{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40789725", "kind": "science-record", "revision": 2, "content_hash": "sha256:b10fa7b81bb17c93f5a830a8ac62f4935642b453abd399718990611f68b7c887", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:45Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Clinical outcomes and interventions related to sedentary behaviours in childhood, adolescent, and young adult cancer patients and survivors: a scoping review protocol.", "doi": "10.1136/bmjopen-2025-100965", "pmid": "40789725", "authors": null, "journal": "BMJ open", "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:40789725"], "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:40789725", "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:40789725' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40789725", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1136/bmjopen-2025-100965", "sha256": "sha256:07ab07519681501b6f8f58cf469ea0b2b90cd81c74bac134a86d67bff2df42c3", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1136/bmjopen-2025-100965", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40789725:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:65d73c14193ffc8363e35e657db7036e4a1cd2cd4d564d39a210cfd638395465", "bytes": 2412, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T1", "version": null, "note": "Search strategy for PubMed", "structure": {"pmcid": "PMC12352156", "section_index": 5, "section_title": "Search strategy", "row_count": 4, "column_count": 2}, "table": {"label": "Table 1", "caption": "Search strategy for PubMed", "rows": [["Domain/concept", "Search terms"], ["Paediatrics", "“Child”[MeSH] OR “Adolescent”[MeSH] OR “Young Adult” [MeSH] OR “Minors” [MeSH] OR “Pediatrics” [MeSH] OR “Hospitals, Pediatric”[MeSH] OR “paediatric*” OR “toddler*” OR “preschool*” OR “pre school*” OR “child*” OR “kid” OR “kids” OR “juvenile*” OR “minor*” OR “youth*” OR “youngster*” OR “girl*” OR “boys” OR “boys” OR “elementary school*” OR “grade school*” OR “preadolescen*“ OR “pre adolescen*” OR “preteen*” OR “pre teen*” OR “middle school*” OR “adolescen*” OR “teen*” OR “high school*” OR “pediatric*” OR “young adult*”"], ["Cancer patients and survivors", "“Neoplasms” [MeSH] OR “Cancer Survivors” [MeSH] OR (“Neoplasms” [MeSH] AND “Survivors” [MeSH]) OR “oncolog*” OR “neoplas*”OR “tumor*” OR “tumour*” OR “cancer*” OR “malignan*” OR “metasta*” OR “carcinogenesis” OR “carcinoma*” OR “sarcoma*” OR “leukemia*” OR “leukaemia*” OR “lymphoma*” OR “Hodgkin* disease” OR “glioma*” OR “astrocytoma*” OR “craniopharyngioma*” OR “ependymoma*” OR “medulloblastoma*” OR “retinoblastoma*” OR “neuroblastoma*” OR “Langerhans cell histiocytosis” OR “hepatoblastoma” OR “cholangiocarcinoma” OR “nephroblastoma” OR “rhabdomyosarcoma*” OR “osteosarcoma*” OR “fibrosarcoma*” OR “melanoma*” OR “angiosarcoma*” OR “antineoplastic*” OR “anti-neoplastic*” OR “anti neoplastic*” OR “cancer survivor*”"], ["Sedentary behaviour", "“Sedentary Behavior” [MeSH] OR “Sitting Position” [MeSH] OR “sedentary” OR “sedentary behaviour*” OR “sedentary behavior*” OR “sedentary lifestyle*” OR “sedentarism” OR “sedentary time” OR “sitting” OR “inactiv* lifestyle*” OR “inactiv* behavi*” OR “lack of physical activit*” OR “physical inactive*” OR “television” OR “television viewing” OR “television time” OR “television watching” OR “TV viewing” OR “TV time” OR “TV viewing” OR “screen time” OR “computer use” OR “computer time” OR “video gam*”"]], "row_count": 4, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:40789725:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:617cb35bdaa4f29c8e7cc71362d901e4b6a39aee9435af18692c77fdd775aa74", "bytes": 3324, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T2", "version": null, "note": "Data charting table for observational studies", "structure": {"pmcid": "PMC12352156", "section_index": 8, "section_title": "Data extraction and charting", "row_count": 29, "column_count": 3}, "table": {"label": "Table 2", "caption": "Data charting table for observational studies", "rows": [["Data category", "Data item", "Description"], ["Study characteristics"], ["", "Author(s)", ""], ["", "Year of publication", ""], ["", "Country of study", ""], ["", "Study design", "Specify if study is cross-sectional, case-control, cohortor other study type."], ["", "Study duration", ""], ["Study objective(s)", "", "Describe the stated objective/aims of the study."], ["Sample characteristics"], ["", "Sample size", "List N for total number of participants, and if applicable, N for number of participants in each study group."], ["", "Age at study enrolment", "Specify mean age and range for the study sample if age is continuous variable or N, % for each age category if listed as categorical variable."], ["", "Sex", "Report N, % for each sex listed."], ["", "Race", "Report N, % for each race category listed."], ["", "Ethnicity", "Report N, % for each ethnicity category listed."], ["", "Other socioeconomic characteristics", "Specify any other reported sociodemographic characteristics, including income, parental education, insurance type, etc. List N, % for each reported category."], ["", "Age at cancer diagnosis", "Specify mean age and range for the study sample if age is continuous variable or N, % for each age category if listed as categorical variable."], ["", "Cancer diagnoses", "List each cancer type reported and specify N,% for each."], ["", "Treatment status", "Specify if participants were on or off treatment at the time of study completion. If mixed population, report N, % for both those on and off treatment."], ["Sedentary behaviour (SB) reporting"], ["", "Type of SB", "Specify which type of SB is being measured/reported with units, such as total sedentary time, screen time, sedentary breaks, etc."], ["", "Measurement method", "Specify if SB is measured via self-report, device measurement or both. If both, report which type of SB is measured by which