{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40679719", "kind": "science-record", "revision": 2, "content_hash": "sha256:4513f0cff6bdedfebb9920cbe762efa2fecd91df1f2e902382e8c60026f24b20", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Identification of biomarkers for Laryngeal squamous cell carcinoma through Mendelian randomization and integrated bioinformatics analysis.", "doi": "10.1007/s12672-025-03114-w", "pmid": "40679719", "authors": null, "journal": "Discover oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 0.857, "unit": "auc", "tolerance": null, "source": "chars 1947-2123 of source sha256 812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7"}, "evidence": [{"asset": "source:pmid:40679719", "locator": "chars 1947-2123 of source sha256 812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "quote": "The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively."}]}], "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:40679719"], "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:40679719", "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:40679719' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40679719", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-03114-w", "sha256": "sha256:812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-03114-w", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40679719:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dbfbb4f905566c0e5abb4f349cb4e502e840fd7d1665313c566074e66b434f5d", "bytes": 1087, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab1", "version": null, "note": "Primer sequences for qRT-PCR", "structure": {"pmcid": "PMC12274188", "section_index": 18, "section_title": "Experimental methods", "row_count": 21, "column_count": 3}, "table": {"label": "Table 1", "caption": "Primer sequences for qRT-PCR", "rows": [["Primers", "Sequence (5ʹ → 3ʹ)"], ["PMAIP1 (116 bp)", "Forward", "GTACGGCGGAGCTGGAA"], ["Reverse", "TCAGGTTCCTGAGCAGAAGA"], ["GATA3 (119 bp)", "Forward", "CCTCAGCCACTCCTACATGG"], ["Reverse", "CCCTGACCGAGTTTCCGTAG"], ["TIMP1 (152 bp)", "Forward", "GCGGATACTTCCACAGGTCC"], ["Reverse", "GTAGGTCTTGGTGAAGCCCC"], ["TIMP2 (106 bp)", "Forward", "AAGAACATCAACGGGCACCA"], ["Reverse", "CGAGAAACTCCTGCTTGGGG"], ["DNAJC3 (118 bp)", "Forward", "AGGAGAGGATTTGCCACTGC"], ["Reverse", "TCTGCTCGATCTTTCAGGGC"], ["NLRP3 (113 bp)", "Forward", "AGAAGCTCTGGTTGGTCAGC"], ["Reverse", "CAAGGCATTCTCCCCCACAT"], ["TNFRSF1B (148 bp)", "Forward", "CCGGGAGCTCAGATTCTTCC"], ["Reverse", "TCCTTGGAGAAGGGGACCTG"], ["FUNDC1 (120 bp)", "Forward", "AAACGAGCGAACAAAGCAGC"], ["Reverse", "TGCAAGTCCGAGCAAAAAGC"], ["TGFB2 (200 bp)", "Forward", "CAGCTTGTGCTCCAGACAGT"], ["Reverse", "GCTCAATCCGTTGTTCAGGC"], ["GAPDH (168 bp)", "Forward", "ATGGGCAGCCGTTAGGAAA"], ["Reverse", "CGCCCAATACGACCAAATC"]], "row_count": 21, "column_count": 3, "numeric_cells": 11, "header_rows": 1, "locator": "section[18]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:40679719:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bef22ee4cd9339ec9c32adada4b2d96a88d75e420132665e31915a7eee74b1aa", "bytes": 285, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#Tab2", "version": null, "note": "MR analysis results", "structure": {"pmcid": "PMC12274188", "section_index": 21, "section_title": "Construction of the prognostic model for LSCC", "row_count": 2, "column_count": 5}, "table": {"label": "Table 2", "caption": "MR analysis results", "rows": [["Exposure", "Method", "nSNP", "p value", "OR (95% CI)"], ["GATA3", "Wald ratio", "1", "0.04434", "1.0016 (1.0000–1.0032)"]], "row_count": 2, "column_count": 5, "numeric_cells": 4, "header_rows": 1, "locator": "section[21]/table-wrap[1]#Tab2"}}], "gaps": ["asset:source:pmid:40679719 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:40679719", "asset:table:pmid:40679719:1", "asset:table:pmid:40679719:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40679719"]}, "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": "9d7619433275d03ea57fec549614145357de0ee1f3a72694e926e73b83134db0", "source_hash": "812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "raw_response_sha256": "sha256:9ec1035929e4fd3d841d6c8d2e8904d9d4a116ec2418fbc470b05fe4cc4ea39a", "raw_response_chars": 4139}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "921b0133e4f06012d472cd76670964ade3e17db218ed532b2cce892e571696af", "source_hash": "812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "raw_response_sha256": "sha256:c5b611285b254db436d19763e9d0523bc3dd3bd05bed123ae55019445eb4df39", "raw_response_chars": 55714}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "59fd10a67e9b87d58689a79af297e3be42b75cf924776a65332fca299d9b9ac3", "source_hash": "812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "raw_response": "{\"parent_value\":0.857,\"unit\":\"AUC\",\"evidence\":\"The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\",\"target_result\":\"The prognostic model's AUC in the validation set was 0.857.