{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40821778", "kind": "science-record", "revision": 2, "content_hash": "sha256:e234d5a4372b88f404311a019bfcd205525a4495f607cc208c3fdc4e78a88de6", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:46Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "HER2-positive breast cancer with invasive micropapillary carcinoma component shows immunosuppressive microenvironment and resistance to neoadjuvant therapy.", "doi": "10.3389/fimmu.2025.1623675", "pmid": "40821778", "authors": null, "journal": "Frontiers in immunology", "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": 21.6, "unit": "percent", "tolerance": null, "source": "chars 1378-1500 of source sha256 670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c"}, "evidence": [{"asset": "source:pmid:40821778", "locator": "chars 1378-1500 of source sha256 670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "quote": "The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall"}]}], "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:40821778"], "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:40821778", "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:40821778' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40821778", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2025.1623675", "sha256": "sha256:670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2025.1623675", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40821778:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6339ba42bbb813ada8b6205800990e40a75b71c395a70157c0d26a996171d11e", "bytes": 1483, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Baseline characteristics.", "structure": {"pmcid": "PMC12354535", "section_index": 9, "section_title": "Baseline characteristics", "row_count": 26, "column_count": 5}, "table": {"label": "Table 1", "caption": "Baseline characteristics.", "rows": [["Characteristic", "Total (n = 244)", "IMPC (n = 38)", "Non-IMPC (n = 206)", "aP-value"], ["Median age (year)", "46 (25–74)", "44 (25–66)", "47 (25–74)", "0.133"], ["Age, n (%)", "", "", "", "0.183"], ["≤40", "80 (32.8)", "16 (42.1)", "64 (31.1)", ""], [">40", "164 (67.2)", "22 (57.9)", "142 (68.9)", ""], ["Tumor size, n (%)", "", "", "", "0.748"], ["≤ 2 cm", "20 (8.2)", "2 (5.3)", "18 (8.7)", ""], ["> 2 cm", "224 (91.8)", "36 (94.7)", "188 (91.3)", ""], ["Lymph nodes, n (%)", "", "", "", "0.406"], ["Negative", "12 (4.9)", "3 (7.9)", "9 (4.4)", ""], ["Positive", "232 (95.1)", "35 (92.1)", "197 (95.6)", ""], ["Hormone receptor, n (%)", "", "", "", "<0.05"], ["Negative", "90 (36.9)", "11 (28.9)", "79 (38.3)", ""], ["Positive", "154 (63.1)", "27 (71.1)", "127 (61.7)", ""], ["Grade, n (%)", "", "", "", "0.993"], ["G1 + G2", "135 (55.3)", "21 (55.3)", "114 (55.3)", ""], ["G3", "109 (44.7)", "17 (44.7)", "92 (44.7)", ""], ["Ki-67, n (%)", "", "", "", "0.254"], ["≤30%", "104 (42.6)", "13 (34.2)", "91 (44.2)", ""], [">30%", "140 (57.4)", "25 (65.8)", "115 (55.8)", ""], ["Neoadjuvant targeted therapy, n (%)", "", "", "", "0.052"], ["Trastuzumab", "94 (38.5)", "20 (52.6)", "74 (35.9)", ""], ["Trastuzumab + pertuzumab", "150 (61.5)", "18 (47.4)", "132 (64.1)", ""], ["Neoadjuvant chemotherapy, n (%)"], ["AC-T", "170 (69.7)", "24 (63.2)", "146 (70.9)", "0.342"], ["TCb", "74 (30.3)", "14 (35.8)", "60 (29.1)", ""]], "row_count": 26, "column_count": 5, "numeric_cells": 70, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:40821778 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:40821778", "asset:table:pmid:40821778:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40821778"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "1459cb735852eefdaee36ec1de2ab4851bce10ed2ef4bab1bd35f12ee83262ba", "source_hash": "670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "raw_response_sha256": "sha256:9d9e740a46f8f9dc42017db9809ded461bceb6928fdc63fefc67f412192a5e5d", "raw_response_chars": 4637}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "fc63ba2c1031fa2a15e156732a8d6c53114f0f6c8faf0b913c82ee20a14e8ddf", "source_hash": "670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "raw_response_sha256": "sha256:95a80186db95a3d58ae49cef443e58838babac9577f53f2d3a34767fe71f8877", "raw_response_chars": 76573}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "541e969952070f47ba86b0a0b91cc993f56080e6943aa831faa8fb4e3a823e36", "source_hash": "670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "raw_response": "{\"parent_value\":21.6,\"unit\":\"%\",\"evidence\":\"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall\",\"target_result\":\"Overall