{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39789627", "kind": "science-record", "revision": 1, "content_hash": "sha256:3dd49a79faea4302a13f38c5dec543bd4539e6ebd8a55d2018847b68677832dd", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T10:25:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "miR-9-5p/HMMR regulates the tumorigenesis and progression of clear cell renal cell carcinoma through EMT and JAK1/STAT1 signaling pathway.", "doi": "10.1186/s12967-024-05988-w", "pmid": "39789627", "authors": null, "journal": "Journal of translational medicine", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "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:39789627"], "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": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:39789627", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39789627' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39789627", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-024-05988-w", "sha256": "sha256:9e70ce552c65cde624f1c00cadc7f6d36fcb0503f4082efa35a4f17d83b0ee53", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-024-05988-w", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:39789627 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39789627"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39789627"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "7827f8360cb3b3210d892137cc00b49e9652464403b79683684f0da384906fe5", "source_hash": "9e70ce552c65cde624f1c00cadc7f6d36fcb0503f4082efa35a4f17d83b0ee53", "raw_response_sha256": "sha256:486591f6c3a520782aa8a75134db20fdd25e4379be3a761243f3aaaa0552c968", "raw_response_chars": 78567}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "95d2735c32b8c5c2d30c09521addf8412191bd46109f8512c468541407451889", "source_hash": "9e70ce552c65cde624f1c00cadc7f6d36fcb0503f4082efa35a4f17d83b0ee53", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states qualitatively that HMMR is overexpressed in ccRCC and is associated with tumor progression and poor patient prognosis, but it does not state a headline numerical result for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states qualitatively that HMMR is overexpressed in ccRCC and is associated with tumor progression and poor patient prognosis, but it does not state a headline numerical result for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:30:25.310257+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "5916c2bc3a8382b07e565c89fade77868e75cdb9313236292f59dade819ed129", "source_hash": "9e70ce552c65cde624f1c00cadc7f6d36fcb0503f4082efa35a4f17d83b0ee53", "raw_response": "<think>We need answer JSON only. Need parse task: find single numerical result replication registered target (headline numerical result main finding). Source supplied appears abstract/methods no headline numeric result, only sample counts and thresholds etc. Registered target is generic headline numerical result. Paper text states no number for registered target likely false. Need set parent_value 0, unit empty, evidence empty, target_result says what text states instead. Need exact schema. We should determine whether perhaps total 614 samples is headline numerical? They specifically ask \"single numerical result that a replication of the registered target has to reproduce\" registered target: \"the headline numerical result the paper states for its main finding.\" The source doesn't state one; findings qualitative. Numbers are sample sizes/method thresholds. Thus number_stated false. target_result perhaps \"The text states that HMMR is overexpressed in ccRCC ... but reports no headline numerical result.\" Unit/evidence empty. Ensure parent_value numeric 0. JSON valid.\n\nCould the answer target_result include source wording, but not evidence exact quote requirement applies if number. They say \"say in target_result what the text does state instead.\" We can paraphrase perhaps mention qualitative finding. No extra props.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that HMMR is overexpressed in ccRCC and associated with pathological grade, stage, and patient prognosis, but it gives no headline numerical result for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that HMMR is overexpressed in ccRCC and associated with pathological grade, stage, and patient prognosis, but it gives no headline numerical result for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:30:24.603444+00:00"}], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "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": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted statement is absent from the supplied text", "raw_response": "{\n  \"target_result\": \"HMMR was significantly up-regulated in ccRCC tumor tissues, and elevated HMMR expression was associated with ccRCC progression and adverse patient prognosis.\",\n  \"work_type\": \"analysis_plus_physical_validation\",\n  \"physical_methods\": [\n    \"Transwell assays\",\n    \"CCK-8 assays\",\n    \"clone formation assays\",\n    \"subcutaneous xenograft experiments in nude mice\",\n    \"cellular functional experiments\"\n  ],\n  \"analysis_methods\": [\n    \"The Cancer Genome Atlas (TCGA) expression analysis\",\n    \"Gene Set Enrichment Analysis (GSEA)\",\n    \"Genomics of Drug Sensitivity in Cancer (GDSC) drug-sensitivity prediction using the pRRophetic package\",\n    \"multivariate regression nomogram model\",\n    \"single-cell analysis using the Seurat package and tSNE algorithm\",\n    \"SingleR cluster annotation\",\n    \"CIBERSORT immune-cell infiltration analysis\",\n    \"differential expression analysis using DESeq2, limma, and edgeR\",\n    \"ENCORI-predicted HMMR-interacting miRNA analysis\"\n  ],\n  \"statistical_method\": \"Student’s t-test for differences between two groups and Pearson correlation analysis for correlations, using p < 0.05 as the threshold for statistical significance.\",\n  \"method_evidence\": \"To evaluate the differences between two groups and to analyze correlations, Student’s t-test and Pearson correlation analysis were applied, respectively, with a threshold of p < 0.05 indicating statistical significance.\",\n  \"repositories\": [\n    {\n      \"repository\": \"The Cancer Genome Atlas (TCGA) database\",\n      \"accession\": \"TCGA\",\n      \"data_description\": \"Raw mRNA expression data for ccRCC, comprising 614 samples: 72 normal and 542 tumor samples; the database was also used for miRNA expression, immune-cell infiltration, and other ccRCC analyses.