{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40646168", "kind": "science-record", "revision": 1, "content_hash": "sha256:5a6b2bed99bca98291e4dcbd21f14dca9098314653628ec79d90496cd1091806", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T10:25:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Machine learning-based construction of a programmed cell death-related model reveals prognosis and immune infiltration in pancreatic adenocarcinoma patients.", "doi": "10.1038/s41598-025-10847-9", "pmid": "40646168", "authors": null, "journal": "Scientific reports", "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": 6.0, "unit": "pcdrgs", "tolerance": null, "source": "chars 648-962 of source sha256 b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc"}, "evidence": [{"asset": "source:pmid:40646168", "locator": "chars 648-962 of source sha256 b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "quote": "Using a comprehensive machine learning framework involving 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy, we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU."}]}], "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:40646168"], "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:40646168", "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:40646168' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40646168", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-10847-9", "sha256": "sha256:b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-10847-9", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40646168 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:40646168"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40646168"]}, "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": "fdf84493d178edfa0d01cb50b82beeba36353ea27f04c3f5008f938fc1db3666", "source_hash": "b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "raw_response_sha256": "sha256:98dfabb5521e48d3ff9be7ffc449901825baa466f4cd59a5f4d0b195e94a21ac", "raw_response_chars": 6524}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "f850ddabfb534f5b4689314bbe25b848de13f27fe73bdc79f1b795754b314a18", "source_hash": "b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "raw_response_sha256": "sha256:83d6041be1ff0f6781afeeb381922285527a220f191d3b18fe7349bdbef9acad", "raw_response_chars": 78380}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "29da7a6684309e5d6a339269d5a74a1293581e8048a3b146a45e4ef1e3d312e9", "source_hash": "b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "raw_response": "{\"parent_value\":6,\"unit\":\"PCDRGs\",\"evidence\":\"Using a comprehensive machine learning framework involving 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy, we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\",\"target_result\":\"The best prognostic model was based on six PCDRGs: ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "PCDRGs", "evidence": "Using a comprehensive machine learning framework involving 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy, we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.", "target_result": "The best prognostic model was based on six PCDRGs: ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.", "number_stated": true, "source_locator": "chars 648-962 of source sha256 b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc"}, "recorded_at": "2026-10-31T15:27:09.905628+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "6cb8dea799fa71590530c8a599a1f56bd4a322cfa78d499a62d4850041236361", "source_hash": "b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline for main finding, value paper itself states registered target. Source abstract and excerpts. Need infer main finding perhaps six PCDRGs? Headline numerical result model based on six genes. \"headline numerical result the paper states for its main finding\" Replication target likely number 6? Need parse request wording. Registered target generic: headline numerical result paper states for main finding. Need report headline number only, paper stated, unit printed, exact contiguous quotation containing number. Candidate numerical results:\n- 1,034 samples integrated\n- 17 candidate genes\n- 117 algorithmic combinations\n- six PCDRGs named\n- risk score no metric\n- k=2 clusters\n- P=0.01\n- 1-,3-,5-year survival prediction (three numbers, not single?)\nWhat is \"headline numerical result\" likely abstract's main finding: model based on six PCDRGs. Perhaps replication of registered target needs reproduce six genes? But unit \"PCDRGs\". They ask numerical result. Need identify likely expected answer based on source extraction benchmark. \"single numerical result that a replication of the registered target has to reproduce.\" Registered target is \"the headline numerical result the paper states for its main finding.\" Could mean determine primary target from text, perhaps \"six PCDRGs\" in model construction. We need quote whole clause attribution. Likely parent_value 6, unit \"PCDRGs\", evidence exact sentence/clause: \"Using a comprehensive machine learning framework involving 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy, we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\" That contains both 117 and six; evidence must contain number and attribution. Quote whole clause. But \"single numerical result\" perhaps 117 algorithmic combinations? Main finding could be \"six PCDRGs\" and exact number. Need choose.