pathological complete response (pCR) rate in the IMPC group\",\"number_stated\":true}", "reading": {"parent_value": 21.6, "unit": "%", "evidence": "The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall", "target_result": "Overall pathological complete response (pCR) rate in the IMPC group", "number_stated": true, "source_locator": "chars 1378-1500 of source sha256 670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c"}, "recorded_at": "2026-10-31T15:31:05.792505+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "fd793bc56b78cbe3ff005ab23894642ed569ee6c1021702c12b75200940cf22a", "source_hash": "670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for registered target main finding. Paper main finding likely pCR rate IMPC vs non-IMPC overall: 21.6% vs 47.1%. Asked \"single numerical result\" and report headline number only: value paper itself states for registered target, not calculated. Registered target vague \"headline numerical result paper states for its main finding.\" Need choose parent_value likely 21.6, unit %. Evidence exact contiguous quote containing number, whole clause attribution. Could perhaps headline result is pCR rates 21.6% vs 47.1%. But schema singular parent_value. \"single numerical result that a replication ... has to reproduce. Report headline number only\". The headline number attached to main target likely IMPC pCR overall =21.6%. Need evidence quote clause: \"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall...\" This includes comparison, and target. But \"headline number only\" parent_value 21.6. Unit %.\n\nCould target perhaps 21.6% vs 47.1%; \"single numerical result\" could mean result statement includes pair? Yet schema parent_value numeric only, singular. Usually these tasks ask registered target likely a benchmark value from source, perhaps paper's headline numerical result. Need infer extraction conventions. They say attribution may be carried by parenthetical list, respectively, or direct words. Quote whole clause. Here direct wording identifies \"IMPC group\" and lower pCR compared to non, then values respectively by order. Headline likely 21.6% for IMPC group. Evidence exact quote. target_result describe. JSON valid, no markdown.\n\nNeed ensure exact contiguous quotation and not shorten. Could quote: \"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall, 15.0% vs. 28.4% (P = 0.223) in the H-based subgroup, and 27.8% vs. 57.6% (P = 0.017) in the HP-based subgroup.\" But whole clause enough, yet perhaps to establish \"overall\" include through \"(P = 0.004) overall\". Exact contiguous. Evidence contains both values and P; that's okay. Asked headline number only refers output fields likely no extra numerical values in target_result. But evidence necessarily contains numbers plural. Could quote minimal contiguous clause: \"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall\" Is that a grammatical exact contiguous quotation? Yes from source before comma. No ellipsis. Attribution clear. Parent_value 21.6. unit \"%\". target_result maybe \"Overall pathological complete response rate in the IMPC group.\" Avoid numerical mention. number_stated true.\n\nQuestion: \"find the single numerical result that a replication of the registered target has to reproduce.\" Could headline numerical result perhaps 244 patients? Main finding headline is lower pCR, likely 21.6%. Need choose. Let's scrutinize title/abstract. Abstract reports n 244, subgroup counts, pCR 21.6 vs 47.1 overall and subgroups, survival P values, CTNNB1. Which is \"headline numerical result\"? Usually benchmark questions might target a specific number like \"pCR in IMPC group.\" They registered target generic, no named endpoint, says headline numerical result paper states for its main finding. Main claim resistance, numerical centerpiece pCR rate 21.6%. So yes.\n\nCould parent_value perhaps 47.1? Headline \"IMPC lower pCR compared to non-IMPC: 21.6% vs 47.1%\" and target main finding may be difference? No difference not stated, cannot calculate. User explicitly no calculated. The first number 21.6 is headline for IMPC main finding. Unit printed \"%\". Evidence should maybe include full sentence as exact contiguous quotation to show attribution. They warn \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" Entire clause sentence perhaps. Use entire sentence including subgroup rates. But \"Report headline number only\" perhaps evidence can contain all, since quote exact and no shortening. They explicitly evidence exact contiguous quote containing number; do not shorten it. \"do not shorten it\" means likely quote source passage, perhaps whole clause. Let's quote sentence exactly. parent_value only headline number. target_result no other number.