{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25520777", "kind": "science-record", "revision": 3, "content_hash": "sha256:b9e2359d6ad3b5adacf61a466625c30f790d3913a5b79945973b11720088e4cd", "created_at": "2026-11-01T15:40:07Z", "updated_at": "2026-11-01T18:47:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Follow up: Compound data sets and software tools for chemoinformatics and medicinal chemistry applications: update and data transfer.", "doi": "10.12688/f1000research.3713.1", "pmid": "25520777", "authors": ["Ye Hu", "Jürgen Bajorath"], "journal": "F1000Research", "year": 2014, "abstract": "In 2012, we reported 30 compound data sets and/or programs developed in our laboratory in a data article and made them freely available to the scientific community to support chemoinformatics and computational medicinal chemistry applications. These data sets and computational tools were provided for download from our website. Since publication of this data article, we have generated 13 new data sets with which we further extend our collection of publicly available data and tools. Due to changes in web servers and website architectures, data accessibility has recently been limited at times. Therefore, we have also transferred our data sets and tools to a public repository to ensure full and stable accessibility. To aid in data selection, we have classified the data sets according to scientific subject areas. Herein, we describe new data sets, introduce the data organization scheme, summarize the database content and provide detailed access information in ZENODO (doi: 10.5281/zenodo.8451 and doi:10.5281/zenodo.8455).", "claims": [{"id": "claim-data-access", "statement": "ZENODO: Programs for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8451 48.\nZENODO: Data sets for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8455 49.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25520777", "locator": "sections[18] \"Data availability\" paragraphs 1-3", "quote": "ZENODO: Programs for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8451 48.\nZENODO: Data sets for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8455 49."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports no statistical method; it is a data-resource paper. Its headline result is the introduction of 13 new compound data sets, with access provided through ZENODO and the underlying data predominantly sourced from ChEMBL, BindingDB, and PubChem.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:25520777", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Since publication of this data article, we have generated 13 new data sets with which we further extend our collection of publicly available data and tools."}, {"asset": "source:pmid:25520777", "locator": "sections[1] \"Introduction\" paragraph 2", "quote": "Our data sets and tools are provided via the ZENODO platform ( https://zenodo.org/) to ensure easy and stable access."}, {"asset": "source:pmid:25520777", "locator": "sections[2] \"Materials and methods\" paragraph 2", "quote": "The data sets reported herein were predominantly generated from ChEMBL 2, 3, BindingDB 4 and PubChem 5"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The paper reports no statistical method; it is a data-resource paper. Its headline result is the introduction of 13 new compound data sets, with access provided through ZENODO and the underlying data predominantly sourced from ChEMBL, BindingDB, and PubChem.", "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:25520777"], "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:25520777", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12688/f1000research.3713.1", "sha256": "sha256:624596650ec8b3acde801f1c48e4280c11bc3fa9534222c410697c46ebecb196", "bytes": 19579, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12688/f1000research.3713.1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4264635", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:25520777:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8efea040c8ef41165356ddb9030fc82ee538aa0c3b7d14a658aa2dd5eddf7491", "bytes": 4078, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Data sets and programs.", "structure": {"pmcid": "PMC4264635", "section_index": 3, "section_title": "Data description", "row_count": 44, "column_count": 4}, "table": {"label": "Table 1.", "caption": "Data sets and programs.", "rows": [["Entry", "Year", "Subject area index label", "Description"], ["1 [9]", "2007", "VS_ML_1", "9 activity classes (AC) with increasing structural diversity"], ["2 [9]", "2007", "VS_ML_2", "~1.44 million ZINC compounds used for various virtual screening trials"], ["3 [10]", "2007", "PROG_1", "Molecular similarity histogram filtering"], ["4 [11]", "2007", "SSR_1", "4 SD files with 26 selectivity sets; compounds are annotated with selectivity values for different targets"], ["5 [12]", "2008", "SSR_2", "7 compound selectivity sets containing 267 biogenic amine GPCR