\n\nLet's examine wording. They expect perhaps output based on \"headline number\" extraction from paper. Registered target description likely points to main abstract claim. Main finding: constructed model based on six PCDRGs. \"A nomogram ... 1-, 3-, and 5-year survival prediction.\" Could headline numerical result be six genes. The word \"headline numerical result\" often asks for main result metric, e.g. AUC = 0.XX. But supplied text omits detailed results with performance metrics. Maybe abstract has counts. Need not calculate. They ask \"single numerical result that a replication of the registered target has to reproduce.\" Could be target is perhaps \"number of genes in signature\" (six). There is no explicit performance number. We should set false if no number for registered target? Yet registered target itself says headline numerical result. Need extract one.\n\nLet's understand likely dataset/task design. User provides source text and asks numerical result with registered target. The target may be abstract semantic slot. They insist \"value paper itself states for registered target, not calculated, converted, averaged or reconstructed.\" Evidence exact contiguous quote. If no number, false. We need likely identify one main result. The abstract's key numerical output could be \"model based on six PCDRGs\". Unit paper prints likely \"PCDRGs\". \"headline number only\" likely they want 6 PCDRGs. The evidence could quote whole clause to check attribution. Need JSON number 6.\n\nCould candidate be 17 candidate PCDRGs associated with OS; model built on six. Main finding ultimately signature based on six. \"headline numerical result\" perhaps best model selected among 117 combos, based on six genes. The final model's headline is six-gene signature. So answer likely 6, unit \"PCDRGs\", exact quote. target_result concise: \"The paper states that the selected prognostic model was based on six PCDRGs.\" number_stated true.\n\nNeed ensure exact contiguous quotation. Could quote full sentence exactly, though starts \"Using...\" and includes number 117. They request headline number only but evidence can have other number; evidence quote whole clause. Maybe quote only \"we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\" Is that exact contiguous clause and contains attribution. It includes only six numeric digit, and gene names. The source sentence begins \"Using...\" We can quote from \"we identified...\" Exact. Is \"whole clause\" enough. Could quote full sentence including 117. Better exact quote from source to establish \"we identified ... based on six PCDRGs\". Their instruction: \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" Clause could be entire sentence. But including 117 could create ambiguity for \"single numerical result\". Better quote only predicate clause after introductory phrase. Exact contiguous: \"we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\" This is a clause, no other numerical result. Great.\n\nUnit: Does paper print \"six PCDRGs\"; unit perhaps \"PCDRGs\". They ask unit must be unit paper prints. Use \"PCDRGs\". parent_value 6. target_result perhaps \"The best-performing prognostic model was based on six PCDRGs.\" We should not overcomplicate. JSON valid, no markdown.\n\nBut let's thoroughly assess possibility target result = 1,034 samples. \"headline numerical result paper states for its main finding\" Main finding perhaps cohort size? A replication of main finding would need reproduce 1,034 samples? No, replication doesn't reproduce sample count necessarily. Six-gene model also would reproduce gene composition, not a numerical outcome. A headline numerical result usually effect estimate or performance metric. Source lacks such. Could answer false: no number stated for registered target? The source text says robust predictive performance, high-risk worse prognosis, etc., but no metric. User specifically says \"If the text states no number for the registered target, set number_stated to false ... say in target_result what the text does state instead.\" Could this be trap: abstract has various counts, but no headline numerical result like AUC or HR for main finding. Registered target likely asks generic main finding, and source excerpts perhaps intentionally don't include metrics. We need discern.\n\nLet's parse first instruction semantically: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" REGISTERED TARGET: \"the headline numerical result the paper states for its main finding\". This seems tautological. They might expect extracting a number like sample count, gene count, clusters. The \"single numerical result\" likely defined in article metadata elsewhere, but target field is natural-language abstraction. The supplied source includes abstract + methods/results snippets. Need locate likely headline number.