{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33578541", "kind": "science-record", "revision": 8, "content_hash": "sha256:5ed254a5034d6e962d252512413e58e2ad0de89515aaae917f68ecc3671e21d8", "created_at": "2026-11-01T15:41:25Z", "updated_at": "2026-11-01T22:46:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key biomarkers and functional pathways in osteosarcomas with lung metastasis: Evidence from bioinformatics analysis.", "doi": "10.1097/MD.0000000000024471", "pmid": "33578541", "authors": ["Denghua Liu", "Rui Zhou", "Aiguo Zhou"], "journal": "Medicine", "year": 2021, "abstract": "BACKGROUND: In osteosarcoma, the lung is the most common metastatic organ. Intensive work has been made to illuminate the pathogeny, but the specific metastatic mechanism remains unclear. Thus, we conducted the study to seek to find the key genes and critical functional pathways associated with progression and treatment in lung metastasis originating from osteosarcoma.\nMETHODS: Two independent datasets (GSE14359 and GSE85537) were screened out from the Gene Expression Omnibus (GEO) database and the overlapping differentially expressed genes (DEGs) were identified using GEO2R online platform. Subsequently, the Gene Ontology (GO) annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways enrichment analysis of DEGs were conducted using DAVID. Meanwhile, the protein-protein interaction (PPI) network constructed by STRING was visualized using Cytoscape. Afterwards, the key module and hub genes were extracted from the PPI network using the MCODE and cytoHubba plugin. Moreover, the raw data obtained from GSE73166 and GSE21257 were applied to verify the expression differences and conduct the survival analyses of hub genes, respectively. Finally, the interaction network of miRNAs and hub genes constructed by ENCORI was visualized using Cytoscape.\nRESULTS: A total of 364 DEGs were identified, comprising 96 downregulated genes and 268 upregulated genes, which were mainly involved in cancer-associated pathways, adherens junction, ECM-receptor interaction, focal adhesion, MAPK signaling pathway. Subsequently, 10 hub genes were obtained and survival analysis demonstrated SKP2 and ASPM were closely related to poor prognosis of patients with osteosarcoma. Finally, hsa-miR-340-5p, has-miR-495-3p, and hsa-miR-96-5p were found to be most closely associated with these hub genes according to the interaction network of miRNAs and hub genes.\nCONCLUSION: The key genes and functional pathways identified in the study may contribute to understanding the molecular mechanisms involved in the carcinogenesis and progression of lung metastasis originating from osteosarcoma, and provide potential diagnostic and therapeutic targets.", "claims": [{"id": "claim-method", "statement": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), a web-based application, contributes to filtrating DEGs through the Bioconductor's GEO Query and limma R software.[11] Therefore, in the present study, the DEGs between the lung metastasis group and the non-metastasis group were screened out by the GEO2R online platform with cut-off criteria of P < .05 and |log fold-change| (|logFC|) >1. The raw data of 2 gene expression microarray datasets (GSE14359, GSE85537) were obtained from the GEO database and then subjected to differential expression analysis by the GEO2R online platform.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33578541", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), a web-based application, contributes to filtrating DEGs through the Bioconductor's GEO Query and limma R software.[11] Therefore, in the present study, the DEGs between the lung metastasis group and the non-metastasis group were screened out by the GEO2R online platform with cut-off criteria of P < .05 and |log fold-change| (|logFC|) >1."}, {"asset": "source:pmid:33578541", "locator": "sections[10] \"Identification of DEGs\" paragraph 2", "quote": "The raw data of 2 gene expression microarray datasets (GSE14359, GSE85537) were obtained from the GEO database and then subjected to differential expression analysis by the GEO2R online platform."