{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40816225", "kind": "science-record", "revision": 1, "content_hash": "sha256:d149c814b1b23a77229b2c0ff6cf56977d18605757f91aca9b0d2955114e2403", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T10:25:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Exosomal gene signature in esophageal carcinoma: Insights from single-cell and bulk RNA sequencing.", "doi": "10.1016/j.tranon.2025.102490", "pmid": "40816225", "authors": null, "journal": "Translational oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 9.0, "unit": "genes", "tolerance": null, "source": "chars 99-183 of source sha256 313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065"}, "evidence": [{"asset": "source:pmid:40816225", "locator": "chars 99-183 of source sha256 313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "quote": "A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data."}]}], "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:40816225"], "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:accession_absent", "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:40816225", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "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:40816225' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40816225", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.tranon.2025.102490", "sha256": "sha256:313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.tranon.2025.102490", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40816225 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:40816225"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40816225"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "9fbfe0619d793ef44d7a1148801d660b275e0fecb26d92fd1fc8df2dfe1b3505", "source_hash": "313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "raw_response_sha256": "sha256:016b48d83055c8883a203b76d5bfc5928de11357bc31c879eb03ec581aea76fc", "raw_response_chars": 3936}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "13ce42f23b613ccedab54234c43f42d2f3d6f0c540324cca12e4ba78e0200657", "source_hash": "313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "raw_response_sha256": "sha256:6833d909c941bd4effa030c131c65517ffde250512b656ba4c1cbccea0c570ff", "raw_response_chars": 52176}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "78c22c0677d78a159bdb222e3621cdf1dd3a993e92443f2121ba1460fa80e4db", "source_hash": "313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "raw_response": "{\"parent_value\":9,\"unit\":\"genes\",\"evidence\":\"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\",\"target_result\":\"The study constructed a nine-gene exosomal signature.\",\"number_stated\":true}", "reading": {"parent_value": 9, "unit": "genes", "evidence": "A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.", "target_result": "The study constructed a nine-gene exosomal signature.", "number_stated": true, "source_locator": "chars 99-183 of source sha256 313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065"}, "recorded_at": "2026-10-31T15:29:33.383199+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "b3fe3a2f2f4419f2f84cccc6a8561ef63d77760ac34a69805aaba2edff87972e", "source_hash": "313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065", "raw_response": "<think>We need answer JSON only. Need determine single numerical result replication of registered target main finding. Source headline says \"A nine-gene exosomal signature was constructed...\" Could headline number be nine genes, unit genes? Need exact contiguous quotation containing number. They ask value paper states for registered target, headline numerical result main finding. \"A nine-gene exosomal signature...\" Number stated in words nine, but parent_value number perhaps 9, evidence exact quote \"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\" Unit must unit paper prints. \"nine-gene\" is number spelled word, unit gene? Or maybe 9 genes stated in Target prediction: \"the 9 genes included in the risk model.\" The headline numerical result likely nine-gene signature. They say numerical result, exact quote. Could extract 9 and unit \"genes\". Evidence quote maybe \"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\" But requirement evidence exact contiguous quote contains the number. Does \"nine\" count? likely yes. Yet \"unit must be unit paper prints.\" \"nine-gene\" unit is gene perhaps. parent_value 9, unit \"genes\" or \"gene\"? Usually benchmark expected unit from source perhaps \"genes\". Need target_result explain main finding. number_stated true.\n\nBut perhaps there is no actual quantitative performance metric (AUC, HR, p-value); only count of nine-gene signature. They specifically registered target \"the headline numerical result the paper states for its main finding\", likely abstract headline is nine-gene signature. Need quote whole clause as attribution. \"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\" Exact contiguous.\n\nCould quote additionally \"the 9 genes included in the risk model\" to support numeric digit and unit. But single exact contiguous quotation can include both? They ask evidence exact quote contains number. We can quote \"A nine-gene...\" It contains number in words. parent_value numeric 9. Unit \"genes\". Is that unit printed? \"gene\" singular in compound adjective, while \"9 genes\" explicitly printed in another clause. Better evidence could be \"the 9 genes included in the risk model.\" This directly says 9 genes, but target registered main finding and attribution? It refers risk model. Yet perhaps whole sentence: \"In order to identify potential therapeutic options, the enrichR database was utilized to predict small molecule drugs that specifically target the 9 genes included in the risk model.\" This establishes risk model has 9 genes, exact digit and unit. But headline finding is a nine-gene exosomal signature. Could quote that sentence, and perhaps also another contiguous clause? Evidence should be exact contiguous quotation from source, not necessarily only one quote. Could quote two sentences separately? \"A nine-gene...\" and later \"...\" But likely simplest one quote.\n\nNeed target_result string perhaps \"The paper states that a nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\" Should not paraphrase? This field can explain. The instruction says report headline number only, but JSON schema demands target_result. We need concise.\n\nQuestion nuanced: \"find the single numerical result that a replication ... has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" There may be a trap: Source text has many numbers, but no performance result. Main headline says \"A nine-gene exosomal signature...\" Thus number 9. It is stated. Unit must paper prints. \"nine-gene\" perhaps unit \"gene\". They might expect \"9 genes\". Evidence exact quote could be \"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\" The number itself is written \"nine\", but exact quote. parent_value 9.