\n\nJSON string escaping. Ensure unicode okay. Could use β irrelevant.\n\nLet's formulate:\n{\n \"parent_value\":21.6,\n \"unit\":\"%\",\n \"evidence\":\"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall, 15.0% vs. 28.4% (P = 0.223) in the H-based subgroup, and 27.8% vs. 57.6% (P = 0.017) in the HP-based subgroup.\",\n \"target_result\":\"Overall pathological complete response (pCR) rate in the IMPC group.\",\n \"number_stated\":true\n}\n\nDoes evidence include multiple numbers but okay. Could quote only clause up to overall, but \"do not shorten it\" suggests full sentence. Good.\n\nNeed reply JSON object only, no code fence.</think>\n\n{\"parent_value\":21.6,\"unit\":\"%\",\"evidence\":\"The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall, 15.0% vs. 28.4% (P = 0.223) in the H-based subgroup, and 27.8% vs. 57.6% (P = 0.017) in the HP-based subgroup.\",\"target_result\":\"Overall pathological complete response (pCR) rate in the IMPC group.\",\"number_stated\":true}", "reading": {"parent_value": 21.6, "unit": "%", "evidence": "The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall, 15.0% vs. 28.4% (P = 0.223) in the H-based subgroup, and 27.8% vs. 57.6% (P = 0.017) in the HP-based subgroup.", "target_result": "Overall pathological complete response (pCR) rate in the IMPC group.", "number_stated": true, "source_locator": "chars 1378-1612 of source sha256 670d0f3c400a9ec12fb132f47497827e1c8a2a6491abae3fa5b9d9322491647c"}, "recorded_at": "2026-10-31T15:31:07.823079+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax": "The IMPC group had a lower overall pathological complete response rate than the non-IMPC group: 21.6% versus 47.1% (P = 0.004).", "minimax_alt": "The IMPC group exhibited significantly lower pCR rates compared to the non-IMPC group: 21.6% vs. 47.1% (P = 0.004) overall, 15.0% vs. 28.4% (P = 0.223) in the H-based subgroup, and 27.8% vs. 57.6% (P = 0.017) in the HP-based subgroup.", "decisive": false}, "physical_methods": {"minimax": ["To validate bioinformatics findings, matched pretreatment tumor samples from both groups were analyzed."], "minimax_alt": ["Validation using matched pretreatment tumor samples from both groups", "Assessment of tumor-infiltrating lymphocytes, CD4+ and CD8+ T cells, M2 macrophages, and PD-L1 expression in matched tumor samples"], "decisive": false}, "analysis_methods": {"minimax": ["Differentially expressed genes (DEGs) were identified using the “limma” R package with criteria of adjusted P-value < 0.05 and |logFC| ≥ 1.", "Enrichment analysis for Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) was performed using “ClusterProfiler” with a significance threshold of corrected P-value < 0.05.", "The protein-protein interaction (PPI) network for Homo sapiens was built using the STRING database with a minimum confidence score of 0.4.", "Hub genes were identified using the CytoHubba plugin with the maximal clique centrality (MCC) algorithm.", "Immune cell abundance was assessed by ImmuCellAI."], "minimax_alt": ["Retrospective IMPC versus non-IMPC comparison of baseline clinical and pathological characteristics, pCR rates, and survival outcomes", "R v4.0.4 normalization of the GSE66418 gene-expression matrix", "Differential expression analysis using the “limma” R package with adjusted P-value < 0.05 and |logFC| ≥ 1", "KEGG and Gene Ontology enrichment analysis using “ClusterProfiler” with corrected P-value < 0.05", "STRING protein-protein interaction network construction", "Cytoscape and CytoHubba hub-gene identification using the maximal clique centrality algorithm", "Immune-cell abundance assessment using ImmuCellAI"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "passed", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:79cf8a6ec0adb3b42af8765ed98092924779e0940a2482150906372b550fcfb1", "type": "sep_package", "label": "SEP v1 package for pmid:40821778"}], "activities": [{"id": "activity:conversion:pmid:40821778", "type": "conversion", "used": ["package:79cf8a6ec0adb3b42af8765ed98092924779e0940a2482150906372b550fcfb1"], "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:40821778", "parent_hash": "sha256:df45a341e5b4753af4d79c3e80855932e7126462a57aeb3be880430b909fca26", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40821778 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40821778' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:45:46+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}}}