{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40591190", "kind": "science-record", "revision": 2, "content_hash": "sha256:fa223168433123872e0f2addd0de6ed2f5c3f12537adfc035b2ecff51813a84d", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:43Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development and validation of a prognostic model for efferocytosis-associated genes in cervical squamous cell carcinoma.", "doi": "10.1007/s12672-025-02901-9", "pmid": "40591190", "authors": null, "journal": "Discover oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40591190"], "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:40591190", "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:40591190' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40591190", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-02901-9", "sha256": "sha256:09e9ebca553ac2ea5cfcb782e3965c83e6f7e0267b0c7cacd2a1dbf0c4ad79dd", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-02901-9", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40591190:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bf27ca8ed7e454ede58b00772ebe977616aad5697c5c8d27860ba45acc23121c", "bytes": 658, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab1", "version": null, "note": "The list of 71 efferocytosis-related genes (ERGs)", "structure": {"pmcid": "PMC12214117", "section_index": 14, "section_title": "Acquisition and enrichment analysis of PER-DEGs", "row_count": 1, "column_count": 2}, "table": {"label": "Table 1", "caption": "The list of 71 efferocytosis-related genes (ERGs)", "rows": [["ERGs", "P2RY2 PGE2 PANX1 STAB2 ADGRB1 TIM4 TYRO3 MERTK AXL ELMO1 ELMO2 ELMO3 DOCK1 DOCK2 DOCK3 DOCK4 DOCK5 RAC1 CD47 SIRPA SLC2A1 SLC16A2 SLC66A1 ADAM17 ADAM10 DNASE1 DNASE1L1 DNASE2 PPARG TIMD4 HAVCR2 ADAM9 MBTPS1 HIF1A ARNT EPO TNF TNFRSF1A LRP1 ABCA1 HMBG1 CX3CL1 CX3CR1 CXCR4 P2RY12 P2RY6 P2RX7 SLC26A6 SLC35A4 SLC46A1 SLC7A7 SLC14A1 PPARA NR1H4 SLC25A1 SLC25A10 SLC20A1 UCP2 CPT1A DNM1L SLC12A4 SLC16A1 SLC6A6 SLC4A7 WNK1 OSR1 SPAK PDK1 PDK4 ARG1 ODC1"]], "row_count": 1, "column_count": 2, "numeric_cells": 1, "header_rows": 0, "locator": "section[14]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:40591190:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7f899feacadef39cebd67be4f6e00ed7f3cb067d6c2da72576523a57ea5f7024", "bytes": 2269, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#Tab2", "version": null, "note": "The list of 332 prognosis-efferocytosis related DEGs (PER-DEGs)", "structure": {"pmcid": "PMC12214117", "section_index": 14, "section_title": "Acquisition and enrichment analysis of PER-DEGs", "row_count": 1, "column_count": 2}, "table": {"label": "Table 2", "caption": "The list of 332 prognosis-efferocytosis related DEGs (PER-DEGs)", "rows": [["PER-DEGs", "SLC2A1 NDRG1 NDUFA4L2 SLC6A8 VEGFA BNIP3 CSTB IGFBP3 ALDOA FAM83A GJB2 ANGPTL4 MXD1 SERPINB1 BNIP3L TGFB1 PYGL ADM GJB6 SFN KRT17 POLR2L UPP1 RHCG ITGA5 PERP RPL35 PLAUR MT1X CDKN1A FSCN1 ENO1 HSP90AB1 MKNK2 RPS2 PTMA NDUFB2 RPS26 ATP1B1 BZW1 HK2 RPLP2 HMGB1 IL1RN HSP90AA1 S100A10 HMGN2 TPM4 CDCP1 NME1 MRPS12 TMPRSS4 EIF5A SERINC2 SERPINB5 DLG1 