{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41367897", "kind": "science-record", "revision": 2, "content_hash": "sha256:9bfeb87bb81261c613600051d09935037547a8b92e6f0bceaa1a420326d23f86", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:52Z", "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-Integrated Analysis of SULF1, CXCL8, and PBLD Expression as Discriminative Biomarkers for Early Detection and Prognosis in Colorectal Cancer.", "doi": "10.2147/ijgm.s553709", "pmid": "41367897", "authors": null, "journal": "International journal of general medicine", "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:41367897"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "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:41367897", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "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:41367897' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41367897", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/ijgm.s553709", "sha256": "sha256:abe8b3fe8d291e5a6d048dd39af0813d49e504d3dd9225b9fb15e23381364a8b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/ijgm.s553709", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41367897:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d11c8a9a8782ef91612b3d83b559e34405e6a9281056dd6881d93f69f5a9e7c5", "bytes": 508, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t0001", "version": null, "note": "Sequences of Primers", "structure": {"pmcid": "PMC12684262", "section_index": 10, "section_title": "Quantitative Real-Time Polymerase Chain Reaction (RT-qPCR)", "row_count": 6, "column_count": 3}, "table": {"label": "Table 1", "caption": "Sequences of Primers", "rows": [["Gene name", "Forward 5′-3′", "Reverse 5′-3′"], ["CXCL8", "TTGGCAGCCTTCCTGATTTCT", "TTCTCAGCCCTCTTCAAAAACT"], ["SULF1", "GGCTTGATCGGCAACTAGGA", "GTTCCTCATCTGCCCTGACC"], ["LRRC19", "CACTGGCCTATCGGCTGTAAT", "TGACCTTGCTCCATCCATACC"], ["PBLD", "TCTGCACACGCTGTTCTCA", "CAGCAGCGTCACAGCATAAC"], ["GAPDH", "CAAATTCCATGGCACCGTCA", "GATGGCATGGACTGTGGTCA"]], "row_count": 6, "column_count": 3, "numeric_cells": 3, "header_rows": 1, "locator": "section[10]/table-wrap[1]#t0001"}}, {"id": "asset:table:pmid:41367897:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:085bd58011351d461ee8609b5c8d511ea4d7ee12f5243a4b4f01746edf564753", "bytes": 10857, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#t0002", "version": null, "note": "Detailed Information of the up-Regulated DEGs", "structure": {"pmcid": "PMC12684262", "section_index": 16, "section_title": "PPI Network Analysis of DEGs", "row_count": 20, "column_count": 6}, "table": {"label": "Table 2", "caption": "Detailed Information of the up-Regulated DEGs", "rows": [["ID", "Gene Name", "GOTERM_BP_DIRECT", "GOTERM_CC_DIRECT", "GOTERM_MF_DIRECT", "KEGG_PATHWAY"], ["CXCL8", "C-X-C motif chemokine ligand 8(CXCL8)", "GO:0001525~angiogenesis,GO:000223 7~response to molecule of bacterial origin,GO:0006928~movement of cell or subcellular component,GO:000 6935~chemotaxis,G O:0006954~inflam matory response,GO:00069 55~immune response,GO:00070 50~cell cycle arrest,GO:0007165~ signal transduction,GO:00 07186~G-protein coupled receptor signaling pathway,GO:000828 5~negative regulation of cellproliferation,GO:00", "GO:0005576~extrac ellular region,GO:0005615~extracellular space,GO:0005622~ intracellular,", "GO:0005153~interle ukin-8 receptor binding,GO:000551 5~protein binding,GO:000800 9~chemokine activity,", "hsa04060:Cytokine-cytokine receptor interaction,hsa0406 2:Chemokine signaling pathway,hsa04064: NF-kappa B signaling pathway,hsa04620: Toll-like