{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41511578", "kind": "science-record", "revision": 2, "content_hash": "sha256:9ac8e522f7759efad7c90797fdd70c22af0b20f7be695ae751c3d11eda9c1193", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "The subtype identification of colorectal cancer and construction of the risk model based on cholesterol synthesis-related genes to predict prognosis and guide immunotherapy.", "doi": "10.1007/s00384-025-05067-6", "pmid": "41511578", "authors": null, "journal": "International journal of colorectal disease", "year": 2026, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 10.0, "unit": "genes", "tolerance": null, "source": "chars 1191-1269 of source sha256 c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f"}, "evidence": [{"asset": "source:pmid:41511578", "locator": "chars 1191-1269 of source sha256 c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "quote": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed."}]}], "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:41511578"], "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:41511578", "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:41511578' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41511578", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s00384-025-05067-6", "sha256": "sha256:c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s00384-025-05067-6", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41511578:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7bb1a4eafc1dcb0672df62e93d7c04b86b0242cc9804655d3cf91b65e8dfd475", "bytes": 351, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#Tab1", "version": null, "note": "qPCR primer sequences", "structure": {"pmcid": "PMC12789220", "section_index": 16, "section_title": "qRT-PCR", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "qPCR primer sequences", "rows": [["Gene", "Forward primer (5′−3′)", "Reverse primer (5′−3′)"], ["EEF1A2", "GGCCACCTCATCTACAAATG", "TCGAACTTCCAGAGGGAGAT"], ["GAPDH", "CGGGAAGCTTGTCATCAAT", "TCTCCATGGTGGTGAAGA"]], "row_count": 3, "column_count": 3, "numeric_cells": 2, "header_rows": 1, "locator": "section[16]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:41511578:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9c42e09436b00121691b68bfda7de252cdf98adea47ec425c7598449aa61797d", "bytes": 387, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[1]#Tab2", "version": null, "note": "Comparison of the distribution relationship between clustering and CMS subtypes", "structure": {"pmcid": "PMC12789220", "section_index": 23, "section_title": "Consensus cluster analysis and construction of PPI network based on CSRGs", "row_count": 4, "column_count": 5}, "table": {"label": "Table 2", "caption": "Comparison of the distribution relationship between clustering and CMS subtypes", "rows": [["Cluster", "CMS1", "CMS2", "CMS3", "CMS4"], ["1", "20.4%", "26.4%", "13.0%", "40.3%"], ["2", "18.8%", "45.1%", "23.3%", "12.8%"], ["Total", "19.8%", "33.5%", "16.9%", "29.8%"]], "row_count": 4, "column_count": 5, "numeric_cells": 14, "header_rows": 1, "locator": "section[23]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:41511578:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fa18deb03b0c9dbbb4ce21fb548d0a46f9da487fd9d57a82f293627983f2e898", "bytes": 345, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[2]#Tab3", "version": null, "note": "Comparison of the distribution relationship between clustering and MSI", "structure": {"pmcid": "PMC12789220", "section_index": 23, "section_title": "Consensus cluster analysis and construction of PPI network based on CSRGs", "row_count": 4, "column_count": 4}, "table": {"label": "Table 3", "caption": "Comparison of the distribution relationship between clustering and MSI", "rows": [["Cluster", "MSI-H", "MSI-L", "MSS"], ["1", "12.0%", "12.0%", "75.9%"], ["2", "9.8%", "5.3%", "85.0%"], ["Total", "11.2%", "9.5%", "79.4%"]], "row_count": 4, "column_count": 4, "numeric_cells": 11, "header_rows": 1, "locator": "section[23]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:41511578:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ebd3d91384ba879aa0a0b41b3b6fa37528cc85b88f0b4716b28435dfd045e245", "bytes": 580, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[3]#Tab4", "version": null, "note": "Post-adjustment logistic regression analysis was used to evaluate the relationship between CMS subtypes and MSI status and clustering classification", "structure": {"pmcid": "PMC12789220", "section_index": 23, "section_title": "Consensus cluster analysis and construction of PPI network based on CSRGs", "row_count": 7, "column_count": 3}, "table": {"label": "Table 