138 not downloaded", "asset:data:geo:GSE93138 licence not read", "asset:data:geo:GSE93215 not downloaded", "asset:data:geo:GSE93215 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": "verbatim", "quote": "Statistical differences between two groups were measured using unpaired Student's t-test, and differences among three or more groups were analysed using one-way or two-way ANOVA followed by the Bonferroni post hoc test."}}, {"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": "ANOVA"}}], "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": ["GSE93138", "GSE93215"], "resolved_accessions": ["GSE93138", "GSE93215"], "statements": ["The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. For bioinformatics analysis, the datasets generated and/or analysed during the current study are available in the GEO database (GSE93138: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93138 and GSE93215: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93215)."], "basis": "The paper names GSE93138, GSE93215 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:38214344", "data:geo:GSE93138"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE93138"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:04:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8078, "completion_tokens": 1486, "cached_tokens": 256}}, "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:38214344", "type": "paper", "label": "pmid:38214344"}, {"id": "source:pmid:38214344", "type": "manuscript", "label": "PMID 38214344 full text"}, {"id": "data:geo:GSE93138", "type": "dataset", "label": "GEO GSE93138"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38214344", "type": "paper", "label": "pmid:38214344"}, {"id": "source:pmid:38214344", "type": "manuscript", "label": "PMID 38214344 full text"}, {"id": "data:geo:GSE93138", "type": "dataset", "label": "GEO GSE93138"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38214344", "type": "extraction", "used": ["source:pmid:38214344"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE93138", "type": "accession_resolution", "used": ["data:geo:GSE93138"], "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:38214344", "parent_hash": "sha256:31642a7412d70bdd7fa863c68631058cf9751db764c46c52d2a7a4c9bfbbcbe7", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE93138 licence not read", "asset:data:geo:GSE93138 not downloaded", "asset:data:geo:GSE93215 licence not read", "asset:data:geo:GSE93215 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": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["it 8 assay, 5‑ethynyl‑2'‑deoxyuridine assay, flow cytometry, reverse transcription‑quantitative PCR, wes"], "order_basis": "paper_text_order:622", "id": "assay:1"}, {"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": ["try, reverse transcription‑quantitative PCR, western blotting and immunostaining. Overlap analysis of acut"], "order_basis": "paper_text_order:678", "id": "assay:2"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["ption‑quantitative PCR, western blotting and immunostaining. Overlap analysis of acutely injured subject"], "order_basis": "paper_text_order:699", "id": "assay:3"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["GS18 was more highly expressed in peripheral blood samples from AIS than in those from HVs. Furthermore, RGS"], "order_basis": "paper_text_order:966", "id": "assay:4"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["liferation and S‑phase arrest, but inhibited apoptosis by suppressing caspase‑3/9 cleavage. Silenci", "rest, but inhibited apoptosis by suppressing caspase‑3/9 cleavage. Silencing RGS18 exerted the op"], "order_basis": "paper_text_order:1140", "id": "assay:5"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Materials and methods Cell culture Mouse osteocyte MLO-Y4 cells (Procell Life Science", "s Co., Ltd.) and 1% penicillin-streptomycin. Mouse osteoblast MC3T3-E1 cells (Nanjing Cobioer B"], "order_basis": "paper_text_order:1739", "id": "assay:6"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ll Life Science & Technology Co., Ltd.) were cultured in α-minimal essential medium (α-MEM; Procell L", "(Nanjing Cobioer Biosciences Co., Ltd.) were cultured in α-MEM containing 20% FBS, 2 mM L-glutamine,"], "order_basis": "paper_text_order:1809", "id": "assay:7"}, {"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 differences between two groups were measured using unpaired Student's t-test, and differences among three or more groups were analysed using one-way or two-way ANOVA followed by the Bonferroni post hoc test."], "order_basis": "consumes_earlier_output", "id": "assay:8"}]},"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":"2026-11-04T00:40:02+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}}}