{"data":{"$schema":"https:\/\/json-schema.org\/draft\/2020-12\/schema","$id":"https:\/\/corpus.bntrg.co.uk\/sci\/1.0\/sci.schema.json","title":"SCI: a science paper and the experiment behind it","description":"One document describes one research record. The paper layer and the experiment layer are filled in over time; each carries its own state, so a partial record is a valid record.","type":"object","required":["sci_version","id","kind","revision","content_hash","paper","experiment","data","analysis","capability","readiness","review","execution","provenance","gaps"],"additionalProperties":false,"properties":{"sci_version":{"enum":["1.0","1.1","1.2","1.3","1.4","1.5"]},"schema":{"const":"https:\/\/corpus.bntrg.co.uk\/sci\/1.0\/sci.schema.json"},"id":{"type":"string","minLength":1},"kind":{"const":"science-record"},"revision":{"type":"integer","minimum":1},"content_hash":{"type":["string","null"],"pattern":"^sha256:[0-9a-f]{64}$"},"created_at":{"type":["string","null"]},"updated_at":{"type":["string","null"]},"generator":{"type":["object","null"]},"paper":{"type":"object","required":["state","title","doi","pmid","authors","journal","year","abstract","claims","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"title":{"type":["string","null"]},"doi":{"type":["string","null"]},"pmid":{"type":["string","null"]},"authors":{"type":["array","null"],"items":{"type":"string"}},"journal":{"type":["string","null"]},"year":{"type":["integer","null"]},"abstract":{"type":["string","null"]},"claims":{"type":"array","items":{"type":"object","required":["id","statement","kind","target","evidence","state"],"additionalProperties":false,"properties":{"id":{"type":"string"},"statement":{"type":["string","null"]},"kind":{"enum":["quantitative","qualitative","methodological"]},"state":{"enum":["absent","partial","complete","blocked"]},"target":{"type":["object","null"],"required":["value","unit","tolerance","source"],"additionalProperties":false,"properties":{"value":{"type":["number","null"]},"unit":{"type":["string","null"]},"tolerance":{"type":["number","null"],"minimum":0},"source":{"type":["string","null"]}}},"evidence":{"type":"array","items":{"type":"object","required":["asset","locator","quote"],"additionalProperties":false,"properties":{"asset":{"type":["string","null"]},"locator":{"type":["string","null"]},"quote":{"type":["string","null"]}}}}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"experiment":{"type":"object","required":["state","objective","steps","materials","instruments","reagents","conditions","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"objective":{"type":["string","null"]},"steps":{"type":"array","items":{"type":"object","required":["id","order","name","kind","state","parameters","inputs","outputs","duration_hours"],"additionalProperties":false,"properties":{"id":{"type":"string"},"order":{"type":"integer","minimum":1},"name":{"type":["string","null"]},"kind":{"enum":["physical","computational","data-preparation","analysis","other"]},"state":{"enum":["absent","partial","complete","blocked"]},"blocked_on":{"description":"What stops this step running, named. The blocker is the step's own, not the paper's.","type":["string","null"]},"description":{"type":["string","null"]},"duration_hours":{"type":["number","null"],"minimum":0},"parameters":{"type":"object"},"inputs":{"type":"array","items":{"type":"string"}},"outputs":{"type":"array","items":{"type":"string"}},"instruments":{"type":"array","items":{"type":"string"}},"reagents":{"type":"array","items":{"type":"object","required":["name","quantity","unit"],"additionalProperties":false,"properties":{"name":{"type":["string","null"]},"quantity":{"type":["number","null"]},"unit":{"type":["string","null"]},"catalogue":{"type":["string","null"]}}}}}}},"materials":{"type":"array","items":{"type":"string"}},"instruments":{"type":"array","items":{"type":"string"}},"reagents":{"type":"array","items":{"type":"string"}},"conditions":{"type":"object"},"gaps":{"type":"array","items":{"type":"string"}}}},"data":{"type":"object","required":["state","assets","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"group_sizes":{"type":["object","null"],"description":"The number of samples in each comparison group of the source data, as the repository metadata states. A consumer that has the samples can check them against the paper's design instead of re-analysing a different set.","additionalProperties":{"type":"integer","minimum":0}},"paper_group_sizes":{"type":["object","null"],"description":"The number of samples the paper says it analysed in each group, with the sentence the numbers came from. `data.group_sizes` is the repository's count; where the two differ the paper analysed a subset of the repository's samples, and a run over the repository's samples is a re-analysis rather than a reproduction. From 1.5.","additionalProperties":false,"required":["sizes"],"properties":{"sizes":{"type":"object","description":"The count the paper states, by group. The group names are the paper's own, so they need not be the repository's names.","additionalProperties":{"type":"integer","minimum":0}},"total":{"type":["integer","null"],"description":"The number of samples the paper states in total, where the paper states it."