\",\"number_stated\":true}", "reading": {"parent_value": 0.857, "unit": "AUC", "evidence": "The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.", "target_result": "The prognostic model's AUC in the validation set was 0.857.", "number_stated": true, "source_locator": "chars 1947-2123 of source sha256 812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7"}, "recorded_at": "2026-10-31T15:21:45.482737+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "ad11df5bb1a3f67a0373fa45983cc7dcd56896ffbc0e77b50eb0ce642bc73818", "source_hash": "812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for registered target main finding. Need infer likely headline number from abstract/results: AUC values 0.769 training, 0.857 validation respectively. \"single numerical result that a replication ... has to reproduce\" Registered target: headline numerical result paper states for its main finding. Which number? Could be 0.857 validation headline? Need parse task wording. Need select one numerical result likely \"headline number\" in paper, perhaps target corresponds to main finding metric. Text states AUC 0.769 and 0.857 in training and validation, respectively. But asks single numerical result. Maybe registered target intentionally generic, wants paper's headline result. Need choose likely 0.857? Need understand benchmark. They provide source and target description. \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". Main finding constructed prognostic model robust predictive power, AUC values training/validation. There are two values, but headline perhaps validation AUC 0.857, more salient. Yet task says \"single numerical result that a replication ... has to reproduce\" and \"Report headline number only: value paper itself states for registered target\". Could target perhaps numerical finding based on title? Need inspect abstract: 114 training, 270 validation; 33 DE genes; 9-gene model; AUC 0.769 and 0.857. Which is \"headline numerical result\"? Likely 0.857 as main headline performance. They may expect unit perhaps \"AUC\" (paper prints area under curve (AUC), dimensionless). Evidence exact contiguous quote containing number, quote whole clause attribution. Could quote: \"The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\" But if number selected 0.857, parent_value 0.857, unit \"AUC\". Evidence whole sentence. Yet \"headline number only\" maybe number field only. Unit must unit paper prints. Could unit be \"AUC\" or perhaps no unit? Source doesn't print \"AUC = 0.857\"; says area under curve (AUC) values. Unit should be \"AUC\" probably.\n\nNeed decide whether number_stated true. target_result string perhaps explain \"Validation-set area under the curve (AUC) was 0.857.\" Evidence exact quote. JSON no markdown.\n\nBut let's deeply consider benchmark semantics. They might expect a specific number, perhaps 0.769? \"headline numerical result the paper states for its main finding\" Usually extraction asks identify a parent metric. \"Registered target\" generated broad label. Main finding = prognostic model's predictive accuracy. Two cohort AUC values. Which is headline? Perhaps first listed training AUC 0.769 is the result tied to primary target; validation 0.857 is validation. Replication of registered target perhaps registered target is \"headline numerical result the paper states for its main finding\", and should report headline number only. Abstract headline may be validation AUC? Let's inspect wording: \"with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\" Both are main model results. They insist single numerical result. Usually benchmark has a target value, perhaps they expect \"0.857\" because highest/headline. Need infer from task design.\n\nCould be target specifically asks \"the headline numerical result the paper states for its main finding\" and source abstract. In papers, headline result often sample count? Main finding is biomarkers/prognostic model, headline metric AUC. Two values. Maybe target could be \"0.769\" if training result and \"0.857\" if validation. But no cohort specified, ambiguity. Their instruction anticipates attribution by respectively, requiring quote whole clause. It may ask to extract one result with exact quote. Maybe the registered target refers to a hidden \"parent\" selected by system, but phrase broad. We need choose.\n\nCould target_result perhaps say both? But asks single number and parent_value number only. Can't report both. Could perhaps number 0.857 because validation is more headline than training. Let's search conceptual context from title \"Identification of biomarkers for Laryngeal squamous cell carcinoma through Mendelian randomization and integrated bioinformatics analysis\". The abstract states sample sizes and AUC. A replication target likely main performance metric. In benchmark tasks, target often asks e.g. \"headline effect size for primary outcome\" and source may list training/validation. If no explicit \"primary\", likely use final/validation number. Could evidence be full clause.\n\nLet's inspect phrase \"a replication of the registered target has to reproduce.\" Maybe generated benchmark where \"registered target\" describes a numeric claim. They emphasize no calculation, conversion, average/reconstruction. \"the headline numerical result the paper states for its main finding.