\",\n      \"evidence\": \"We downloaded the raw mRNA expression data for ccRCC from the TCGA database, encompassing a total of 614 samples—normal (n = 72) and tumor (n = 542).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"NCBI GEO\",\n      \"accession\": \"GSE207493\",\n      \"data_description\": \"Single-cell data from 19 ccRCC patients, used for pathway enrichment and analysis of HMMR expression across cell subtypes.\",\n      \"evidence\": \"Additionally, for single-cell analysis, data for 19 ccRCC patients were extracted from the NCBI GEO public database (GSE207493).\",\n      \"publicly_downloadable\": true\n    },\n    {\n      \"repository\": \"MsigDB database\",\n      \"accession\": \"annotated gene sets version 7.0\",\n      \"data_description\": \"Annotated gene sets used with GSE207493 for GSEA between HMMR high-expression and low-expression subtypes.\",\n      \"evidence\": \"We downloaded annotated gene sets version 7.0 from the MsigDB database and data from GSE207493 for pathway enrichment analysis between subtypes.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Genomics of Drug Sensitivity in Cancer (GDSC) database\",\n      \"accession\": \"unknown\",\n      \"data_description\": \"Drug-sensitivity data used with the pRRophetic package to estimate IC50 values and predict drug sensitivity for tumor samples.\",\n      \"evidence\": \"The Genomics of Drug Sensitivity in Cancer (GDSC) database was used, along with the “pRRophetic” package, to predict drug sensitivity for each tumor sample.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"ENCORI database\",\n      \"accession\": \"unknown\",\n      \"data_description\": \"Predicted low-expressed miRNAs potentially interacting with HMMR, intersected with differentially expressed miRNAs identified by DESeq2, limma, and edgeR.\",\n      \"evidence\": \"We then intersected the differentially expressed miRNAs identified by these methods with low-expressed miRNAs predicted to potentially interact with HMMR from the ENCORI database.\",\n      \"publicly_downloadable\": false\n    }\n  ],\n  \"availability_statement\": \"The paper states that raw TCGA mRNA expression data were downloaded and that GSE207493 was extracted from the public NCBI GEO database. It does not explicitly state that the TCGA, MsigDB, GDSC, or ENCORI data can be downloaded without an application, embargo, or request, and it gives no availability statement for newly generated experimental data.\",\n  \"data_on_request\": false,\n  \"source_claims\": [\n    \"HMMR expression was significantly up-regulated in tumor tissues of ccRCC patients.\",\n    \"Elevated HMMR expression showed a strong correlation with ccRCC progression and adverse patient prognosis.\",\n    \"Knocking down HMMR inhibited the proliferative and migratory abilities of ccRCC cells, whereas HMMR overexpression amplified these oncogenic properties.\",\n    \"Reduced HMMR expression inhibited ccRCC tumor proliferation in a nude-mouse model.\",\n    \"miR-9-5p overexpression effectively downregulated HMMR expression and impeded ccRCC cell proliferation and migration.\",\n    \"HMMR might influence ccRCC growth through the EMT and JAK1/STAT1 signaling pathways.\"\n  ],\n  \"missing_information\": [\n    \"No single headline numerical estimate, effect size, confidence interval, or exact p-value for the main finding is stated in the supplied text.\",\n    \"The supplied text does not identify which statistical test was applied specifically to the primary HMMR up-regulation comparison beyond the general statement that Student’s t-test was used for differences between two groups.\",\n    \"The supplied text does not explicitly describe unrestricted, no-application download conditions for the TCGA, MsigDB, GDSC, or ENCORI repositories.\",\n    \"No accession is provided for the GDSC or ENCORI data.\",\n    \"The availability of newly generated experimental data is not stated.\",\n    \"The numerical results underlying the prognostic association, xenograft measurements, proliferation assays, and migration assays are not provided in the supplied text.\"\n  ],\n  \"evidence_spans\": [\n    \"HMMR expression was significantly up-regulated in tumor tissues of ccRCC patients, and elevated HMMR expression level showed a strong correlation with ccRCC progression and adverse prognoses of patients.\",\n    \"Knocking down HMMR inhibited the proliferative and migratory abilities of ccRCC cells, while its overexpression amplified these oncogenic properties.\",\n    \"In nude mice model, reduced HMMR expression inhibited ccRCC tumor proliferation in vivo.\",\n    \"Furthermore, overexpression of an upstream transcriptional regulator, miR-9-5p, effectively downregulated HMMR expression and thus impeded ccRCC cells proliferation and migration.\",\n    \"HMMR might influence ccRCC growth via the Epithelial-Mesenchymal Transition (EMT) pathway and the Janus Kinase 1/Signal Transducer and Activator of Transcription 1 (JAK1/STAT1) pathway.\",\n    \"We downloaded the raw mRNA expression data for ccRCC from the TCGA database, encompassing a total of 614 samples—normal (n = 72) and tumor (n = 542).\",\n    \"Additionally, for single-cell analysis, data for 19 ccRCC patients were extracted from the NCBI GEO public database (GSE207493).\",\n    \"The statistical analyses of the acquired data were performed using GraphPad Prism 8.0 software and the R programming language (version 4.3.0) for both graphical presentation and the assessment of statistical significance.\",\n    \"To evaluate the differences between two groups and to analyze correlations, Student’s t-test and Pearson correlation analysis were applied, respectively, with a threshold of p < 0.05 indicating statistical significance.\"\n  ]\n}"}]}}, {"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:fcccf8e64b6368b496e0ed624dd9172dd8542111debe5e19bcc155ded6de1346", "type": "sep_package", "label": "SEP v1 package for pmid:39789627"}], "activities": [{"id": "activity:conversion:pmid:39789627", "type": "conversion", "used": ["package:fcccf8e64b6368b496e0ed624dd9172dd8542111debe5e19bcc155ded6de1346"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"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": "e42b8804-bde8-4947-972e-edb416bc8734", "parent_hash": "fcccf8e64b6368b496e0ed624dd9172dd8542111debe5e19bcc155ded6de1346", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:39789627 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39789627' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:42:48+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}}}