{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35213063", "kind": "science-record", "revision": 2, "content_hash": "sha256:98b1fd0afe0a7055541f11f6ef34ee4a951bd38ebeee16d5b7a7c32614ebab80", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:31Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Predicting Mohs surgery complexity by applying machine learning to patient demographics and tumor characteristics", "doi": "10.1111/exd.14550", "pmid": "35213063", "authors": null, "journal": "Experimental Dermatology", "year": 2022, "abstract": null, "claims": [{"id": "claim-1", "statement": "the area under the receiver operating characteristic curve of the Mohs surgery stage-count complexity classifier", "kind": "quantitative", "state": "complete", "target": {"value": 0.79, "unit": "auroc", "tolerance": null, "source": "chars 1077-1381 of source sha256 0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0"}, "evidence": [{"asset": "source:pmid:35213063", "locator": "chars 1077-1381 of source sha256 0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "quote": "For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance), with model accuracy of 77%, sensitivity of 71%, specificity of 77%, positive prediction value (PPV) of 14% and negative prediction value (NPV) of 98%."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the area under the receiver operating characteristic curve of the Mohs surgery stage-count complexity classifier", "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:35213063"], "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:accession_absent", "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": "method:diagnostic_evaluation_roc", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the analysis programme that recomputes the published estimate"], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": ["the source data behind pmid:35213063, which the paper says are available from the authors on request", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:diagnostic_evaluation_roc"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35213063", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/exd.14550", "sha256": "sha256:0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/exd.14550", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind pmid:35213063, which the paper says are available from the authors on request", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "restricted", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind pmid:35213063, which the paper says are available from the authors on request", "structure": {"material_kind": "dataset", "access_state": "restricted"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "data:availability", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "The data that support the findings of this study are available from the corresponding author upon reasonable request.", "structure": {"access_route": "request_on_author", "location": "section [data-availability-statement]: Data Availability Statement"}}, {"id": "asset:table:pmid:35213063:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:980472143db1c5bfcc93becb7383d1f528aa4ba06e93b4904758bfb49110cbfd", "bytes": 852, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#exd14550-tbl-0001", "version": null, "note": "Participant demographics, preoperative tumor evaluation characteristics and surgical outcomes", "structure": {"pmcid": "PMC9543558", "section_index": 6, "section_title": "RESULTS", "row_count": 18, "column_count": 2}, "table": {"label": "TABLE 1", "caption": "Participant demographics, preoperative tumor evaluation characteristics and surgical outcomes", "rows": [["Feature", "Total"], ["Demographics", "(n = 8644)"], ["Age, years, mean ± SD", "69 ± 13"], ["Gender, male, n (%)", "4725 (55)"], ["Tumor size, mm, mean ± SD", "12 ± 6"], ["Tumor characteristics"], ["Pigmented, n (%)", "739 (8.5)"], ["Ulcerated, n (%)", "1478 (17)"], ["Keratinized, n (%)", "1477 (17.1)"], ["Scarred, n (%)", "712 (8.2)"], ["Regular borders, n (%)", "5776 (66.8)"], ["Tumor topography"], ["Flat, n (%)", "1207 (14)"], ["Elevated, n (%)", "4241 (49)"], ["Mixed, n (%)", "3196 (37)"], ["Procedure outcome"], ["MMS stages > 2, n (%)", "479 (5.5)"], ["Skin graft/flap wound reconstruction, n (%)", "1379 (16)"]], "row_count": 18, "column_count": 2, "numeric_cells": 15, "header_rows": 1, "locator": "section[6]/table-wrap[1]#exd14550-tbl-0001"}}, {"id": "asset:table:pmid:35213063:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:98880af04d5ef99610cb7fb127a9012a0ff6c20482760875484d21a5554cdcd3", "bytes": 611, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#exd14550-tbl-0002", "version": null, "note": "Complexity classification models: the marginal contribution of each feature in the model", "structure": {"pmcid": "PMC9543558", "section_index": 6, "section_title": "RESULTS", "row_count": 7, "column_count": 3}, "table": {"label": "TABLE 2", "caption": "Complexity classification models: the marginal contribution of each feature