\n\nCould parent_value need 9, unit \"genes\". JSON valid. Evidence no ellipsis. Let's ensure exact source punctuation. It is exactly. target_result perhaps \"The headline result is a nine-gene exosomal signature constructed using scRNA-seq and multi-omics data.\" This paraphrases slightly but okay field. number_stated true.\n\n\"unit must be the unit the paper prints.\" The paper prints \"nine-gene\" not \"genes\" in headline. But elsewhere \"9 genes\". Maybe unit should be \"genes\", as semantic unit. They might reject because printed unit \"gene\" in compound. Better quote exact phrase from source \"the 9 genes included in the risk model.\" This explicitly prints \"9 genes\", and is a contiguous exact quotation. But to connect main target, maybe quote full sentence: \"In order to identify potential therapeutic options, the enrichR database was utilized to predict small molecule drugs that specifically target the 9 genes included in the risk model.\" Does that state headline main finding? It confirms 9 genes in risk model. Yet the actual headline sentence is clearer. Could evidence include both exact contiguous quotations separated? Requirement \"evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it.\" Could quote a longer contiguous passage spanning huge sections? No need. One quote \"A nine-gene...\" contains number. Unit perhaps \"genes\" can be derived, but not calculated. In number extraction tasks, numerical words count. The number is attached to target by wording directly.\n\nMaybe expected no number because \"nine-gene\" is a count describing signature, not a result metric? Registered target says \"headline numerical result the paper states for its main finding\". The source title/abstract-like highlights. \"A nine-gene exosomal signature was constructed...\" clearly headline numerical result. They might define target deliberately broad to select this. There is also 78 immune genes, 32 cancer types, 9 genes. Main finding headline = nine-gene. So yes.\n\nNeed only JSON, no markdown. Let's formulate:\n{\n \"parent_value\": 9,\n \"unit\": \"genes\",\n \"evidence\": \"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\",\n \"target_result\": \"The paper states that a nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\",\n \"number_stated\": true\n}\nWould \"unit paper prints\" perhaps \"gene\" not \"genes\"? Usually unit field should be \"genes\" because 9 genes. Evidence exact. Another option evidence sentence with explicit 9 genes: \"In order to identify potential therapeutic options, the enrichR database was utilized to predict small molecule drugs that specifically target the 9 genes included in the risk model.\" Then unit exact \"genes\". But target_result says main finding. Is evidence attribution sufficient? It says \"risk model\", not \"exosomal signature\". Meanwhile headline quote directly names exosomal signature. The unit printed there is compound \"nine-gene\". Unit can still be \"genes.\" User says \"unit must be the unit the paper prints\", likely means don't transform %, etc. Maybe they expect \"genes\". Explicit occurrence helps.\n\nCould evidence be:\n\"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data. The risk score correlates strongly with prognosis in esophageal carcinoma patients.\"\nNo explicit 9 digit. Not needed.\n\nCould quote exact contiguous region from target prediction and mention risk model. But maybe \"registered target\" is the headline numerical result, and evidence should directly support target. Best quote is headline. If evaluator checks number substring perhaps \"nine\" recognized, likely.\n\n\"Report the headline number only\" means target_result maybe just \"9 genes\" perhaps not explanatory.</think>\n\n{\"parent_value\":9,\"unit\":\"genes\",\"evidence\":\"A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\",\"target_result\":\"The paper states that a nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.\",\"number_stated\":true}", "reading": {"parent_value": 9, "unit": "genes", "evidence": "A nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.", "target_result": "The paper states that a nine-gene exosomal signature was constructed using scRNA-seq and multi-omics data.", "number_stated": true, "source_locator": "chars 99-183 of source sha256 313192d582eb1d576797a59fa371aca21d8dec7ff6b0b084cb88e38bb0905065"}, "recorded_at": "2026-10-31T15:29:42.516788+00:00"}], "agreement": true, "disagreements": {"analysis_methods": {"minimax": ["Seurat single-cell RNA-seq analysis", "quality control filtering", "t-SNE dimensionality reduction", "marker-gene identification", "log₂(TPM + 1) normalization", "ComBat batch-effect correction", "Seurat SCTransform-based integration", "principal component analysis", "AUCell exosome gene scoring", "differential gene expression analysis", "intersection analysis", "Gene Ontology pathway enrichment analysis", "clusterProfiler", "enrichR target prediction", "Gene Set Variation Analysis (GSVA)", "pan-cancer analysis"], "minimax_alt": ["Single-cell RNA sequencing analysis with Seurat", "Quality-control filtering", "t-SNE dimensionality reduction", "Marker-gene identification", "log₂(TPM + 1) normalization", "ComBat batch-effect correction using sva (v3.36.0)", "Seurat SCTransform-based integration using FindIntegrationAnchors and IntegrateData", "Principal component analysis", "AUCell exosome gene scoring", "Differential gene expression analysis", "Intersection analysis of differential and known exosome-related genes", "Gene Ontology pathway enrichment analysis using clusterProfiler", "Mutation analysis using TCGAbiolinks and maftools", "enrichR small-molecule target prediction", "Gene Set Variation Analysis (GSVA)", "Immunotherapy-cohort analysis", "Pan-cancer analysis"], "decisive": false}}, "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": "passed", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "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.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:8ca158d65fe01932bf2a1be3a643b016e803c579a6eeb450fea0627d79d0b0d0", "type": "sep_package", "label": "SEP v1 package for pmid:40816225"}], "activities": [{"id": "activity:conversion:pmid:40816225", "type": "conversion", "used": ["package:8ca158d65fe01932bf2a1be3a643b016e803c579a6eeb450fea0627d79d0b0d0"], "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": "97b028fa-732e-4aba-9fc5-8f1244089b36", "parent_hash": "8ca158d65fe01932bf2a1be3a643b016e803c579a6eeb450fea0627d79d0b0d0", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40816225 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:accession_absent", "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:40816225' 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":"2026-11-04T02:51:16+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}}}