{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36276274", "kind": "science-record", "revision": 5, "content_hash": "sha256:e1256f5f013c8920b084823488859e3d03b8b869cfc6477931b8e390aabb2890", "created_at": "2026-11-01T18:15:41Z", "updated_at": "2026-11-01T22:50:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "SFRP2 is a Novel Diagnostic Biomarker and Suppresses the Proliferation of Pituitary Adenoma.", "doi": "10.1155/2022/4272525", "pmid": "36276274", "authors": ["Rongxi Huang", "Danyan Chen", "Hongman Wang", "Binghan Zhang", "Yu Zhang", "Wei Ren"], "journal": "Journal of oncology", "year": 2022, "abstract": "Pituitary adenoma (PA) constitutes one of the most common intracranial tumors. The present study was designed to identify potential diagnostic markers for PA. We used gene expression profiles (GEO: GSE26966 and GEO: GSE63357 datasets) derived from human PA and nontumor samples that were made freely accessible by the gene expression omnibus (GEO) datasets. Differentially expressed genes (DEGs) were screened between 14 normal specimens and 34 PA specimens by the use of the limma package of the R. The diagnostic genes were determined using a LASSO regression model and SVM-RFE analysis. SFRP2 expression in PA cells was analyzed using RT-PCR, and the effect of SFRP2 dysregulation on PA cell proliferation was measured using CCK-8 analysis. In this study, 361 DEGs were identified: 309 genes were downregulated and 52 genes were upregulated. The results of KEGG assays revealed that the 361 DEGs were mainly enriched in the PI3K-Akt signaling pathway, MAPK signaling pathway, growth hormone synthesis, secretion and action, and AGE-RAGE signaling pathway in diabetic complications. Results from the LASSO regression model and the SVM-RFE analysis indicated that LOC101060391 and SFRP2 were diagnostic genes. In contrast to normal tissue, the expressions of LOC101060391 and SFRP2 were much lower in PA samples. According to the ROC assays, high LOC101060391 and SFRP2 expression had an AUC value >0.9 for PA. Upregulation of SFRP2 distinctly inhibited the proliferative capacity of PA cells, as shown by CCK-8 analysis. Furthermore, knockdown of SFRP2 had an influence on cell growth in both the AtT-20 and HP75 cell lines. Taken together, our findings indicate that LOC101060391 and SFRP2 have diagnostic potential for PA. Furthermore, SFRP2 may be an antioncogene and a therapeutic target for PA.", "claims": [{"id": "claim-method", "statement": "Differential expression analysis between 14 normal specimens and 34 tumor specimens was all performed with the help of the limma package of the R programming language (https://www.bioconductor.org/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36276274", "locator": "sections[7] \"2.5. Data Processing and DEG Screening\" paragraph 2", "quote": "Differential expression analysis between 14 normal specimens and 34 tumor specimens was all performed with the help of the limma package of the R programming language (https://www.bioconductor.org/)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original data are provided by the corresponding author upon request without any hesitation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36276274", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The original data are provided by the corresponding author upon request without any hesitation."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using limma for differential-expression analysis of two GEO datasets and LASSO regression plus SVM-RFE for biomarker selection, the study identified LOC101060391 and SFRP2 as diagnostic biomarkers for pituitary adenoma.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36276274", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We used gene expression profiles (GEO: GSE26966 and GEO: GSE63357 datasets) derived from human PA and nontumor samples that were made freely accessible by the gene expression omnibus (GEO) datasets."}, {"asset": "source:pmid:36276274", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Differentially expressed genes (DEGs) were screened between 14 normal specimens and 34 PA specimens by the use of the limma package of the R."}, {"asset": "source:pmid:36276274", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Results from the LASSO regression model and the SVM-RFE analysis indicated that LOC101060391 and SFRP2 were diagnostic genes."}, {"asset": "source:pmid:36276274", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "According to the ROC assays, high LOC101060391 and SFRP2 expression had an AUC value >0.9 for PA."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using limma for differential-expression analysis of two GEO datasets and LASSO regression plus SVM-RFE for biomarker selection, the study identified LOC101060391 and SFRP2 as diagnostic biomarkers for pituitary adenoma.", "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:36276274"], "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:GSE26966"], "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": ["data:geo:GSE26966"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36276274", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/4272525", "sha256": "sha256:f063d3177403b36525b7a58a2bfb2a8d98c18c53a4dcf62dd2af3f030d8f64d4", "bytes": 21268, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/4272525", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9586780", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE26966", "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=GSE26966", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26966", "version": null, "note": "The original data are provided by the corresponding author upon request without any hesitation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original data are provided by the corresponding author upon request without any hesitation.