},"source":{"type":["string","null"],"description":"The sentence the counts came from, verbatim, so a reader can check the corpus's reading against the paper."},"reference_group":{"type":["string","null"],"description":"The group the paper's results are expressed against, where the paper names one."}}},"assets":{"type":"array","items":{"type":"object","required":["id","role","format","media_type","uri","sha256","bytes","access","state","reader","reader_status","structure"],"additionalProperties":false,"properties":{"id":{"type":"string"},"role":{"enum":["manuscript","protocol","raw","processed","derived","code","supplementary","figure","table","reference"]},"format":{"type":"string"},"media_type":{"type":"string"},"uri":{"type":["string","null"]},"sha256":{"type":["string","null"],"pattern":"^sha256:[0-9a-f]{64}$"},"bytes":{"type":["integer","null"],"minimum":0},"access":{"enum":["open","restricted","embargoed","unknown"]},"state":{"enum":["declared","resolved","verified","unavailable"]},"reader":{"type":["string","null"]},"reader_status":{"enum":["available","converter_required","reader_required","unknown"]},"identifier":{"type":["string","null"]},"version":{"type":["string","null"]},"note":{"type":["string","null"]},"structure":{"type":["object","null"]},"table":{"type":["object","null"],"additionalProperties":false,"required":["label","caption","rows","row_count","column_count","numeric_cells","header_rows","locator"],"properties":{"label":{"type":["string","null"]},"caption":{"type":["string","null"]},"rows":{"type":"array","items":{"type":"array","items":{"type":"string"}}},"row_count":{"type":"integer","minimum":0},"column_count":{"type":"integer","minimum":0},"numeric_cells":{"type":"integer","minimum":0},"header_rows":{"type":"integer","minimum":0},"locator":{"type":"string"}}}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"analysis":{"type":"object","required":["state","methods","targets","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"methods":{"type":"array","items":{"type":"object","required":["id","family","specific","label","dsl_operations","missing_operations","expressible","parameters","data_shapes","evidence"],"additionalProperties":false,"properties":{"id":{"type":"string"},"family":{"type":["string","null"]},"specific":{"type":["string","null"]},"label":{"type":["string","null"]},"dsl_operations":{"type":"array","items":{"type":"string"}},"missing_operations":{"type":"array","items":{"type":"string"}},"expressible":{"type":["boolean","null"]},"parameters":{"type":"object"},"data_shapes":{"type":"array","items":{"type":"string"}},"evidence":{"type":"object","required":["score","band","quote"],"additionalProperties":false,"properties":{"score":{"type":["number","null"]},"band":{"type":["string","null"]},"quote":{"type":["string","null"]}}}}}},"targets":{"type":"array","items":{"type":"object","required":["id","claim_id","operation","expected_value","unit","tolerance","state"],"additionalProperties":false,"properties":{"id":{"type":"string"},"claim_id":{"type":["string","null"]},"operation":{"type":["string","null"]},"expected_value":{"type":["number","null"]},"unit":{"type":["string","null"]},"tolerance":{"type":["number","null"],"minimum":0},"state":{"enum":["absent","partial","complete","blocked"]},"note":{"type":["string","null"]}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"capability":{"type":"object","required":["state","requirements","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"requirements":{"type":"array","items":{"type":"object","required":["capability_id","label","assay_families","availability_state","tier_unlocked"],"additionalProperties":false,"properties":{"capability_id":{"type":"string"},"label":{"type":["string","null"]},"assay_families":{"type":"array","items":{"type":"string"}},"availability_state":{"type":["string","null"]},"tier_unlocked":{"type":["string","null"]},"candidate":{"type":["string","null"]}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"readiness":{"type":"object","required":["state","tier","blocking_axis","blocked_on","axes","can_run","must_build","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"tier":{"description":"The corpus tier, or null when the corpus has not tiered this paper. A null tier is not a high tier: it says the corpus has not judged it.","enum":["R0","R1","R2","R3","R4","R5",null]},"blocking_axis":{"description":"The axis that blocks the paper, or null when the corpus has not judged it. `none` is a positive claim that nothing blocks it.","enum":["method","capability","data","none",null]},"blocked_on":{"type":["string","null"]},"axes":{"type":"object"},"can_run":{"type":"object","required":["dsl_operations","assets","steps"],"additionalProperties":false,"properties":{"dsl_operations":{"type":"array","items":{"type":"string"}},"assets":{"type":"array","items":{"type":"string"}},"steps":{"type":"array","items":{"type":"string"}}}},"must_build":{"type":"object","required":["dsl_operations","converters","readers","capabilities","data_gaps"],"additionalProperties":false,"properties":{"dsl_operations":{"type":"array","items":{"type":"object","required":["operation","unlocks_papers","priority"],"additionalProperties":false,"properties":{"operation":{"type":"string"},"unlocks_papers":{"type":["integer","null"]},"priority":{"type":["integer","null"]}}}},"converters":{"type":"array","items":{"type":"string"}},"readers":{"type":"array","items":{"type":"string"}},"capabilities":{"type":"array","items":{"type":"string"}},"data_gaps":{"type":"array","items":{"type":"string"}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"review":{"type":"object","description":"What