receptor signaling pathway,hsa04621: NOD-like receptor signaling pathway,hsa04622: RIG-I-like receptor signaling pathway,hsa04932: Non-alcoholic fatty liver disease (NAFLD),hsa05120:Epithelial cellsignaling in Helicobacter pylori infection,hsa05131: Shigellosis,hsa0513"], ["SULF1", "sulfatase 1(SULF1)", "GO:0001822~kidney development,GO:0 001937~negative regulation of endothelial cell proliferation,GO:00 02063~chondrocyte development,GO:0 003094~glomerular filtration,GO:00069 15~apoptotic process,GO:000815 2~metabolic process,GO:001057 5~positive regulation of vascular endothelial growth factor production,GO:001 4846~esophagus smooth muscle contraction,GO:001 6525~negative regulation of", "GO:0005615~extrac ellular space,GO:0005783~ endoplasmic reticulum,GO:00057 94~Golgi apparatus,GO:0005 795~Golgi stack,GO:0005886~ plasma membrane,GO:0009 986~cell surface,GO:0045121~membrane raft,", "GO:0003824~cataly tic activity,GO:0004065~arylsulfatase activity,GO:0005509~calcium ion binding,GO:000844 9~N-acetylglucosamine- 6-sulfatase activity,GO:0008484~sulfuric ester hydrolase activity,", ""], ["HMGCS2", "3-hydroxy-3- methylglutaryl-CoA synthase 2(HMGCS2)", "", "GO:0006695~choles terol biosynthetic process,GO:000829 9~isoprenoid biosynthetic process,GO:004695 1~ketone body biosynthetic process,", "GO:0005739~mitoc hondrion,GO:00057 43~mitochondrial inner membrane,GO:0005 759~mitochondrial matrix,", "hsa00072:Synthesis and degradation of ketone bodies,hsa00280:Va line, leucine and isoleucine degradation,hsa006 50:Butanoate metabolism,hsa009 00:Terpenoid backbone biosynthesis,hsa01 100:Metabolic pathways,hsa01130: Biosynthesis of antibiotics,"], ["ABCG2", "ATP binding cassette subfamily G member 2 (Junior blood group)(ABCG2)", "", "GO:0006810~transp ort,GO:0006855~dr ug transmembrane transport,GO:00068 79~cellular iron ion homeostasis,GO:00 15886~heme transport,GO:00424 93~response to drug,GO:0042908~x enobiotic transport,GO:00464 15~urate metabolic process,", "GO:0005634~nucle us,GO:0005886~pla sma membrane,GO:0016 021~integral component of membrane,GO:0031 966~mitochondrial membrane,", "hsa02010:ABCtransporters,hsa049 76:Bile secretion,"], ["CD177", "CD177molecule(CD177)", "", "GO:0007596~blood coagulation,GO:005 0900~leukocyte migration,", "GO:0005886~plasm a membrane,GO:0031 225~anchored component of membrane,GO:0070 062~extracellular exosome,", ""], ["ANPEP", "alanyl aminopeptidase, membrane(ANPEP)", "Amino acid transport and metabolism,", "GO:0001525~angio genesis,GO:000650 8~proteolysis,GO:0 030154~cell differentiation,GO: 0043171~peptide catabolic process,GO:004671 8~viral entry into host cell,", "GO:0005615~extracellular space,GO:0005765~ lysosomal membrane,GO:0005 793~endoplasmic reticulum-Golgi intermediate compartment,GO:0 005829~cytosol,GO:0005887~integral component of plasma membrane,GO:0009 897~external side of plasma membrane,GO:0016 021~integral component of membrane,GO:0070 062~extracellular exosome,", "hsa00480:Glutathio ne metabolism,hsa011 00:Metabolic pathways,hsa04614: Renin-angiotensin system,hsa04640:H ematopoietic cell lineage,"], ["ADH1C", "alcohol dehydrogenase 1C (class I), gamma polypeptide(ADH1C)", "Energy production and conversion,", "GO:0006069~ethan ol oxidation,", "GO:0005829~cytos ol,", "hsa00010:Glycolysis/ Gluconeogenesis,h sa00071:Fatty acid degradation,hsa003 50:Tyrosine metabolism,hsa008 30:Retinol metabolism,hsa009 80:Metabolism of xenobiotics by cytochrome P450,hsa00982:Drug metabolism - cytochrome P450,hsa01100:Metabolic pathways,hsa05204: Chemical carcinogenesis,"], ["AKR1B10", "aldo-keto reductase family 1 member