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM663736", "GSM663737", "GSM663738", "GSM663739", "GSM663740", "GSM663741", "GSM663742", "GSM663743", "GSM663744", "GSM663745", "GSM663746", "GSM663747", "GSM663748", "GSM663749", "GSM663750", "GSM663751", "GSM663752", "GSM663753", "GSM663754", "GSM663755", "GSM663756", "GSM663757", "GSM663758"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Identification of Growth arrest and DNA-damage-inducible gene beta (GADD45beta) as a Novel Tumor Suppressor in Pituitary Gonadotrope Tumors", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE63357", "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=GSE63357", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63357", "version": null, "note": "The original data are provided by the corresponding author upon request without any hesitation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original data are provided by the corresponding author upon request without any hesitation.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1546562", "GSM1546563", "GSM1546564", "GSM1546565", "GSM1546566", "GSM1546567", "GSM1546568", "GSM1546569", "GSM1546570", "GSM1546571", "GSM1546572", "GSM1546573", "GSM1546574", "GSM1546575", "GSM1546576", "GSM1546577", "GSM1546578", "GSM1546579", "GSM1546580", "GSM1546581", "GSM1546582", "GSM1546583", "GSM1546584", "GSM1546585", "GSM1546586"], "sample_count": 25, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Identification of distinct molecular signatures in AIP mutation-positive familial isolated pituitary adenomas", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE26966 not downloaded", "asset:data:geo:GSE26966 licence not read", "asset:data:geo:GSE63357 not downloaded", "asset:data:geo:GSE63357 licence not read"]}, "analysis": {"state": "partial", "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": "verbatim", "quote": "Differential expression analysis between 14 normal specimens and 34 tumor specimens was all performed with the help of the limma package of the R programming language (https://www.bioconductor.org/)."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Student's t test"}}, {"id": "method-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}, {"id": "method-4", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": 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": "R1", "reachable": true, "accessions": ["GSE26966", "GSE63357"], "resolved_accessions": ["GSE26966", "GSE63357"], "statements": ["The original data are provided by the corresponding author upon request without any hesitation."], "basis": "The paper names GSE26966, GSE63357 in gene expression omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36276274", "data:geo:GSE26966"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE26966"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:12:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7030, "completion_tokens": 1197, "cached_tokens": 264}}, "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:36276274", "type": "paper", "label": "pmid:36276274"}, {"id": "source:pmid:36276274", "type": "manuscript", "label": "PMID 36276274 full text"}, {"id": "data:geo:GSE26966", "type": "dataset", "label": "GEO GSE26966"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36276274", "type": "paper", "label": "pmid:36276274"}, {"id": "source:pmid:36276274", "type": "manuscript", "label": "PMID 36276274 full text"}, {"id": "data:geo:GSE26966", "type": "dataset", "label": "GEO GSE26966"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36276274", "type": "extraction", "used": ["source:pmid:36276274"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE26966", "type": "accession_resolution", "used": ["data:geo:GSE26966"], "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:36276274", "parent_hash": "sha256:fbb0894395a67ea1503a41d457555b5041bc616bf454b598d7f047fd2780b3a0", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE26966 licence not read", "asset:data:geo:GSE26966 not downloaded", "asset:data:geo:GSE63357 licence not read", "asset:data:geo:GSE63357 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["on PA cell proliferation was measured using CCK-8 analysis. In this study, 361 DEGs were ident", "liferative capacity of PA cells, as shown by CCK-8 analysis. Furthermore, knockdown of SFRP2 ha"], "order_basis": "paper_text_order:777", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ls, as shown by CCK-8 analysis. Furthermore, knockdown of SFRP2 had an influence on cell growth in", "Materials and Methods 2.1. Cell Culture and Transfection The HP75 and AtT-20 pituitary tumor cell lin", "density a full twenty-four hours before the transfection, and the plates were left to incubate overni", "e overnight. Both AtT-20 and HP75 cells were transfected with pcDNA-SFRP2, sh-SFRP2, and a control (b"], "order_basis": "paper_text_order:1584", "id": "assay:2"}, {"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": ["Differential expression analysis between 14 normal specimens and 34 tumor specimens was all performed with the help of the limma package of the R programming language (https://www.bioconductor.org/)."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:24:57+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}}}