{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37928388", "kind": "science-record", "revision": 2, "content_hash": "sha256:47566b7fb6e497c18600300add55add08cdc6c576dfbcdd511c144de99d5041a", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:32Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Hierarchical clustering identifies oxidative stress-related subgroups for the prediction of prognosis and immune microenvironment in gastric cancer", "doi": "10.1016/j.heliyon.2023.e20804", "pmid": "37928388", "authors": null, "journal": "Heliyon", "year": 2023, "abstract": null, "claims": [{"id": "claim-1", "statement": "the overall survival difference between the two oxidative-stress-related gastric cancer subgroups", "kind": "quantitative", "state": "complete", "target": {"value": 0.01, "unit": "p-value", "tolerance": null, "source": "chars 12212-12368 of source sha256 a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb"}, "evidence": [{"asset": "source:pmid:37928388", "locator": "chars 12212-12368 of source sha256 a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "quote": "Furthermore, when compared to GC patients from the C1 subgroup, GC patients in the C2 subgroup exhibited a better overall survival rate (Fig. 2E, p = 0.01)."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the overall survival difference between the two oxidative-stress-related gastric cancer subgroups", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:37928388"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "method:diagnostic_evaluation_roc", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the source data behind pmid:37928388, at the location the paper names"], "outputs": ["the registered result"], "instruments": [], "reagents": []}, {"id": "provide_capability_bench_workcell", "order": 4, "name": "Provide General bench workcell (liquid transfer, plate handling, incubation)", "kind": "computational", "state": "blocked", "blocked_on": "instrument not yet purchased", "description": "Make this capability available to the experiment: amplicon_seq, animal_model, apoptosis_assay, cell_culture, cell_imaging, chip_seq, clinical_cohort, clinical_trial, elisa, flow_cytometry, ihc, image_quantification, mass_spectrometry, methylation_array, microarray, qpcr, rna_seq, transfection, western_blot", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": [], "instruments": [], "reagents": []}], "materials": ["the source data behind pmid:37928388, at the location the paper names", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:diagnostic_evaluation_roc"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37928388", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2023.e20804", "sha256": "sha256:a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2023.e20804", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind pmid:37928388, at the location the paper names", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": "TCGA", "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind pmid:37928388, at the location the paper names", "structure": {"material_kind": "dataset", "access_state": "named_not_verified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "data:availability", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "open", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": "TCGA", "version": null, "note": "The data come from TCGA database (https://portal.gdc.cancer.gov/) and the GEO database (https://www.ncbi.nlm.nih.gov/geo/); further requires can be directed to the corresponding author.", "structure": {"access_route": "repository_accession", "location": "section [data-availability]: Availability of data and material"}}, {"id": "asset:table:pmid:37928388:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1daa552616466e618c43e099cbfb27b1ccd61ddcc2dda4c8124b7647d5d8f611", "bytes": 702, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tbl1", "version": null, "note": "Univariate and multivariate Cox analyses assessed the independent prognostic value of ORGs risk score in GC patients.", "structure": {"pmcid": "PMC10622623", "section_index": 15, "section_title": "Establishment and verification of a prognostic model", "row_count": 7, "column_count": 6}, "table": {"label": "Table 1", "caption": "Univariate and multivariate Cox analyses assessed the independent prognostic value of ORGs risk score in GC patients.", "rows": [["Characteristics", "Total(N)", "Univariate analysis", "Multivariate analysis"], ["Hazard ratio (95 % CI)", "P value", "Hazard ratio (95 % CI)", "P value"], ["Age", "374", "1.028 (1.011–1.046)", "0.001", "1.031 (1.014–1.049)", "<0.001"], ["Sex", "374", "", "", "", ""], ["MALE", "241", "Reference", "", "", ""], ["FEMALE", "133", "0.792 (0.557–1.128)", "0.196", "", ""], ["risk score", "374", "8.692 (3.226–23.415)", "<0.001", "10.338 (3.815–28.014)", "<0.001"]], "row_count": 7, "column_count": 6, "numeric_cells": 17, "header_rows": 2, "locator": "section[15]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:37928388, at the location the paper names not verified", "asset:source:pmid:37928388 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "kaplan-meier", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Initially, we conducted an assessment of 41 ORGs linked to the predictive significance of patients with GC from the TCGA database. To accomplish this, we employed the univariate Cox regression analysis technique. Subsequently, utilizing the R software's ConcensusClusterPlus tool, we executed consensus clustering by considering the gene expression profiles of the aforementioned 41 ORGs [31]. Afterwards, the optimal number of clusters was assessed, and this procedure was iterated 1000 times to guarantee the credibility of findings. Following that, a cluster map was created utilizing the pheatmap tool in R. To compare the overall survival rates between the two subgroups, we conducted Kaplan-Meier analysis employing the survminer and survival packages in R software."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 0.01, "unit": "p-value", "tolerance": null, "state": "complete"}], "gaps": []}, "capability": {"state": "partial", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}, {"capability_id": "capability:bench_workcell", "label": "General bench workcell (liquid transfer, plate handling, incubation)", "assay_families": ["amplicon_seq", "animal_model", "apoptosis_assay", "cell_culture", "cell_imaging", "chip_seq", "clinical_cohort", "clinical_trial", "elisa", "flow_cytometry", "ihc", "image_quantification", "mass_spectrometry", "methylation_array", "microarray", "qpcr", "rna_seq", "transfection", "western_blot"], "availability_state": "purchasable", "tier_unlocked": "R3", "candidate": "Supplier-neutral 96/384-well liquid handler"}], "gaps": ["capability:capability:bench_workcell purchasable"]}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"axis": "method", "tier": "R1", "blocker": null, "detail": {"outcome": "determined", "family": "clustering", "specific_method": "hierarchical", "required_operations": ["hierarchical_cluster"], "basis": "Every DSL operation this method needs already exists."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "data": {"axis": "data", "tier": "R1", "blocker": null, "detail": {"applies": true, "reachable": true, "accessions": [{"kind": "geo_series", "text": "GSE84437"}, {"kind": "tcga", "text": "TCGA"}], "statements": [], "basis": "The record names where the data can be obtained."}}}, "can_run": {"dsl_operations": ["hierarchical_cluster"], "assets": ["source:pmid:37928388", "asset:table:pmid:37928388:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": ["capability:bench_workcell"], "data_gaps": ["source:pmid:37928388", "materials:the source data behind pmid:37928388, at the location the paper names", "materials:the analysis programme that recomputes the published estimate", "data:availability"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "35a558221f67c3bbd7a6c86da4bd7c33fd18586d11b8c1b5c6fa3dae55d44f1c", "source_hash": "a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "raw_response_sha256": "sha256:45d8e769d47eab4422dd3e6e714b53edab507303752c8dd72123812c75a1a13a", "raw_response_chars": 2141}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "3f6f60d98eb1b3d1f39395314d66cb3bba28540798e985aace0956fd979b118f", "source_hash": "a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "raw_response_sha256": "sha256:217d88b5f32a0438691b80d88d406202c18a8bcf2dd37ab0869148df07ae862f", "raw_response_chars": 2038}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "01e813ab8893b2b37fea56cb3bfc93b98a0e8941ed51bb15b9837c92cbe45d3c", "source_hash": "a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "raw_response": "{\"parent_value\":0.01,\"unit\":\"\",\"evidence\":\"Furthermore, when compared to GC patients from the C1 subgroup, GC patients in the C2 subgroup exhibited a better overall survival rate (Fig. 2E, p = 0.01).