B10(AKR1B10)", "", "GO:0001523~retino id metabolic process,GO:000608 1~cellular aldehyde metabolic process,GO:000758 6~digestion,GO:00 08202~steroid metabolic process,GO:001648 8~farnesol catabolic process,GO:004459 7~daunorubicin metabolic process,GO:004459 8~doxorubicin metabolic process,GO:005511 4~oxidation- reduction process,", "GO:0005764~lysoso me,GO:0005829~cy tosol,GO:0070062~ extracellular exosome,", "hsa00040:Pentose and glucuronate interconversions,hs a00051:Fructose and mannose metabolism,hsa000 52:Galactose metabolism,hsa005 61:Glycerolipid metabolism,hsa011 00:Metabolic pathways,"], ["AQP8", "aquaporin 8(AQP8)", "", "GO:0006810~transp ort,GO:0006833~wa ter transport,GO:00099 92~cellular water homeostasis,GO:00 15793~glycerol transport,GO:00342 20~ion transmembrane transport,GO:00713 20~cellular response to cAMP,", "GO:0005886~plasm a membrane,GO:0005 887~integral component of plasma membrane,GO:0016 021~integral component of membrane,GO:0045 177~apical part of cell,", "hsa04976:Bile secretion,"], ["CHP2", "calcineurin like EF- hand protein 2(CHP2)", "Signal transduction mechanisms / Cytoskeleton / Cell division and chromosome partitioning / General function prediction only,", "GO:0008284~positi ve regulation of cell proliferation,GO:00 10922~positive regulation of phosphatase activity,GO:0015031~protein transport,GO:00423 07~positive regulation of protein import into nucleus,GO:004594 4~positive regulation of transcription from RNA polymerase II promoter,GO:00708 86~positive regulation of calcineurin-NFAT signaling cascade,GO:007127 7~cellular response to calcium ion,", "GO:0005634~nucle us,GO:0005737~cyt oplasm,GO:0005886~plasma membrane,", ""], ["CA2", "carbonic anhydrase 2(CA2)", "", "GO:0001822~kidney development,GO:0 002009~morphoge nesis of an epithelium,GO:0006 730~one-carbon metabolic process,GO:000926 8~response to pH,GO:0010043~response to zinc ion,GO:0015670~ca rbon dioxide transport,GO:00157 01~bicarbonate transport,GO:00322 30~positive regulation of synaptic transmission, GABAergic,GO:0032849~positive regulation of cellular pHreduction,GO:00381", "GO:0005615~extracellular space,GO:0005737~ cytoplasm,GO:0005 829~cytosol,GO:00 05886~plasma membrane,GO:0005 902~microvillus,GO:0016323~basolater al plasma membrane,GO:0030 424~axon,GO:0043 209~myelin sheath,GO:0045177~apical part of cell,GO:0070062~ex tracellular exosome,", "hsa00910:Nitrogen metabolism,hsa049 64:Proximal tubule bicarbonate reclamation,hsa049 66:Collecting duct acid secretion,hsa04971: Gastric acid secretion,hsa04972: Pancreatic secretion,hsa04976: Bile secretion,"], ["CLCA1", "chloride channel accessory 1(CLCA1)", "", "GO:0006508~prote olysis,GO:0006810~ transport,GO:00068 16~calcium ion transport,GO:00342 20~ion transmembrane transport,GO:00714 56~cellular response to hypoxia,GO:190247 6~chloride transmembrane transport,", "GO:0005615~extracellular space,GO:0005886~ plasma membrane,GO:0005 887~integral component of plasma membrane,GO:0005 902~microvillus,GO:0042589~zymogen granule membrane,", "hsa04924:Renin secretion,hsa04972: Pancreatic secretion,"], ["DHRS9", "dehydrogenase/reductase 9(DHRS9)", "General function prediction only,", "GO:0002138~retino ic acid biosynthetic process,GO:000820 9~androgen metabolic process,GO:003085 5~epithelial cell differentiation,GO: 0042448~progester one metabolic process,GO:004257 2~retinol metabolic process,GO:004290 4~9-cis-retinoic acid biosynthetic process,GO:005511 4~oxidation- reduction process,", "GO:0005789~endo plasmic reticulum membrane,GO:0030 176~integral component of endoplasmic reticulum membrane,GO:0031 090~organelle membrane,", "hsa00830:Retinol