method."], ["", "Summary SB data", "Report main SB data in mean and range if continuous and/or N, % if categorical."], ["Main study outcomes"], ["", "Cardiometabolic outcomes", "Specify any cardiometabolic outcomes reported with applicable units and measurement type, such as cardiorespiratory fitness, weight, body mass index, resting heart rate, glucose metabolism/insulin sensitivity, cholesterol levels, etc."], ["", "Patient-reported outcomes (PROs)", "Specify any PROs reported with measurement type, such as quality of life, fatigue, treatment-related symptoms, mood, etc."], ["", "Morbidity and survival-related outcomes", "Specify any morbidity or mortality-related outcomes reported with measurement type, such as number of chronic diseases, incidence of secondary malignancy, incidence of cardiac disease, all-cause mortality, cancer-related mortality, etc."], ["", "Other outcomes", "Describe any other study outcomes reported that are not included in the above categories. Specify measurement type and units, if applicable."], ["Covariates", "", "Specify covariates included in study analysis."], ["Study limitations", "", "List any limitations noted in the study discussion as well as those determined by reviewer including sample size, sample demographics, study type, confounding, potential biases, etc."]], "row_count": 29, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[8]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:40789725:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7963c75141e191a6f8978b1aa4c4f0cfdab3ed75885210db7d598d8ddc9ba969", "bytes": 2852, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[2]#T3", "version": null, "note": "Data charting table for interventional studies", "structure": {"pmcid": "PMC12352156", "section_index": 8, "section_title": "Data extraction and charting", "row_count": 28, "column_count": 3}, "table": {"label": "Table 3", "caption": "Data charting table for interventional studies", "rows": [["Data category", "Data item", "Description"], ["Study characteristics"], ["", "Author(s)", ""], ["", "Year of publication", ""], ["", "Country of study", ""], ["", "Study design", "Specify if study is a randomised controlled trial (RCT), cluster RCT, non-randomised trial, etc."], ["", "Study duration", ""], ["Study objectives", "", "Describe the stated objective/aims of the study."], ["Sample characteristics"], ["", "Sample size", "List N for total number of participants, and if applicable N for number of participants in each study group."], ["", "Age at study enrolment", "Specify mean age and range for the study sample if age is continuous variable or N, % for each age category if listed as categorical variable."], ["", "Sex", "Report N, % for each sex listed."], ["", "Race", "Report N, % for each race category listed."], ["", "Ethnicity", "Report N, % for each ethnicity category listed."], ["", "Other socioeconomic characteristics", "Specify any other reported sociodemographic characteristics, including income, parental education, insurance type, etc. List N, % for each reported category."], ["", "Age at cancer diagnosis", "Specify mean age and range for the study sample if age is continuous variable or N, % for each age category if listed as categorical variable."], ["", "Cancer diagnoses", "List each cancer type reported and specify N, % for each."], ["", "Treatment status", "Specify if participants were on or off treatment at the time of study completion. If mixed population, report N, % for both those on and off treatment."], ["Intervention characteristics"], ["", "Intervention type", "Specify how many intervention arms are included and the intervention components for each arm."], ["", "Intervention duration", ""], ["", "Intervention goals/aims", "Specific aims of the intervention, such as reducing total sedentary time, increase sedentary breaks, etc."], ["Sedentary behaviour (SB) measurement"], ["", "Type of SB", "Specify which type of SB is being measured/reported with units, such as total sedentary time, screen time, sedentary breaks, etc."], ["", "Measurement method", "Specify if SB is measured via self-report, device measurement or both. If both, report which type of SB is measured by which method."], ["Results", "", "Describe any within and/or between group-differences in SB reported as well as any other associated outcomes (physical activity, patient-reported outcomes, biomarkers, etc.)."], ["Covariates", "", "Describe covariates included in study analysis."], ["Study limitations", "", "List any limitations noted in the study discussion as well as those determined by reviewer including sample size, sample demographics, randomisation, confounding, potential biases, etc."]], "row_count": 28, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[8]/table-wrap[2]#T3"}}], "gaps": ["asset:source:pmid:40789725 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:40789725", "asset:table:pmid:40789725:1", "asset:table:pmid:40789725:2", "asset:table:pmid:40789725:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40789725"]}, "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": "feb83a8cae33fa654fb22db5bad3d7d786687da7b22cbf57f1d5a67ce354c904", "source_hash": "07ab07519681501b6f8f58cf469ea0b2b90cd81c74bac134a86d67bff2df42c3", "raw_response_sha256": "sha256:e9036ac98ac1ef128a1bb08429387632eacf31132cc0d9fb06b2464e3bbfe4a8", "raw_response_chars": 2447}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "742470c22470425b5c6f03c51bae9b17a1182aecb1db93e80ac4ea074ecbf434", "source_hash": "07ab07519681501b6f8f58cf469ea0b2b90cd81c74bac134a86d67bff2df42c3", "raw_response_sha256": "sha256:3c16d236513b66720e418593bd5761a79495588124808b9c91044527e5625496", "raw_response_chars": 32870}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "88fd145ea624060d1a2f6674a37ee792d56937d1f259690f87aa55a0e4dc0419", "source_hash": "07ab07519681501b6f8f58cf469ea0b2b90cd81c74bac134a86d67bff2df42c3", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The source text is a scoping review protocol and states that results are currently being summarised; it reports no numerical result for the registered target.