\",\"target_result\":\"p = 0.01\",\"number_stated\":true}", "reading": {"parent_value": 0.01, "unit": "", "evidence": "Furthermore, when compared to GC patients from the C1 subgroup, GC patients in the C2 subgroup exhibited a better overall survival rate (Fig. 2E, p = 0.01).", "target_result": "p = 0.01", "number_stated": true, "source_locator": "chars 12212-12368 of source sha256 a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb"}, "recorded_at": "2026-10-31T14:39:08.520167+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "5eb6fb0388a33794d54cc8464eaa1a8f755cf93e8f61069e9c03ecd3a3578234", "source_hash": "a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb", "raw_response": "{\"parent_value\":0.01,\"unit\":\"p-value\",\"evidence\":\"Furthermore, when compared to GC patients from the C1 subgroup, GC patients in the C2 subgroup exhibited a better overall survival rate (Fig. 2E, p = 0.01).\",\"target_result\":\"p = 0.01\",\"number_stated\":true}", "reading": {"parent_value": 0.01, "unit": "p-value", "evidence": "Furthermore, when compared to GC patients from the C1 subgroup, GC patients in the C2 subgroup exhibited a better overall survival rate (Fig. 2E, p = 0.01).", "target_result": "p = 0.01", "number_stated": true, "source_locator": "chars 12212-12368 of source sha256 a8dd6088f1e5b1369a4868d964e3238312c3d9eb9a826deabf4aa15ac08a1deb"}, "recorded_at": "2026-10-31T14:39:32.305781+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "The C1 oxidative stress-related gastric cancer subgroup had a worse overall survival rate than the C2 subgroup (p = 0.01).", "minimax-m3": "In the TCGA gastric cancer cohort, the oxidative-stress-related C2 subgroup had a better overall survival rate than the C1 subgroup (p = 0.01).", "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Consensus clustering based on oxidative stress-related genes", "Kaplan-Meier survival analysis"], "minimax-m3": ["Univariate Cox regression screening of oxidative-stress-related genes", "Consensus clustering based on the selected oxidative-stress-related genes, with K = 2", "Kaplan-Meier analysis comparing overall survival between the C1 and C2 subgroups"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["Consensus clustering identified two gastric cancer subgroups, C1 and C2, based on oxidative stress-related genes.", "Gastric cancer patients in the C2 subgroup had a better overall survival rate than those in the C1 subgroup.", "The difference in overall survival between the two subgroups was statistically significant at p = 0.01.", "The C1 subgroup was associated with poor prognosis and activated immune-related pathways."], "minimax-m3": ["Consensus clustering identified two oxidative-stress-related gastric cancer subgroups, with K = 2 achieving the optimal clustering stability: 167 patients in C1 and 207 patients in C2.", "Compared with patients in the C1 subgroup, patients in the C2 subgroup exhibited a better overall survival rate (p = 0.01).", "The two oxidative-stress-related subtypes were reported to have markedly different survival rates."], "decisive": false}, "unit": {"minimax-m3-1-flash": "", "minimax-m3": "p-value", "decisive": false, "resolution": "One reader left the unit blank. The other named 'p-value', and the paper carries that unit in its own text, so the source settles the difference.", "support": ["The criteria for determining differentially expressed genes were as follows: adjusted p-value <0.05 and absolute log fold change (|logFC|) ≥ 1.", "The thresholds were set as |NES| > 1 and adjusted p-value <0.05."]}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "Both readers returned the same number from the same sentence. The only difference was that one reader left the unit blank; the paper's own text carries the unit the other reader named, so the source resolved it.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:e82cfb0aef3d6f530ebce744928d86d3c6e13215c480cdc3b3f57d69d526cf4a", "type": "sep_package", "label": "SEP v1 package for pmid:37928388"}], "activities": [{"id": "activity:conversion:pmid:37928388", "type": "conversion", "used": ["package:e82cfb0aef3d6f530ebce744928d86d3c6e13215c480cdc3b3f57d69d526cf4a"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:37928388", "parent_hash": "sha256:e5b3d36ad8523f1229316bb20b4ac8837868c2aeda9c17615da022587a31437b", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:37928388, at the location the paper names not verified", "asset:source:pmid:37928388 not verified", "authors", "capability:capability:bench_workcell purchasable", "execution.not_run", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:diagnostic_evaluation_roc"]},"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":"2026-11-04T02:53:05+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}}}