the readers made of the paper. A critique is a record of what the readers said and where they disagreed, so it is carried with its providers and its disagreements intact.","required":["state","machine_critique","human_critique","stages","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"machine_critique":{"type":["object","null"]},"human_critique":{"type":["object","null"]},"stages":{"type":"array","items":{"type":"object"}},"gaps":{"type":"array","items":{"type":"string"}}}},"execution":{"type":"object","description":"Whether the experiment was run. A record that has never been executed says so, rather than leaving it to be assumed.","required":["state","status","mode","runs","gaps"],"additionalProperties":false,"properties":{"state":{"enum":["absent","partial","complete","blocked"]},"status":{"type":["string","null"]},"mode":{"type":["string","null"]},"runs":{"type":"array","items":{"type":"object"}},"gaps":{"type":"array","items":{"type":"string"}}}},"provenance":{"type":"object","required":["entities","activities","agents","source_run_id"],"additionalProperties":false,"properties":{"entities":{"type":"array","items":{"type":"object"}},"activities":{"type":"array","items":{"type":"object"}},"agents":{"type":"array","items":{"type":"object"}},"source_run_id":{"type":["string","null"]},"dsl_catalogue_fingerprint":{"type":["string","null"]},"capability_table_fingerprint":{"type":["string","null"]},"snapshot_id":{"type":["string","null"]}}},"lineage":{"type":["object","null"],"additionalProperties":false,"properties":{"parent_id":{"type":["string","null"]},"parent_hash":{"type":["string","null"]},"fork_of":{"type":["string","null"]},"generation":{"type":["integer","null"]}}},"assays":{"type":"array","minItems":1,"description":"Every assay the experiment ran, in the order it ran them. An experiment is a set of processes and each process is an assay: the measurement, the analysis, the validation, the normalisation. Every binding here is required for the experiment as described; there is no primary assay and no optional one. A consumer that wants to run the experiment walks the list in order.","items":{"type":"object","additionalProperties":false,"anyOf":[{"required":["definition_id","definition_version"]},{"required":["definition"]},{"required":["request"]},{"required":["result"]}],"required":["id"],"properties":{"id":{"type":"string","minLength":1,"description":"This entry's identifier within the record. It is required, because a request or a result names it and a reference that may be missing is not a reference: with it, a consumer can say which assay it ran or produced."},"role":{"type":["string","null"],"description":"What this process is: the measurement, the analysis, the validation, the normalisation. Free text. It names the process; it does not make the process optional, because every assay in the list is required."},"order_basis":{"type":["string","null"],"description":"How this assay's place in the order was established: `paper_text_order:<offset>` when the paper's own text describes this process at that offset, `consumes_earlier_output` when it consumes what the earlier ones produced. Free text. The order of the list is the order of the experiment."},"depends_on":{"type":["array","null"],"items":{"type":"string","minLength":1},"description":"The assay entries of this document whose output this entry needs, named by their identifiers within this document. It is a statement about the experiment as it ran, and it is written, never inferred from the order of the array: an entry that states no dependency says so, and an ordered array does not say that each entry needs the one before it. A dependency names an entry in this document; it does not cross to another record, and the dependencies of a document do not form a cycle."},"definition_id":{"type":"string","minLength":1},"definition_version":{"type":"string","minLength":1},"definition_digest":{"type":["string","null"]},"required_operations":{"type":"array","items":{"type":"string"}},"support_state":{"enum":["supported","partial","unsupported","unknown"]},"source_hashes":{"type":"object","additionalProperties":{"type":"string"}},"confidence":{"type":["number","null"],"minimum":0,"maximum":1,"description":"How strongly the evidence supports this binding, in [0,1]. It is an evidence score, not a probability."},"evidence":{"type":"array","items":{"type":"string"},"description":"The passages of the paper that support this binding, so the binding can be checked against the paper's own text."