{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35389773", "kind": "science-record", "revision": 4, "content_hash": "sha256:bdada790435d6aaad6b943312f8ab01d3fbc8dc9cd97ed2e579db874026d2639", "created_at": "2026-11-01T18:14:12Z", "updated_at": "2026-11-01T22:06:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Kinetochore-associated protein 1 promotes the invasion and tumorigenicity of cervical cancer cells via matrix metalloproteinase-2 and matrix metalloproteinase-9.", "doi": "10.1080/21655979.2022.2061144", "pmid": "35389773", "authors": ["Caimei Wang", "Yiyuan Wang", "Congrong Liu", "Xiaoyu Meng", "Zhongxia Hang"], "journal": "Bioengineered", "year": 2022, "abstract": "Cervical cancer, a common cancer in women, has become a serious social burden. Kinetochore-associated protein 1 (KNTC1) that regulates the cell cycle by regulating mitosis is related to the malignant behavior of different types of tumors. However, its role in the development of cervical cancer remains unclear. In this study, we initially explored the role of KNTC1 in cervical cancer. KNTC1 expression and relevant information were downloaded from The Cancer Genome Atlas (TCGA) and dataset GSE63514 in the Gene Expression Omnibus (GEO) database for bioinformatics analyses. Cell proliferation was detected by cell counting kit-8 (CCK8) and colony formation assays. Wound healing and Transwell assays were used to evaluate cell migration and invasion abilities. Protein expression levels of matrix metallopeptidase 2 (MMP2) and matrix metallopeptidase 9 (MMP9) were measured by western blotting. Nude mouse models of subcutaneous xenograft tumor were constructed to analyze tumor growth in vivo. CCK8 and colony formation assay results demonstrated that the proliferation rate of SiHa and C-33A cells decreased when KNTC1 was silenced. Western blot and Transwell assays indicated that KNTC1 knockdown weakened the invasion and migration abilities of SiHa and C-33A cells and decreased the expression of MMP-2 and MMP-9. In-vivo experiments suggested that the inhibition of KNTC1 reduced tumor growth. Taken together, our study showed that KNTC1 plays an important role in cervical cancer. Further, we verified the promotional effect of KNTC1 on cervical cancer through in-vivo and in-vitro experiments and speculated that KNTC1 might mediate tumor invasion via MMP9 and MMP2.", "claims": [{"id": "claim-method", "statement": "Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35389773", "locator": "sections[14] \"Bioinformatics results\" paragraph 2", "quote": "Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Cervical cancer GSE63514 series from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/) database was obtained using the GEOquery package to further organize and standardize the data [27]. Subsequently, the limma package was used for differential gene analysis [28], and the clusterProfiler package was used for gene ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis [29].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35389773", "locator": "sections[3] \"Bioinformatics analysis\" paragraph 2", "quote": "Cervical cancer GSE63514 series from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/) database was obtained using the GEOquery package to further organize and standardize the data [27]. Subsequently, the limma package was used for differential gene analysis [28], and the clusterProfiler package was used for gene ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis [29]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "KNTC1 expression was significantly higher in cervical cancer tumor tissue than in normal tissue, with a median difference of 2.694.", "kind": "quantitative", "target": {"value": 0.003, "unit": "p-value", "tolerance": null, "source": "Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f)."}, "evidence": [{"asset": "source:pmid:35389773", "locator": "sections[14] \"Bioinformatics results\" paragraph 2", "quote": "Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "KNTC1 expression was significantly higher in cervical cancer tumor tissue than in normal tissue, with a median difference of 2.694.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:35389773"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE63514"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE63514"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35389773", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/21655979.2022.2061144", "sha256": "sha256:c1f39eae86a06da65059d0622bc49b3b35f9cba9156b626292fb937ded38cf4e", "bytes": 31632, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/21655979.2022.2061144", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9161993", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE63514", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE63514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63514", "version": null, "note": "Cervical cancer GSE63514 series from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/) database was obtained using the GEOquery package to further organize and standardize the data [27]. Subsequently, the limma package was used for differential gene analysis [28], and the clusterProfiler package was used for gene ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis [29].