{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40800173", "kind": "science-record", "revision": 2, "content_hash": "sha256:c29a9cb285ca51b507f050b74081a6079742662ff94e76793a30478907b3bcf3", "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": "Comprehensive analysis of disulfidoptosis-related genes reveals molecular heterogeneity and key regulators in retinoblastoma progression.", "doi": "10.21037/tp-2024-596", "pmid": "40800173", "authors": null, "journal": "Translational pediatrics", "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": 8.0, "unit": "de-drgs", "tolerance": null, "source": "chars 1012-1220 of source sha256 e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f"}, "evidence": [{"asset": "source:pmid:40800173", "locator": "chars 1012-1220 of source sha256 e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "quote": "Compared with controls, the disulfidoptosis score was significantly lower (P<0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma."}]}], "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:40800173"], "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:40800173", "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:40800173' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40800173", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tp-2024-596", "sha256": "sha256:e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tp-2024-596", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40800173:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d773fdfd2284715e61c99f13b3a520106c9a41a0cecdf477ecd315c56ebb3727", "bytes": 446, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t1", "version": null, "note": "The detailed information for the used datasets", "structure": {"pmcid": "PMC12336911", "section_index": 4, "section_title": "Data acquisition and preprocessing", "row_count": 4, "column_count": 5}, "table": {"label": "Table 1", "caption": "The detailed information for the used datasets", "rows": [["Data set", "Platforms", "Type", "Sample size", "Usage"], ["GSE208143", "GPL17077", "mRNA", "33 (27 RB and 6 control)", "Train"], ["GSE97508", "GPL15207", "mRNA", "9 (6 RB and 3 control)", "Train"], ["GSE24673", "GPL6244", "mRNA", "11 (9 RB and 2 control)", "Validation"]], "row_count": 4, "column_count": 5, "numeric_cells": 9, "header_rows": 1, "locator": "section[4]/table-wrap[1]#t1"}}], "gaps": ["asset:source:pmid:40800173 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:40800173", "asset:table:pmid:40800173:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40800173"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "9482a1280595c2702e951495fe8bb8cea4e4aec3095d57370e9d014060ef39bc", "source_hash": "e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "raw_response_sha256": "sha256:7cc6d55009e7d04b2d18d9edba6a942b3f5776562dadb80d1fb7b1eb68d16bd9", "raw_response_chars": 5351}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "8b64cd49f0367e29159d6353b5af155b4583ed8838b3d4ff703d0e19d30d8b29", "source_hash": "e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "raw_response_sha256": "sha256:2f090e445a6495106ef3d6f7e1a0e34029d8e53ade575284396dae6ebd1e289a", "raw_response_chars": 58915}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "36c89f66cc63d205862df971747c42a1eeae7d687f20a141456e127057bd534b", "source_hash": "e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "raw_response": "{\"parent_value\":8,\"unit\":\"DE-DRGs\",\"evidence\":\"Compared with controls, the disulfidoptosis score was significantly lower (P<0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\",\"target_result\":\"Eight differentially expressed disulfidoptosis-related genes were identified in retinoblastoma.\",\"number_stated\":true}", "reading": {"parent_value": 8, "unit": "DE-DRGs", "evidence": "Compared with controls, the disulfidoptosis score was significantly lower (P<0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.", "target_result": "Eight differentially expressed disulfidoptosis-related genes were identified in retinoblastoma.", "number_stated": true, "source_locator": "chars 1012-1220 of source sha256 e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f"}, "recorded_at": "2026-10-31T15:30:35.616443+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "28a441fcf898d05ae18bfecc7a8dccc04a42f8177e2fd4279aa0b91aeb29d86d", "source_hash": "e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for main finding. Source has multiple numbers: eight DE-DRGs, two subtypes, two key genes, P&lt;0.05, etc. Registered target \"headline numerical result the paper states for its main finding\". Likely central headline numerical result? Main finding involvement DRGs and subtype heterogeneity. Could be \"eight DE-DRGs were identified\" perhaps headline numerical result. Need decide. Prompt asks single numerical result replication registered target has to reproduce. Target broad main finding. The paper's headline likely number maybe eight DE-DRGs? Need report paper's own value, unit printed. Could unit \"DE-DRGs\" or perhaps \"eight\" isn't numeric? parent_value 8, unit \"DE-DRGs\". Exact contiguous quote containing number: \"Compared with controls, the disulfidoptosis score was significantly lower (P&lt;0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\" But number is spelled \"eight\", not numeric digit. Parent value 8, unit DE-DRGs. However question says value paper itself states, evidence exact quote contains number. \"eight\" is a number. The source's abstract headline findings includes eight DE-DRGs. Alternatively two molecular subtypes perhaps headline. Need understand likely benchmark task: They want extract \"parent numerical result\" from supplied paper text, often quantity associated with registered target. Registered target deliberately generic \"the headline numerical result the paper states for its main finding\". We infer likely count of DE-DRGs (8) is main numerical finding. Could also be 2 subtypes. Need perhaps use exact clause. They emphasize \"single numerical result\". Main result probably \"eight DE-DRGs were identified\" because this is substantive discovery, whereas two subtypes and two genes are counts. Which is headline? Title \"Comprehensive analysis ... reveals molecular heterogeneity and key regulators...\" Abstract conclusion no numeric. In results, first sentence: lower score, and eight DE-DRGs identified. Main finding perhaps 8 DE-DRGs. Key findings: two subtypes. The term \"headline numerical result\" maybe benchmark registered target derived from paper's metadata. Need answer one.\n\nLet's parse wording: \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". They want value paper itself states, not calculated. Unit must printed. Evidence quote exact contiguous. Likely target is \"eight DE-DRGs\". Number stated in words; parent_value number 8. Unit \"DE-DRGs\" exactly printed. Evidence whole clause linking target. Could quote: \"Compared with controls, the disulfidoptosis score was significantly lower (P&lt;0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\" This includes other number P&lt;0.05, though asked single result and evidence quote can contain another number, potentially confusion. Better exact contiguous clause \"eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\" Is that whole clause enough? Yes exact contiguous, contains number in words. \"do not shorten it\" means if clause needed, quote whole clause. Could quote only \"eight DE-DRGs were identified\" perhaps exact phrase but they ask attribution by text wording and quote whole clause. Better \"eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\" Is this a clause; perhaps yes.\n\nBut unit: \"DE-DRGs\" perhaps unit isn't conventional unit. Could use \"DE-DRGs\" as unit, number = 8. Or \"differentially expressed disulfidoptosis-related genes\" though source prints acronym. Must unit paper prints. It says \"eight DE-DRGs\". Unit can be \"DE-DRGs\". target_result phrase.\n\nCould number stated false if no headline number? But clearly there are numeric counts. Need select.\n\nLet's inspect abstract main numerical result perhaps \"eight DE-DRGs\" and \"two molecular subtypes\", \"two key downregulated genes\". Which one is \"headline numerical result\"? They might expect \"8 DE-DRGs\". The title speaks heterogeneity and key regulators; key regulator genes count 2. But no measurement. The paper main finding \"involvement of disulfidoptosis in retinoblastoma\" with 8 DE-DRGs and two subtypes. The target phrase is vague intentionally perhaps source itself has one obvious headline numerical result in abstract? Let's identify counts in abstract:\n- Three datasets\n- eight DE-DRGs\n- two molecular subtypes\n- two key genes\n- P&lt;0.05\nNo singular headline metric. Maybe source truncated from article where figures have AUC etc, but given text only. Registered target may refer to \"headline numerical result\" as one specific value. They expect model to choose most headline-like. In title/main finding maybe \"eight DE-DRGs were identified\" is first result. Yet \"two disulfidoptosis-based molecular subtypes\" is highlighted under key findings and conclusion. Could be target result = 2 molecular subtypes? Need reason from common extraction benchmark patterns.\n\nThe user asks \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce.\" Registered target could be semantic label generated by them. They want one number. \"the headline numerical result the paper states for its main finding.\" This paper is exploratory bioinformatic, likely no single headline effect size. The most concrete result is \"eight DE-DRGs\". A replication of main finding would reproduce identification of eight genes. Two subtypes is also a result, but perhaps central. They might define \"headline numerical result\" as count of identified DE-DRGs because abstract explicitly says \"eight DE-DRGs were identified\". The source's conclusion says \"identified two disulfidoptosis-based molecular subtypes\". Hmm.\n\nMaybe target_result should state \"eight DE-DRGs were identified\". parent_value 8. Unit \"DE-DRGs\". number_stated true. Evidence exact.\n\nNeed ensure JSON valid, no markdown. Should unit maybe \"genes\" because DE-DRGs are genes. The paper prints \"eight DE-DRGs\"; unit \"DE-DRGs\". Good.\n\nCould evidence include full exact sentence. The instruction: \"Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" Here direct wording \"eight DE-DRGs were identified\". Quote whole clause likely enough. Exact sentence perhaps safer, despite containing P. Use exact full sentence to avoid shortening. They say \"do not shorten it\" referring evidence quote? \"The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it.