in the model", "rows": [["Feature", "Stage complexity classification model's modified MCI (AUROC)", "Wound reconstruction complexity classification model's modified MCI (AUROC)"], ["Tumor location", "0.2073", "0.3592"], ["Gender", "0.0125", "0.0214"], ["Age", "0.0086", "0.0510"], ["Tumor size", "0.0274", "0.1212"], ["Tumor topography", "0.1897", "0.1244"], ["Tumor characteristics", "0.2611", "0.1614"]], "row_count": 7, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[6]/table-wrap[2]#exd14550-tbl-0002"}}], "gaps": ["asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:35213063, which the paper says are available from the authors on request not verified", "asset:source:pmid:35213063 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "diagnostic_evaluation", "specific": "receiver operating", "label": "Diagnostic test evaluation", "dsl_operations": [], "missing_operations": ["diagnostic_evaluation_roc"], "expressible": false, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "The dataset was shuffled and divided to train and test datasets, 90% of the data were allocated to training and 10% were allocated to testing. The models were created using the training dataset for a 10‐fold cross‐validation. We used a gradient boosting decision tree (GBDT) for classification models, constructed using XGBoost (version 1.2). 25 XGBoost is an optimized distributed gradient boosting library (open source) and the most common method for structured problems in Kaggle competitions. XGBoost shares qualities with other decision tree ensemble algorithms, such as the ability to handle a mixture of numerical and categorical data features. Moreover, XGBoost is a highly suitable tool for these models because it learns trees in a sequential order such that each additional tree is a gradient step with respect to a loss function, and has an extra randomization parameter used to decorrelate the individual trees. 26 (Additional information regarding model design can be found in the Supporting Information.) We selected the area under the receiver operating characteristic curve (AUROC) for the models' evaluation metric. ROC graphs are an extremely useful tool for evaluating classifiers; the AUROC is equivalent to the probability that the classifier will rank a randomly chosen positive instance higher than a randomly chosen negative instance. 27 To meet the reporting standard of ML predictive models in biomedical research, we reported accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). 28 All machine learning models were implemented using Python (The Python Software Foundation, Fredericksburg, VA, USA) (version 3.7)."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 0.79, "unit": "auroc", "tolerance": null, "state": "complete"}], "gaps": ["operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:diagnostic_evaluation_roc", "axes": {"method": {"axis": "method", "tier": "R4", "blocker": "method:diagnostic_evaluation_roc", "detail": {"outcome": "determined", "family": "diagnostic_evaluation", "specific_method": "roc", "required_operations": ["diagnostic_evaluation_roc"], "missing_operations": ["diagnostic_evaluation_roc"], "basis": "The DSL has no operation for diagnostic_evaluation_roc. Writing the first one is a bounded piece of work."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:35213063", "asset:table:pmid:35213063:1", "asset:table:pmid:35213063:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [{"operation": "diagnostic_evaluation_roc", "unlocks_papers": 12, "priority": 4}], "converters": [], "readers": ["unknown", "xml"], "capabilities": [], "data_gaps": ["source:pmid:35213063", "materials:the source data behind pmid:35213063, which the paper says are available from the authors on request", "materials:the analysis programme that recomputes the published estimate", "data:availability"]}, "gaps": ["method:diagnostic_evaluation_roc"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "d2b9abd2ebdcf06f4116e29d95bbac9c44ba19320d7c90eeae0ef4a7aab03672", "source_hash": "0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "raw_response_sha256": "sha256:d704feaa660915475176164aecaf25b0c774704ce68730f5bddd0ed352e58ca3", "raw_response_chars": 2418}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "a76bc4382f9a765b66acf3c82716c772bab06dc9a133d638597983cae995a5b0", "source_hash": "0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "raw_response_sha256": "sha256:55d8868924062bf322772a9366e2aa9e02063d4f5b4535dbeb4103fbd5529a70", "raw_response_chars": 2562}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "2a75859a656a40766164a903115de5f5e0bb3c0db4e094c3db066ccaf45c699c", "source_hash": "0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "raw_response": "{\"parent_value\":0.79,\"unit\":\"AUROC\",\"evidence\":\"For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance), with model accuracy of 77%, sensitivity of 71%, specificity of 77%, positive prediction value (PPV) of 14% and negative prediction value (NPV) of 98%.