GPI TMEM158 PGAM1 RPS27A DSC2 MRPL12 NET1 ERH S100A2 TIMM8B AHNAK2 SRM RPL22 DNAJB6 SLC16A1 ZFP36 IRF6 RPL32 FOSL1 ITGB1 CYCS HSPD1 PSMB2 FAU RPS15 TMEM91 RPS12 RPL8 LINC00520 TXNIP EZR HNRNPA2B1 CD55 SNRPF RPS29 PPIA RPLP1 TMEM45A TGM1 RPS25 TMEM160 SLIRP CYB5R1 LSM7 SEC61G RPL38 RPS17 SERPINB13 AK4 COX6B1 PDK1 COX6C TOMM40 MIR210HG MRPS21 ARNTL2 RPSA SNRPE ISOC2 MRPL52 DHRS3 ASB2 SYNJ2 FERMT1 NDUFS6 SLCO4A1 LIMA1 MRPS34 TRMT112 RPL27 ADAM8 CCT5 RPL14 ISG15 MAP3K13 SRP14 SKIL RPL13 GJB3 NAMPT NCL DCXR PHLDB2 ZNF385A RPS5 LSM4 DSG3 SOD2 CD68 RPS18 EIF3K APRT TUBA1B MRPL4 PIM1 HNRNPA3 PPP4R1 ACAP2 NDUFS8 UQCR11 CEBPB SNRPD1 EEF1B2 HNRNPA1 SRSF7 MRPL3 COA4 RPL12 SET TIMM13 GADD45GIP1 EGLN1 ADAM9 CNN3 DSC3 POLR2F CHCHD2 ZNF593 CCT3 KRT16 CEACAM5 PSMB3 NDUFB7 EHD2 S100A9 NAA38 PPP1CB C1QBP UQCRH EHD4 STMN1 B3GNT8 IL36G RAI14 RIOK3 TGFA CYC1 SERTAD1 CTHRC1 SSBP1 ARL8B ANKLE2 CDKN3 SOWAHC MRPS15 NHP2 EIF4EBP1 KRT6B FNDC3B TPD52 IQGAP1 NDUFB10 CAV2 PTTG1 SDF2L1 CDH1 EHF RPL21 COX5B CAV1 MRPL55 HCAR3 DENND2C TRIB1 ITPA MRPL20 RPS10 YBX1 KCMF1 MRPL36 COX8A CDH3 ANXA5 AREG RBMX SRSF3 HBEGF DNPH1 PPARD TMEM30B NPC1 DDX39A CENPF CKS1B CDC20 FBL PRDX6 ARHGAP5 SYNE2 CKS2 RALA GNA15 MDK UQCRQ VCL MAD1L1 WDR83OS SERPINB2 NAA10 EID1 ELL2 ISCU AKR1B10 GPR68 DUSP7 SULT2B1 CA2 EIF3G NDUFA2 AKR1C3 SRSF2 LYPD3 KRT6A FOS HCAR2 PYCARD EXOC3 JTB TP63 ZFP36L1 P3H2 CFD DAPK3 PDLIM5 MARK3 TMPO EEF1D SPRR1B ANP32B CP UBE2S HSPG2 PSMB4 CALM3 ITGAV TOP2A PPP1R13L SNRNP70 NUSAP1 EGR1 KLF3 CHCHD10 NUCKS1 NASP ID3 PCNA CCT4 BGN RPL9 DDX5 S100A4 CLEC2B SLC20A1 CTSL LURAP1L PRELID1 ITPKC GABRP CALM2 HMGB2 SRGAP3 IVL LGALS7 HOPX ITGAE THBD TSC22D3 ARL6IP1 KRT1 KRT6C ARL6IP5 HSPA6 CNFN APOBEC3G ID2 MT2A"]], "row_count": 1, "column_count": 2, "numeric_cells": 1, "header_rows": 0, "locator": "section[14]/table-wrap[2]#Tab2"}}], "gaps": ["asset:source:pmid:40591190 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:40591190", "asset:table:pmid:40591190:1", "asset:table:pmid:40591190:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40591190"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "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": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"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", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:b627d88414a547664e9f90a54572fd03ab189f63bceed4725d65502b2c5330e1", "type": "sep_package", "label": "SEP v1 package for pmid:40591190"}], "activities": [{"id": "activity:conversion:pmid:40591190", "type": "conversion", "used": ["package:b627d88414a547664e9f90a54572fd03ab189f63bceed4725d65502b2c5330e1"], "agent": "agent:corpus-assay-engine"}], "agents": [{"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:40591190", "parent_hash": "sha256:55990a8e714293d0113b3c82a8318bf7a9feb7d7bd9682ab2ebf91f599385d70", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40591190 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "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:40591190' 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":"2026-11-04T01:35:24+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}}}