\" Usually paper's abstract conclusion mentions robust predictive power with AUC values 0.769 and 0.857. Maybe expected result is actually \"0.857\" because that's max AUC / headline. The training AUC is setup, validation is replication headline. A replication would reproduce validation AUC 0.857. Likely.\n\nNeed make evidence exact contiguous quote. Full sentence exactly:\n\"The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\"\nThis contains number and attribution. Fine.\n\nunit: \"AUC\" (paper prints AUC). Could it be no unit? Schema string and instruction unit must unit paper prints. Use \"AUC\". target_result maybe \"The prognostic model's validation-set area under the curve (AUC) was 0.857.\" Does target_result need say what paper states instead only if false? Can still summarize true result. They ask headline number only perhaps target_result should be concise. Maybe target_result: \"Validation-set AUC of 0.857 for the constructed prognostic model.\" Good.\n\nCould parent_value be 0.857, evidence whole clause. number_stated true. JSON valid.\n\nLet's ensure no issue \"headline number only\" perhaps don't include 0.769 in evidence? But evidence exact clause naturally contains both due to attribution requirement. They explicitly say if attached by respectively, quote whole clause. So okay. \"Report headline number only\" refers parent_value, likely.\n\nMaybe evidence should include entire sentence from abstract; exact contiguous. Ensure source punctuation. \"The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\" Exact. Unit \"AUC\" perhaps dimensionless, but paper uses area under curve (AUC). Could write \"area under the curve (AUC)\" exact printed unit phrase. They say unit must be unit paper prints. Use \"AUC\". Headline number 0.857.\n\nNeed output only JSON object.</think>\n\n{\"parent_value\":0.857,\"unit\":\"AUC\",\"evidence\":\"The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.\",\"target_result\":\"The constructed prognostic model achieved a validation-set AUC of 0.857.\",\"number_stated\":true}", "reading": {"parent_value": 0.857, "unit": "AUC", "evidence": "The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.", "target_result": "The constructed prognostic model achieved a validation-set AUC of 0.857.", "number_stated": true, "source_locator": "chars 1947-2123 of source sha256 812cd23dc5b06f68367253cd5c9909f5f04a1187bbf95b89fc46a97d4e13d3d7"}, "recorded_at": "2026-10-31T15:21:55.986475+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The constructed prognostic model had area under the curve (AUC) values of 0.769 in the TCGA-HNSC training set and 0.857 in the GSE65858 validation set.", "minimax_alt": "The constructed prognostic model exhibited robust predictive power, with area under the curve (AUC) values of 0.769 and 0.857 in the training and validation sets, respectively.", "decisive": false}, "physical_methods": {"minimax": ["qRT-PCR experiments using the 2⁻ΔΔCt method"], "minimax_alt": ["qRT-PCR experiments", "2⁻ΔΔCt method"], "decisive": false}, "analysis_methods": {"minimax": ["Lasso–Cox regression", "Kaplan–Meier analysis", "receiver operating characteristic (ROC) curves", "limma differential expression analysis", "Gene Ontology enrichment analysis", "KEGG enrichment analysis", "Metascape enrichment analysis", "CIBERSORT", "oncoPredict", "pseudotime analysis", "gene set scoring", "Mendelian randomization"], "minimax_alt": ["limma differential expression analysis with lmFit and eBayes", "Benjamini–Hochberg p-value adjustment", "maftools tumor mutation burden analysis", "GO, KEGG, and Metascape enrichment analyses", "clusterProfiler enrichment analysis", "fgsea gene set enrichment analysis", "Seurat single-cell RNA-seq preprocessing", "PCA and t-SNE dimensionality reduction", "Harmony batch-effect correction", "singleR cell-type annotation", "CellChat cell–cell communication analysis", "monocle2 pseudotime analysis", "AUCell, UCell, singscore, GSVA, AddModuleScore, and irGSEA gene-set scoring", "DoRothEA transcription factor activity analysis", "Lasso–Cox prognostic modeling", "Kaplan–Meier analysis", "receiver operating characteristic (ROC) curves", "CIBERSORT immune-cell deconvolution", "oncoPredict drug-sensitivity analysis", "TwoSampleMR Mendelian randomization using IVW, MR-Egger, weighted median, and weighted mode", "Cochran’s Q test and I2 statistic", "Wilcoxon test", "Spearman’s correlation coefficient"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic (ROC) curve analysis", "minimax_alt": "receiver operating characteristic (ROC) curves", "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:2ef9f9a3c13948e9ca067ba29e9b950b0bcaf9b034261ecfc2b6da9c25a57c7c", "type": "sep_package", "label": "SEP v1 package for pmid:40679719"}], "activities": [{"id": "activity:conversion:pmid:40679719", "type": "conversion", "used": ["package:2ef9f9a3c13948e9ca067ba29e9b950b0bcaf9b034261ecfc2b6da9c25a57c7c"], "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:40679719", "parent_hash": "sha256:a9f17bfd047b44789d3999b354e225e82df4a51f0919f4565dbc9527425df8f9", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40679719 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:40679719' 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":"2026-11-04T01:33:18+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}}}