\",\"target_result\":\"The stage-count complexity classifier had an AUROC of 0.79.\",\"number_stated\":true}", "reading": {"parent_value": 0.79, "unit": "AUROC", "evidence": "For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance), with model accuracy of 77%, sensitivity of 71%, specificity of 77%, positive prediction value (PPV) of 14% and negative prediction value (NPV) of 98%.", "target_result": "The stage-count complexity classifier had an AUROC of 0.79.", "number_stated": true, "source_locator": "chars 1077-1381 of source sha256 0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0"}, "recorded_at": "2026-10-31T14:37:33.735003+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "cca32bd2cf9fe1a7a78c64756240f056287766d0fd7a239ed1fcca4b43e04222", "source_hash": "0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0", "raw_response": "{\"parent_value\":0.79,\"unit\":\"AUROC\",\"evidence\":\"For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance)\",\"target_result\":\"0.79 AUROC\",\"number_stated\":true}", "reading": {"parent_value": 0.79, "unit": "AUROC", "evidence": "For the number of stages complexity classification model, the area under the receiver operating characteristic curve (AUROC) was 0.79 (good performance)", "target_result": "0.79 AUROC", "number_stated": true, "source_locator": "chars 1077-1229 of source sha256 0d65673d5223700ffc22fc58ddbbdadc89784e8acfd119213c0389cf404958e0"}, "recorded_at": "2026-10-31T14:37:44.489353+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "The area under the receiver operating characteristic curve (AUROC) of the Mohs surgery stage-count complexity classifier was 0.79 on the test set.", "minimax-m3": "0.79 test-set AUROC for the Mohs surgery stage-count complexity classifier", "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Retrospective analysis of 8644 Mohs micrographic surgery procedures", "Modified marginal contribution feature importance (MCI) feature selection", "Gradient boosting decision tree (GBDT) classification using XGBoost version 1.2", "10-fold cross-validation on 90% of the dataset", "Evaluation on a held-out test set comprising 10% of the dataset", "SHAP-based model interpretability"], "minimax-m3": ["Retrospective machine-learning analysis of 8,644 Mohs micrographic surgery procedures", "Gradient boosting decision tree classification implemented with XGBoost version 1.2", "Modified marginal contribution feature importance algorithm for feature exclusion", "Shuffled 90% training and 10% test data split with 10-fold cross-validation on the training data", "AUROC evaluation supplemented by accuracy, sensitivity, specificity, positive predictive value, and negative predictive value"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["The stage-count complexity model predicted tumor excision complexity based on the number of Mohs stages required to achieve tumor-free margins; excisions requiring more than two stages were classified as complex.", "The dataset was shuffled and divided into training and test datasets, with 90% allocated to training and 10% allocated to testing.", "The models were created using the training dataset for 10-fold cross-validation and used a gradient boosting decision tree constructed with XGBoost version 1.2.", "For the stages complexity classification model, the average 10-fold cross-validation AUROC was 0.75 ± 0.03.", "The test set AUROC was 0.79.", "The model achieved 77% accuracy, 71% sensitivity, 77% specificity, 14% positive predictive value, and 98% negative predictive value."], "minimax-m3": ["The stage-count complexity classifier achieved a test-set AUROC of 0.79, described as good performance.", "The average 10-fold cross-validation AUROC for the stage-count complexity classifier was 0.75 ± 0.03.", "Tumor excisions requiring more than two Mohs stages were categorized as complex.", "The classifier was evaluated using a gradient boosting decision tree constructed with XGBoost."], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": null, "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:4e1a683d889508ec06b92836be57b1f087c78f6bcd3cc31fb88b06ea592311aa", "type": "sep_package", "label": "SEP v1 package for pmid:35213063"}], "activities": [{"id": "activity:conversion:pmid:35213063", "type": "conversion", "used": ["package:4e1a683d889508ec06b92836be57b1f087c78f6bcd3cc31fb88b06ea592311aa"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"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:35213063", "parent_hash": "sha256:939e1f76c88fabca9054534298095a8acb6e3bd1280afe4d14b8d7bbb70f9c3b", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:35213063, which the paper says are available from the authors on request not verified", "asset:source:pmid:35213063 not verified", "authors", "execution.not_run", "method:diagnostic_evaluation_roc", "operations", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:diagnostic_evaluation_roc"]},"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":"2026-11-04T02:51:16+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}}}