\" Ambiguous: don't shorten source? Probably quote complete relevant clause, not entire source. Full sentence is exact and allows check. Let's provide sentence. It contains P&lt;0.05 and 8. But parent target clear.\n\ntarget_result maybe \"Eight differentially expressed disulfidoptosis-related genes (DE-DRGs) were identified.\" Is that paraphrase allowed? Restriction applies evidence not target_result. Fine. But to avoid invented interpretation, \"eight DE-DRGs were identified\" exact.\n\nNeed decide whether \"eight\" qualifies number and parent_value numeric 8. yes.\n\nLet's formulate JSON:\n{\"parent_value\":8,\"unit\":\"DE-DRGs\",\"evidence\":\"Compared with controls, the disulfidoptosis score was significantly lower (P&lt;0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\",\"target_result\":\"Eight DE-DRGs were identified in retinoblastoma.\",\"number_stated\":true}\n\nWould a critic say headline is two subtypes? Maybe target result main finding title says molecular heterogeneity and key regulators. Key findings bullet 2 says two subtypes. Hmm.\n\nLet's investigate textual hierarchy: Abstract:\nAim...\nMethods...\nResults: Compared..., and eight DE-DRGs identified... Consensus clustering revealed two molecular subtypes. C2... LASSO and SVM-RFE identified two key downregulated genes...\nConclusions.\nThe \"headline numerical result\" perhaps first numerical result in abstract = eight. Usually if task targets \"number of DE-DRGs identified\", they'd register explicitly. Here generic because perhaps generated target was \"eight differentially expressed disulfidoptosis-related genes\". But user registered target phrase \"the headline numerical result the paper states for its main finding\" obfuscates exact metric. We need infer likely one from abstract title. The primary main finding is disulfidoptosis involvement, quantified by \"eight DE-DRGs\". Number of subtypes is structural secondary. I'd choose 8.\n\nCould use unit \"DE-DRGs\" exactly. Great.</think>\n\n{\"parent_value\":8,\"unit\":\"DE-DRGs\",\"evidence\":\"Compared with controls, the disulfidoptosis score was significantly lower (P<0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.\",\"target_result\":\"Eight DE-DRGs were identified in retinoblastoma.\",\"number_stated\":true}", "reading": {"parent_value": 8, "unit": "DE-DRGs", "evidence": "Compared with controls, the disulfidoptosis score was significantly lower (P<0.05) in retinoblastoma, and eight DE-DRGs were identified, suggesting the potential involvement disulfidoptosis in retinoblastoma.", "target_result": "Eight DE-DRGs were identified in retinoblastoma.", "number_stated": true, "source_locator": "chars 1012-1220 of source sha256 e411df047ef5899662cfdc3d4a6d6a0ddeb622f0a3e5fc4689a3d5b00eec539f"}, "recorded_at": "2026-10-31T15:30:53.680289+00:00"}], "agreement": false, "disagreements": {"physical_methods": {"minimax": ["Expression of key genes was validated in retinoblastoma cells.", "EPAS1 overexpression experiments", "Cell viability, migration, invasion, and apoptosis assays", "Measurement of the relative NADP+/NADPH ratio"], "minimax_alt": ["Key-gene expression validation in retinoblastoma cells", "Functional experiments involving EPAS1 overexpression in retinoblastoma cells, assessing viability, migration, invasion, apoptosis, and the relative NADP+/reduced NADP (NADPH) ratio"], "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis", "Gene set variation analysis", "Single-sample gene set enrichment analysis", "ESTIMATE", "Consensus cluster analysis", "Least absolute shrinkage and selection operator", "Support vector machine-recursive feature elimination", "Correlation analysis", "One-way analysis of variance", "Tukey’s multiple comparison test"], "minimax_alt": ["Differentially expressed disulfidoptosis-related gene identification", "Gene set variation analysis (GSVA)", "Single-sample gene set enrichment analysis", "ESTIMATE", "Consensus cluster analysis", "Least absolute shrinkage and selection operator", "Support vector machine-recursive feature elimination", "Correlation analysis of EPAS1 and SLC7A11 expression with oxidative phosphorylation and immune cell infiltration", "One-way analysis of variance", "Tukey’s multiple comparison test"], "decisive": false}, "statistical_method": {"minimax": "One-way analysis of variance with Tukey’s multiple comparison test", "minimax_alt": "One-way analysis of variance and Tukey’s multiple comparison test", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:a8612eb6bf01a2736c713cb8cec6325784da3f80293d2ad5eae24a85ab17bcc8", "type": "sep_package", "label": "SEP v1 package for pmid:40800173"}], "activities": [{"id": "activity:conversion:pmid:40800173", "type": "conversion", "used": ["package:a8612eb6bf01a2736c713cb8cec6325784da3f80293d2ad5eae24a85ab17bcc8"], "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:40800173", "parent_hash": "sha256:6a208e69a5c03fb8f5eac1a80bc3ba819e23c78f586996683d61643a38f8ed9c", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40800173 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40800173' 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":"2026-11-04T03:14:17+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}}}