\n\nCould be from abstract's result: \"identified 17 candidate PCD-related genes significantly associated with overall survival\" then machine learning identifies model based on six genes. Main finding's number perhaps 6. The \"registered target\" wording may be generated to avoid naming target explicitly, but description is clear enough: headline numerical result for main finding = six PCDRGs. They want only headline number, perhaps not all numeric claims. So answer 6.\n\nLet's look at paper title and abstract. Main finding: machine-learning construction of programmed cell death-related model reveals prognosis and immune infiltration. Key quantitative element: \"model based on six PCDRGs\". That's indeed model composition, central headline. Other abstract numbers: 1,034 samples, 17 candidates, 117 algorithmic combinations, 1/3/5 years. Which is \"headline numerical result\"? Usually abstract conclusion: established prognostic signature, no numeric performance. The distinctive main output is six genes. Replication of registered target perhaps replicating \"six-gene model\". So yes.\n\nUnit perhaps \"PCDRGs\" not \"genes\". They specify \"unit must be the unit the paper prints.\" Quote says \"six PCDRGs\". Good.\n\nEvidence exact contiguous quote. Let's make sure punctuation and Unicode. Source:\n\"Using a comprehensive machine learning framework involving 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy, we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\"\nWe'll quote from \"we identified...\" exact, perhaps ending period. Exact contiguous. The evidence requirement says exact contiguous quotation from SOURCE TEXT. JSON escape no issues. Use this.\n\ntarget_result: \"The paper states that the best algorithms composition constructed a prognostic model based on six PCDRGs.\" Should headline number only maybe target_result should state result with number? Schema likely expected explanatory. Could say \"Prognostic model based on six PCDRGs.\" But instruction \"Report the headline number only\" applies parent_value perhaps. target_result can summarize. Could avoid number because headline number separately. Maybe \"The prognostic model is based on six PCDRGs.\" Number stated true. JSON number 6.\n\nNeed ensure no markdown.</think>\n\n{\"parent_value\":6,\"unit\":\"PCDRGs\",\"evidence\":\"we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.\",\"target_result\":\"The selected prognostic model was based on six PCDRGs.\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "PCDRGs", "evidence": "we identified the StepCox[both] + Ridge as the best algorithms composition to construct a prognostic model based on six PCDRGs, ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.", "target_result": "The selected prognostic model was based on six PCDRGs.", "number_stated": true, "source_locator": "chars 793-962 of source sha256 b7e9f327d2fd0dbe9ba3f932f4561e6c0bcd6773363bc2dd890bf0d1860567cc"}, "recorded_at": "2026-10-31T15:27:24.070491+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A prognostic model based on six PCDRGs—ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU—was selected from 17 candidate genes after evaluating 117 algorithmic combinations under a Leave-one-out cross-validation (LOOCV) strategy.", "minimax_alt": "The StepCox[both] + Ridge algorithm composition, selected from 117 algorithmic combinations under leave-one-out cross-validation, was used to construct a prognostic model based on six PCDRGs: ITGA3, CDCP1, IL1RAP, CLU, PBK, and PLAU.", "decisive": false}, "physical_methods": {"minimax": [], "minimax_alt": ["qRT-PCR"], "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis", "Univariate Cox regression analysis", "Leave-one-out cross-validation (LOOCV)", "StepCox[both] + Ridge", "Kaplan-Meier survival analysis", "Log-rank test", "Multivariate Cox proportional hazards regression", "Unsupervised consensus clustering", "GO enrichment analysis", "KEGG pathway enrichment analysis", "GSVA", "Shapiro-Wilk test", "Student’s t-test", "One-way analysis of variance (ANOVA)", "Wilcoxon rank-sum test", "Mann-Whitney U test"], "minimax_alt": ["Differential expression analysis", "Univariate Cox regression analysis", "Leave-one-out cross-validation (LOOCV)", "StepCox[both] + Ridge", "Kaplan-Meier survival analysis with the log-rank test", "Univariate and multivariate Cox proportional hazards regression"], "decisive": false}, "statistical_method": {"minimax": "Leave-one-out cross-validation (LOOCV)", "minimax_alt": "Leave-one-out cross-validation (LOOCV) with the StepCox[both] + Ridge algorithmic composition", "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:e0708e49cafcfd12ab2f377be17c458d00fd9abbadb1658cf8534411040038c9", "type": "sep_package", "label": "SEP v1 package for pmid:40646168"}], "activities": [{"id": "activity:conversion:pmid:40646168", "type": "conversion", "used": ["package:e0708e49cafcfd12ab2f377be17c458d00fd9abbadb1658cf8534411040038c9"], "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": "48b1e2d6-012e-4b25-b3f5-76256875205d", "parent_hash": "e0708e49cafcfd12ab2f377be17c458d00fd9abbadb1658cf8534411040038c9", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40646168 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:40646168' 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":"2026-11-04T02:15:01+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}}}