antagonists"], ["6 [13]", "2008", "SSR_3", "18 selectivity sets for targets from 4 families"], ["7 [14]", "2008", "VS_ML_3", "25 sets of compounds of increasing complexity and size"], ["8 [15]", "2009", "VS_ML_4", "242 hERG inhibitors"], ["9 [16]", "2009", "SSR_4", "243 ionotropic glutamate ion channel antagonists"], ["10 [17]", "2009", "PROG_2", "Combinatorial analog graph (CAG) program with a sample set consisting of 51 thrombin inhibitors"], ["11 [18]", "2009", "VS_ML_5", "20 AC from the literature and 15 AC from the Molecular Drug Data Report"], ["12 [19]", "2010", "VS_ML_6", "8 AC"], ["13 [20]", "2010", "PROG_3", "Program to generate target selectivity patterns of scaffolds"], ["14 [21]", "2010", "PROG_4", "Multi-target CAGs (see also entry 10) with a sample set containing 33 kinase inhibitors"], ["15 [22]", "2010", "PROG_5", "SARANEA"], ["16 [23]", "2010", "PROG_6", "3D activity landscape program with a sample set containing 248 cathepsin S inhibitors"], ["17 [24]", "2010", "SAR_1", "2 sets of MMPs from BindingDB and ChEMBL"], ["18 [25]", "2010", "PROG_7", "Similarity-potency tree (SPT) program with a sample set containing 874 factor Xa inhibitors"], ["19 [26]", "2010", "VS_ML_7", "17 target-directed compound sets; each set contains a minimum of 10 distinct scaffolds and each scaffold represents 5 compounds"], ["20 [27]", "2011", "SAR_VZ", "10,489 malaria screening hits"], ["21 [28]", "2011", "SAR_2", "458 target-based sets with scaffolds and scaffold hierarchies"], ["22 [29]", "2011", "SAR_VZ", "4 sets of compounds active against 3 or 4 targets"], ["23 [30]", "2011", "SAR_VZ", "881 factor Xa inhibitors"], ["24 [31]", "2011", "VS_ML_8", "50 AC prioritized for similarity searching"], ["25 [32]", "2011", "VS_ML_9", "25 data sets from successful ligand-based virtual screening applications"], ["26 [33]", "2011", "SAR_3", "26 conserved scaffolds in activity profile sequences of length 4"], ["27 [34]", "2011", "PROG_8", "Scaffold distance function"], ["28 [35]", "2011", "SAR_4", "2 sets of compounds with multiple K i or IC 50 measurements against the same targets that differed within 1 order of magnitude"], ["29 [36]", "2012", "SAR_VZ", "4 AC"], ["30 [37]", "2012", "SAR_5", "5 sets of different types of activity cliffs"], ["31 [38]", "2012", "VS_ML_10", "50 AC for scaffold hopping analysis"], ["32 [39]", "2012", "SAR_6", "61 AC consisting of SAR transfer series with regular potency progression"], ["33 [40]", "2013", "SAR_7", "4 activity measurement type-dependent sets of scaffolds"], ["34 [41]", "2013", "VS_ML_11", "2 multi-target compound sets"], ["35 [42]", "2013", "VS_ML_12", "4 multi-target compound sets and 3 multi-mechanism sets"], ["36 [43]", "2013", "SAR_8", "2337 compound series matrices"], ["37 [44]", "2013", "SAR_9", "128 AC containing ≥100 compounds with K i values"], ["38 [45]", "2014", "SAR_10", "30,452 and 45,607 target-based MMS with K i and IC 50 values, respectively"], ["39 [46]", "2014", "SAR_11", "221 drug-unique scaffolds"], ["40 [47]", "2014", "SAR_12", "92,734 MMPs based upon retrosynthetic rules for 435 AC"], ["41 [8]", "2014", "SAR_13", "20,073 and 25,297 MMP-based activity cliffs with K i and IC 50 values, respectively"], ["42 [8]", "2014", "SAR_14", "4 activity measurement type-dependent sets of SAR transfer series with approximate or regular potency progression"], ["43 [8]", "2014", "SAR_15", "169,889 and 240,322 transformation size-restricted MMPs based upon retrosynthetic rules with K i and IC 50 values, respectively"]], "row_count": 44, "column_count": 4, "numeric_cells": 164, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}], "gaps": []}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["ZENODO: Programs for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8451 48.\nZENODO: Data sets for chemoinformatics and computational medicinal chemistry, doi: 10.5281/zenodo.8455 49."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:25520777", "asset:table:pmid:25520777:1"], "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": "2026-10-31T18:23:21Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 45189, "completion_tokens": 3847, "cached_tokens": 1560}}, "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:25520777", "type": "paper", "label": "pmid:25520777"}, {"id": "source:pmid:25520777", "type": "manuscript", "label": "PMID 25520777 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25520777", "type": "paper", "label": "pmid:25520777"}, {"id": "source:pmid:25520777", "type": "manuscript", "label": "PMID 25520777 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25520777", "type": "extraction", "used": ["source:pmid:25520777"], "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:25520777", "parent_hash": "sha256:b62e419ed7e27f8b1612a6f0f63f87d08f49037a462ade74c812bbb443e759b2", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]},"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":"2026-11-04T02:51:20+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}}}