4", "caption": "Post-adjustment logistic regression analysis was used to evaluate the relationship between CMS subtypes and MSI status and clustering classification", "rows": [["Term", "OR (95% CI)", "P-value"], ["(Intercept)", "0.790(0.390–1.570)", "0.496"], ["CMS2", "1.360(0.630–2.970)", "0.435"], ["CMS3", "1.500(0.660–3.420)", "0.330"], ["CMS4", "0.270(0.120–0.620)", "0.002"], ["MSI-H", "0.640(0.250–1.560)", "0.330"], ["MSI-L", "0.500(0.180–1.240)", "0.152"]], "row_count": 7, "column_count": 3, "numeric_cells": 13, "header_rows": 1, "locator": "section[23]/table-wrap[3]#Tab4"}}, {"id": "asset:table:pmid:41511578:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ec94dd11eb232ffcd76c44ca93d910b7ff2378d8177a291af34a4847074a6f97", "bytes": 329, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#Tab5", "version": null, "note": "Time-dependent AUC after bootstrap optimism bias correction", "structure": {"pmcid": "PMC12789220", "section_index": 24, "section_title": "The construction and validation of CSRRS as well as the assessment of its independent prognostic value", "row_count": 4, "column_count": 3}, "table": {"label": "Table 5", "caption": "Time-dependent AUC after bootstrap optimism bias correction", "rows": [["Time (year)", "AUC", "95%CI"], ["1", "0.713", "0.591–0.833"], ["3", "0.743", "0.644–0.842"], ["5", "0.675", "0.514–0.824"]], "row_count": 4, "column_count": 3, "numeric_cells": 10, "header_rows": 1, "locator": "section[24]/table-wrap[1]#Tab5"}}], "gaps": ["asset:source:pmid:41511578 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:41511578", "asset:table:pmid:41511578:1", "asset:table:pmid:41511578:2", "asset:table:pmid:41511578:3", "asset:table:pmid:41511578:4", "asset:table:pmid:41511578:5"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41511578"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "ac0b236318f3cfcee32bcdfbb2b3a0b3560cf68bb6ffb570c4049f16c6bcb3d2", "source_hash": "c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "raw_response_sha256": "sha256:ee03d185035d5bb70dcc02883d11e2f4e58b7a35b0e81b9c1ea64dbd17577ac0", "raw_response_chars": 5950}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "62940d86060f00badfbdf2434a0632680552b6664d2a5e693edc7b100b90f7b9", "source_hash": "c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "raw_response_sha256": "sha256:6bc14cb238994dad334ecf8b51f129ec0f9a5cbf13fe01c8e19c6aabcb20ff67", "raw_response_chars": 65453}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "ca353d4ff266e6952f9a30ced80fb03561a885ae59d40bf542737cdaefbae7ef", "source_hash": "c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "raw_response": "{\"parent_value\":10,\"unit\":\"genes\",\"evidence\":\"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\",\"target_result\":\"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\",\"number_stated\":true}", "reading": {"parent_value": 10, "unit": "genes", "evidence": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.", "target_result": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.", "number_stated": true, "source_locator": "chars 1191-1269 of source sha256 c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f"}, "recorded_at": "2026-10-31T15:27:41.626278+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "a0583402ffb03c9b3344d96b605e3cec9e492b6b1d2533133808490a9db7d720", "source_hash": "c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for main finding / registered target. Source abstract says 10-gene signature constructed. Is that headline numerical result? Likely yes: \"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\" Replication target headline numerical result paper states. Need value 10, unit perhaps \"genes\" because printed wording 10-gene. Evidence exact contiguous quote. Could perhaps target is main finding as risk model? No performance metric (AUC, HR) absent. Headline numerical result likely 10-gene CSRS. Need report headline number only and unit paper prints. Unit maybe \"genes\". Evidence exact sentence. target_result likely \"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\" Number stated true, parent_value 10, unit \"genes\". Ensure JSON valid unicode. They insist evidence exact contiguous quotation contains number; quote whole clause attribution. Could evidence be \"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\" Exact source. Target_result same perhaps. \"headline number only\" perhaps target_result textual. Schema asks. Need not quote larger. Use exact sentence.\n\nPotential ambiguity: 2 subtypes, 10 gene risk signature. Registered target \"headline numerical result the paper states for its main finding\". Main finding could 10 gene signature. \"headline numerical result\" likely extraction benchmark where source lacks clear metric? They may expect 10 and genes. Let's deeply assess.