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Cervical cancer GSE63514 series from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/) database was obtained using the GEOquery package to further organize and standardize the data [27]. Subsequently, the limma package was used for differential gene analysis [28], and the clusterProfiler package was used for gene ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis [29].", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1551311", "GSM1551312", "GSM1551313", "GSM1551314", "GSM1551315", "GSM1551316", "GSM1551317", "GSM1551318", "GSM1551319", "GSM1551320", "GSM1551321", "GSM1551322", "GSM1551323", "GSM1551324", "GSM1551325", "GSM1551326", "GSM1551327", "GSM1551328", "GSM1551329", "GSM1551330", "GSM1551331", "GSM1551332", "GSM1551333", "GSM1551334", "GSM1551335", "GSM1551336", "GSM1551337", "GSM1551338", "GSM1551339", "GSM1551340", "GSM1551341", "GSM1551342", "GSM1551343", "GSM1551344", "GSM1551345", "GSM1551346", "GSM1551347", "GSM1551348", "GSM1551349", "GSM1551350", "GSM1551351", "GSM1551352", "GSM1551353", "GSM1551354", "GSM1551355", "GSM1551356", "GSM1551357", "GSM1551358", "GSM1551359", "GSM1551360", "GSM1551361", "GSM1551362", "GSM1551363", "GSM1551364", "GSM1551365", "GSM1551366", "GSM1551367", "GSM1551368", "GSM1551369", "GSM1551370", "GSM1551371", "GSM1551372", "GSM1551373", "GSM1551374", "GSM1551375", "GSM1551376", "GSM1551377", "GSM1551378", "GSM1551379", "GSM1551380", "GSM1551381", "GSM1551382", "GSM1551383", "GSM1551384", "GSM1551385", "GSM1551386", "GSM1551387", "GSM1551388", "GSM1551389", "GSM1551390", "GSM1551391", "GSM1551392", "GSM1551393", "GSM1551394", "GSM1551395", "GSM1551396", "GSM1551397", "GSM1551398", "GSM1551399", "GSM1551400", "GSM1551401", "GSM1551402", "GSM1551403", "GSM1551404", "GSM1551405", "GSM1551406", "GSM1551407", "GSM1551408", "GSM1551409", "GSM1551410", "GSM1551411", "GSM1551412", "GSM1551413", "GSM1551414", "GSM1551415", "GSM1551416", "GSM1551417", "GSM1551418", "GSM1551419", "GSM1551420", "GSM1551421", "GSM1551422", "GSM1551423", "GSM1551424", "GSM1551425", "GSM1551426", "GSM1551427", "GSM1551428", "GSM1551429", "GSM1551430", "GSM1551431", "GSM1551432", "GSM1551433", "GSM1551434", "GSM1551435", "GSM1551436", "GSM1551437", "GSM1551438"], "sample_count": 128, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of cervical cancer progression", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE63514 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f)."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "bootstrap_mean_difference", "expected_value": 0.003, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.group_comparison_wilcoxon"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE63514"], "resolved_accessions": ["GSE63514"], "statements": ["Cervical cancer GSE63514 series from the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/) database was obtained using the GEOquery package to further organize and standardize the data [27]. Subsequently, the limma package was used for differential gene analysis [28], and the clusterProfiler package was used for gene ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis [29]."], "basis": "The paper names GSE63514 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:35389773", "data:geo:GSE63514"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE63514"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:40:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 9011, "completion_tokens": 1432, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:35389773", "type": "paper", "label": "pmid:35389773"}, {"id": "source:pmid:35389773", "type": "manuscript", "label": "PMID 35389773 full text"}, {"id": "data:geo:GSE63514", "type": "dataset", "label": "GEO GSE63514"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35389773", "type": "paper", "label": "pmid:35389773"}, {"id": "source:pmid:35389773", "type": "manuscript", "label": "PMID 35389773 full text"}, {"id": "data:geo:GSE63514", "type": "dataset", "label": "GEO GSE63514"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35389773", "type": "extraction", "used": ["source:pmid:35389773"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE63514", "type": "accession_resolution", "used": ["data:geo:GSE63514"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:35389773", "parent_hash": "sha256:28706246fb1e58bbbeb3971bef18e67a787bee62604347c017c8823f3a8267e4", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE63514 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["eration was detected by cell counting kit-8 (CCK8) and colony formation assays. Wound healing", "constructed to analyze tumor growth in vivo. CCK8 and colony formation assay results demonstra"], "order_basis": "paper_text_order:750", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["x metallopeptidase 9 (MMP9) were measured by western blotting. Nude mouse models of subcutaneous xenograft", "33A cells decreased when KNTC1 was silenced. Western blot and Transwell assays indicated that KNTC1 kn", "2 weeks of puromycin selection, qRT-PCR and western blotting were used to verify knockdown efficiency. An"], "order_basis": "paper_text_order:997", "id": "assay:2"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["mor were constructed to analyze tumor growth in vivo. CCK8 and colony formation assay results dem", "MP9) were measured by western blotting. Nude mouse models of subcutaneous xenograft tumor were", "ent Center of Xi’an Jiaotong University. The mice were randomly divided into two groups and shKNTC1", "width × width/2. Thirty days later, the nude mice were euthanized by cervical dislocation after bei"], "order_basis": "paper_text_order:1020", "id": "assay:3"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ot and Transwell assays indicated that KNTC1 knockdown weakened the invasion and migration abilitie", "Materials and methods Cell culture and transfection Cervical cancer cell lines SiHa and C-33A, a", "and right armpits of each group. SiHa cells transfected with the lentivirus were injected into the r", "PCR and western blotting were used to verify knockdown efficiency. Animals and treatment Six female"], "order_basis": "paper_text_order:1310", "id": "assay:4"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Procell (Wuhan, China). SiHa and C-33A were cultured in minimum essential medium containing 10% feta", "fetal bovine serum, and HcerEpic cells were cultured in complete medium for human cervical epithelia"], "order_basis": "paper_text_order:2016", "id": "assay:5"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Wilcoxon rank sum test results showed that the expression level of KNTC1 in tumor group was higher than normal, and the median difference between the two groups was 2.694 (2.081–3.311), which was statistically significant (P = 0.003) (figure 1f)."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T02:16:37+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}}}