},"definition":{"type":["object","null"],"description":"The assay definition this record belongs to, with the contract the record relies on. The definition itself is owned by the catalogue; this is the binding, not the catalogue.","additionalProperties":false,"required":["definition_id","definition_version"],"properties":{"definition_id":{"type":"string","minLength":1},"definition_version":{"type":"string","minLength":1},"definition_digest":{"type":["string","null"]},"required_operations":{"type":"array","items":{"type":"string"}},"support_state":{"enum":["supported","partial","unsupported","unknown"]},"input_contract":{"type":["object","null"]},"parameter_contract":{"type":["object","null"]},"output_contract":{"type":["object","null"]},"limitations":{"type":["array","null"],"items":{"type":"string"},"description":"The standing limitations of the operation: what it cannot establish, and the assumptions it rests on. The limitations live here and not in `analysis.methods[]` because that array forbids extra keys: an operation's limits are a property of the operation, and the catalogue owns the operation."},"interpretation":{"type":["string","null"],"description":"How a result of this assay should be read: what a reproduction of it would and would not show. Free text, written by the assay's owner."}}},"request":{"type":["object","null"],"description":"A request to run one operation against one source record. The source record id and the hash of its body bind the request to the version that was asked for.","additionalProperties":false,"required":["source_record_id","source_content_hash","operation","assay_id"],"properties":{"assay_id":{"type":"string","minLength":1,"description":"The identifier of the assay entry in the source document's `assays[]` that this request runs. Together with `source_content_hash` it says exactly which entry, in which version of the record, the request concerns."},"source_record_id":{"type":"string","minLength":1},"source_content_hash":{"type":"string","minLength":1},"operation":{"type":"string","minLength":1},"operation_version":{"type":["string","null"]},"inputs":{"type":"array","items":{"type":"object"}},"parameters":{"type":["object","null"]},"request_id":{"type":["string","null"]},"provider":{"type":["string","null"]}}},"result":{"type":["object","null"],"description":"The outcome of one request. The input, result and evidence hashes bind the outcome to the input it came from and to the evidence for it.","additionalProperties":false,"required":["execution_id","status","assay_id"],"properties":{"assay_id":{"type":"string","minLength":1,"description":"The identifier of the assay entry in the source document's `assays[]` that this result belongs to."},"operation":{"type":["string","null"],"description":"The operation this result is the result of. An assay entry may be run as more than one operation, so a result that does not say which operation produced it says less than the reader needs. From 1.4."},"provider":{"type":["string","null"]},"execution_id":{"type":"string","minLength":1},"input_hash":{"type":["string","null"]},"result_hash":{"type":["string","null"]},"evidence_hash":{"type":["string","null"]},"status":{"type":"string","minLength":1},"finding":{"type":["string","null"]},"result":{"type":["object","null"]}}},"operations":{"type":["array","null"],"items":{"type":"object","description":"One operation the assay may be run as, with the contract of that operation: what it takes, what it refuses and what it returns.","additionalProperties":false,"required":["operation"],"properties":{"operation":{"type":"string","minLength":1,"description":"The name of the operation. It is the name the owner of the catalogue publishes the operation under, so a consumer can look it up."},"operation_version":{"type":["string","null"],"description":"The version of the operation, when the owner publishes one. The name alone does not say which version of an operation was run."},"support_state":{"enum":["supported","partial","unsupported","unknown"],"description":"How well this operation can be run today. It is a property of this operation, and it can differ from the support state of the assay that contains it: an assay may be supported because one of its operations is."},"input_contract":{"type":["object","null"]},"parameter_contract":{"type":["object","null"]},"output_contract":{"type":["object","null"]},"limitations":{"type":["array","null"],"items":{"type":"string"},"description":"The standing limitations of this operation: what it cannot establish, and the assumptions it rests on. They live here and not in `analysis.methods[]` because that array forbids extra keys."},"interpretation":{"type":["string","null"],"description":"How a result of this operation should be read: what a reproduction of it would and would not show. Free text, written by the owner of the operation."}}},"description":"The operations this assay may be run as, each with the contract of that operation. An assay definition can implement several operations \u2014 a group comparison can be run as an analysis of variance, a rank-sum test or a t-test \u2014 and the definition is still one assay. The operations are stated inside the entry, one item each, so a request or a result can say which operation it concerns and a consumer can read that operation's own contract rather than a contract for whichever operation the emitter picked first. The array is optional: an entry that states no operations says nothing about how it may be run, which is not the same as stating that it may be run as nothing."}}}},"gaps":{"type":"array","items":{"type":"string"}}}},"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":"2026-11-04T14:24:55+00:00","generated_at":"2026-11-05T02:16:36+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\u2019s 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}}}