\n\nPaper title: subtype identification and risk model. Abstract results: divided into two subtypes; A 10-gene signature constructed; high group poorer prognosis; EEF1A2 etc. The replication of registered target has to reproduce \"the headline numerical result paper states for its main finding\". Maybe target is specifically main finding and wants a singular number. Could be 10-gene signature. Other headline number: two subtypes. Which is headline? Wording says \"single numerical result that a replication of the registered target has to reproduce.\" Registered target generic. \"headline numerical result the paper itself states for the registered target\" We need identify main result likely number of genes in risk signature. The title \"construction of risk model based on cholesterol synthesis-related genes\"; abstract explicitly \"A 10-gene ... Risk Signature ... was constructed.\" This is likely intended.\n\nUnit exact printed? \"10-gene\" means unit could be \"genes\". They ask \"unit must be the unit the paper prints.\" The printed unit is \"gene\" adjectivally, likely unit \"genes\". Maybe value 10, unit \"gene\". Need decide. Usually these tasks expect numerical value and unit as textual, e.g. 10 genes. We can use \"genes\". Evidence exact sentence.\n\ntarget_result maybe \"The study constructed a 10-gene Cholesterol Synthesis-related Risk Signature (CSRS).\" This paraphrases perhaps okay in field. Evidence exact. \"Report headline number only\" perhaps target_result should simply describe. JSON.\n\nLet's ensure no extra properties.</think>\n\n{\"parent_value\":10,\"unit\":\"genes\",\"evidence\":\"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\",\"target_result\":\"A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.\",\"number_stated\":true}", "reading": {"parent_value": 10, "unit": "genes", "evidence": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.", "target_result": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.", "number_stated": true, "source_locator": "chars 1191-1269 of source sha256 c6a932a4b7150c3d8f27a54e73036392e871d485c366e1e98bd0f35322fa666f"}, "recorded_at": "2026-10-31T15:27:45.607065+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed.", "minimax_alt": "A 10-gene Cholesterol Synthesis-related Risk Signature (CSRS) was constructed for CRC prognosis, and patients in the high-CSRS group had a poorer prognosis.", "decisive": false}, "analysis_methods": {"minimax": ["univariate Cox regression analysis", "consensus clustering", "PPI network analysis", "regression analysis", "ROC curve analysis", "Kaplan–Meier survival analysis", "differential expression analysis", "GO enrichment analysis", "KEGG enrichment analysis", "immune infiltration analysis", "drug sensitivity analysis", "mutational waterfall plot analysis"], "minimax_alt": ["univariate Cox regression analysis", "consensus clustering using the ConsensusClusterPlus R package", "differential expression analysis using the edgeR package", "PPI network analysis using STRING", "multivariate logistic regression analysis", "ROC curve analysis", "Kaplan–Meier survival analysis", "KEGG and Gene Ontology enrichment analysis using clusterProfiler", "ssGSEA using the GSVA R package", "xcell algorithm", "immunophenoscore (IPS) and Tumor Immune Dysfunction and Exclusion (TIDE) analysis", "mutation analysis using maftools", "CellMiner and GDSC-related drug-sensitivity analysis", "oncoPredict algorithm", "t-test for comparisons between two groups in wet experiments"], "decisive": false}, "statistical_method": {"minimax": "univariate Cox regression analysis", "minimax_alt": "Univariate Cox regression analysis for prognostic gene screening and Kaplan–Meier survival analysis for the prognosis comparison", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:0b3890d25f030fdb5988c24039945d370257e9edfef41683b3981e9bda8ff8b1", "type": "sep_package", "label": "SEP v1 package for pmid:41511578"}], "activities": [{"id": "activity:conversion:pmid:41511578", "type": "conversion", "used": ["package:0b3890d25f030fdb5988c24039945d370257e9edfef41683b3981e9bda8ff8b1"], "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:41511578", "parent_hash": "sha256:d884fe490c724e835a2a1351f2501bb30bf659ba6d466ffc7c48f423ff608042", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41511578 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41511578' 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":"2026-11-04T02:46:38+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}}}