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The source text is a scoping review protocol and states that results are currently being summarised; it reports no numerical result for the registered target.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:28:20.125400+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "53c5022dc1f04e6ff4f1a7ce002ef2c8362c01efa4f32f9b9ad4c2d96c86299e", "source_hash": "07ab07519681501b6f8f58cf469ea0b2b90cd81c74bac134a86d67bff2df42c3", "raw_response": "<think>We need answer JSON only. Need parse request. Need identify single numerical result replication of registered target has to reproduce; headline numerical result paper states for main finding. Source is protocol, no results, likely no number for registered target. Need set number_stated false, parent_value 0, unit/evidence empty, target_result say text does state instead. Need be careful schema, JSON valid. What does \"say in target_result what the text does state instead.\" We need formulate concise perhaps \"The text states that this is a scoping review protocol and that results are currently being summarised; it reports no headline numerical result.\" Evidence empty, unit empty, parent_value 0. Need perhaps mention registration URL? Since registered target maybe OSF link, but target asks headline numerical result. Source states no number. Could target_result be \"The source describes a scoping review protocol and states that database searches, article screening, and data extraction have been completed and results are currently being summarised; it does not state a headline numerical result.\" Need ensure no evidence quote requirement only if number. They explicitly if no number set ... leave unit and evidence empty, and say in target_result what text does state instead. Good.\n\nBut let's deeply consider ambiguity: There are numbers in text (five databases, ages, dates, 2025), but no result. Need not extract. \"registered target\" perhaps OSF registration and replication target? User likely benchmark designed to detect hallucination. Source protocol no numerical result. Return exact schema fields. JSON strings. parent_value number 0. number_stated false.\n\nNeed ensure target_result perhaps source wording with no number? \"The text states that the scoping review's database searches, article screening, and data extraction have been completed and that results are currently being summarised; no headline numerical result is stated.\" This paraphrases target_result permitted. Evidence empty string. unit empty string.\n\nCould quote exact source in target_result? They ask \"say in target_result what the text does state instead.\" Could state protocol status. Maybe exact quote useful, but evidence must empty according instruction. We can say \"The paper states: 'As of July 2025, database searches, article screening, and data extraction have been completed, and results are currently being summarised.' It does not state a headline numerical result.\" Does including July 2025 in target_result create issue? likely okay, but requested headline number only and no result. Better target_result: \"The source describes a scoping review protocol and states that results are currently being summarised; it does not state a headline numerical result.\" This says what text states instead but paraphrase. They said \"say ... what the text does state instead,\" no exact quote requirement in no-number branch except evidence empty. Could include quote, but target_result should perhaps mention protocol/aim. Need not overdo.\n\nLet's ensure output only JSON no markdown.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The source describes a scoping review protocol and states that results are currently being summarised; it does not state a headline numerical result.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The source describes a scoping review protocol and states that results are currently being summarised; it does not state a headline numerical result.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:28:22.094528+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "No headline numerical result is reported; the paper is a scoping review protocol whose results were still being summarised.", "minimax_alt": "No headline numerical result is reported in the supplied text; this is a scoping review protocol whose results were still being summarised.", "decisive": false}, "analysis_methods": {"minimax": ["Arksey and O’Malley scoping review methodology framework", "descriptive and quantitative summary of each study’s key characteristics and results", "study-specific quality assessment using established tools"], "minimax_alt": ["Arksey and O’Malley five-stage scoping review methodology framework", "Descriptive and quantitative summary of each study’s key characteristics and results", "Study-specific quality assessment using established tools"], "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:69d7910580da9e3beb1ebb020f2d5d28808134662ec3f0ee32d2f9d3d4be4503", "type": "sep_package", "label": "SEP v1 package for pmid:40789725"}], "activities": [{"id": "activity:conversion:pmid:40789725", "type": "conversion", "used": ["package:69d7910580da9e3beb1ebb020f2d5d28808134662ec3f0ee32d2f9d3d4be4503"], "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": "pmid:40789725", "parent_hash": "sha256:0a7c00ed6837fd54b5d9554c49bec195add35ebf2d468bc0e1f6d52b28f5ab6e", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40789725 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: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:40789725' 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":"2026-11-04T01:33:24+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}}}