}], "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:33578541"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33578541", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000024471", "sha256": "sha256:13dabb7ea3c8df40776f989054467465f2a3c4f2c7896e82e161711303a681fd", "bytes": 28241, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000024471", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7886415", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33578541:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ba1afb77726971e6e5df0ec527093bd31b2ed313094775229386ac6f1895ee27", "bytes": 2417, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "The detailed information of hub genes.", "structure": {"pmcid": "PMC7886415", "section_index": 13, "section_title": "Hub gene selection and analysis", "row_count": 11, "column_count": 3}, "table": {"label": "Table 1", "caption": "The detailed information of hub genes.", "rows": [["Gene symbol", "Full name", "Function"], ["SKP2", "S-Phase kinase associated protein 2", "SKP2 encodes a substrate recognition component of a SCF (SKP1-CUL1-F-box protein) E3 ubiquitin-protein ligase complex, which mediates the ubiquitination and subsequent proteasomal degradation of target proteins involved in cell cycle progression, signal transduction, and transcription."], ["ASPM", "Abnormal spindle microtubule assembly", "ASPM encodes a centrosomal protein that plays an essential part in maintaining the normal function of the mitotic spindle and regulating neurogenesis."], ["TOP2A", "Topoisomerase (DNA) II alpha", "TOP2A encodes a DNA topoisomerase that is essential in the regulation of DNA structure and transcription, and it is the direct molecular target of anthacyclines."], ["SMC2", "Structural maintenance of chromosomes 2", "SMC2 encodes the central component of the condensin complex, which is required for conversion of interphase chromatin into mitotic-like condense chromosomes."], ["CDC25C", "Cell division cycle 25C", "CDC25C encoded a tyrosine protein phosphatase that participated in regulating G2/M progression and mediating DNA damage repair"], ["SOCS3", "Suppressor of cytokine signaling 3", "SOCS family proteins form part of a classical negative feedback system that mainly regulates cytokine signal transduction."], ["DTL", "Denticleless E3 ubiquitin protein ligase homolog", "DTL encodes a substrate-specific adapter of a DCX (DDB1-CUL4-X-box) E3 ubiquitin-protein ligase complex required for cell cycle control, DNA damage response, and translesion DNA synthesis"], ["ECT2", "Epithelial cell transforming 2", "ECT2 is a guanine nucleotide exchange factor (GEF) of the Rho family members of small GTPases and essential for signal transduction pathways involved in the regulation of cytokinesis."], ["CENPN", "Centromere protein N", "CENPN is the vital component of the CENPA-NAC (nucleosome-associated) complex, which plays a central role in assembly of kinetochore proteins, mitotic progression and chromosome segregation"], ["PARPBP", "PARP1 binding protein", "PARPBP contributes to suppressing inappropriate homologous recombination, thereby playing a central role in DNA repair and the maintenance of genomic stability."]], "row_count": 11, "column_count": 3, "numeric_cells": 7, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T1"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "reordered", "quote": "GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), a web-based application, contributes to filtrating DEGs through the Bioconductor's GEO Query and limma R software.[11] Therefore, in the present study, the DEGs between the lung metastasis group and the non-metastasis group were screened out by the GEO2R online platform with cut-off criteria of P < .05 and |log fold-change| (|logFC|) >1. The raw data of 2 gene expression microarray datasets (GSE14359, GSE85537) were obtained from the GEO database and then subjected to differential expression analysis by the GEO2R online platform."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33578541", "asset:table:pmid:33578541:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:24:43Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 20009, "completion_tokens": 1868, "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:33578541", "type": "paper", "label": "pmid:33578541"}, {"id": "source:pmid:33578541", "type": "manuscript", "label": "PMID 33578541 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33578541", "type": "paper", "label": "pmid:33578541"}, {"id": "source:pmid:33578541", "type": "manuscript", "label": "PMID 33578541 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33578541", "type": "extraction", "used": ["source:pmid:33578541"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33578541", "parent_hash": "sha256:2fdd7f9e8bc8e9d42f220b6d8038b51d6132d29eb9fa23d6c3698979ad27667a", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r), a web-based application, contributes to filtrating DEGs through the Bioconductor's GEO Query and limma R software.[11] Therefore, in the present study, the DEGs between the lung metastasis group and the non-metastasis group were screened out by the GEO2R online platform with cut-off criteria of P < .05 and |log fold-change| (|logFC|) >1. The raw data of 2 gene expression microarray datasets (GSE14359, GSE85537) were obtained from the GEO database and then subjected to differential expression analysis by the GEO2R online platform."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:17:20+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}}}