metabolism,hsa011 00:Metabolic pathways,"], ["LRRC19", "leucine rich repeat containing 19(LRRC19)", "", "GO:0006469~negati ve regulation of protein kinase activity,GO:0019221~cytokine- mediated signaling pathway,GO:004642 6~negative regulation of JAK- STAT cascade,", "GO:0005737~cytopl asm,GO:0016021~integral component of membrane,", ""], ["PADI2", "peptidyl arginine deiminase 2(PADI2)", "", "GO:0006325~chromatin organization,GO:00 10848~regulation of chromatin disassembly,GO:00 18101~protein citrullination,GO:00 21762~substantia nigra development,GO:0 030520~intracellula r estrogen receptor signaling pathway,GO:003641 3~histone H3-R26 citrullination,GO:00 48096~chromatin- mediated maintenance of transcription,GO:00 70100~negative regulation of chemokine- mediated signaling pathway,GO:190162", "GO:0005737~cytopl asm,GO:0005829~c ytosol,GO:0035327~transcriptionally active chromatin,GO:0070 062~extracellular exosome,", ""], ["PBLD", "phenazine biosynthesis like protein domain containing(PBLD)", "", "GO:0009058~biosynthetic process,GO:001063 3~negative regulation of epithelial cell migration,GO:0010 719~negative regulation of epithelial to mesenchymal transition,GO:00302 77~maintenance of gastrointestinal epithelium,GO:0030 512~negative regulation of transforming growth factor beta receptor signaling pathway,GO:005068 0~negative regulation of epithelial cell proliferation,GO:00 60392~negative", "GO:0005737~cytopl asm,GO:0070062~extracellular exosome,", ""], ["SELENBP1", "selenium binding protein 1(SELENBP1)", "", "GO:0015031~protei n transport,", "GO:0005615~extracellular space,GO:0005730~ nucleolus,GO:00058 29~cytosol,GO:001 6020~membrane,G O:0070062~extracellular exosome,", ""], ["SLC4A4", "solute carrier family 4 member 4(SLC4A4)", "", "GO:0006810~transp ort,GO:0006814~sodium ion transport,GO:00156 98~inorganic anion transport,GO:00157 01~bicarbonate transport,GO:00357 25~sodium ion transmembrane transport,GO:00514 53~regulation of intracellular pH,GO:0098656~anion transmembrane transport,", "GO:0005886~plasm a membrane,GO:0005 887~integral component of plasma membrane,GO:0016 021~integral component of membrane,GO:0016 323~basolateral plasma membrane,GO:0070 062~extracellular exosome,", "hsa04964:Proximal tubule bicarbonate reclamation,hsa049 72:Pancreatic secretion,hsa04976: Bile secretion,"], ["ZG16", "zymogen granule protein 16(ZG16)", "", "GO:0015031~protei n transport,", "GO:0005578~protei naceous extracellular matrix,GO:0005796~Golgi lumen,GO:0031012~extracellular matrix,GO:0042589~zymogen granule membrane,GO:0060 205~cytoplasmic membrane- bounded vesicle lumen,", ""]], "row_count": 20, "column_count": 6, "numeric_cells": 72, "header_rows": 1, "locator": "section[16]/table-wrap[1]#t0002"}}, {"id": "asset:table:pmid:41367897:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a8604a243bba991a030dd0afab87e9da0c48d61b2404120eb69bbd09ffc9c6d9", "bytes": 1278, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#t0003", "version": null, "note": "Clinicopathologic Data from Patients", "structure": {"pmcid": "PMC12684262", "section_index": 17, "section_title": "CXCL8, SULF1, LRRC19 and PBLD Gene Expression", "row_count": 16, "column_count": 8}, "table": {"label": "Table 3", "caption": "Clinicopathologic Data from Patients", "rows": [["Access ID", "Age", "Gender", "TumorSize (cm)", "TumorLocation", "HistologicGrade", "LymphaticMetastasis", "VenousInvasion"], ["4671602", "61", "Male", "7*6", "Colon", "T4a", "Present", "Present"], ["4673620", "50", "Male", "4.5*4", "Rectum", "T3", "Absent", "Absent"], ["4671722", "66", "Male", "4.5*3.5", "Rectum", "T3", "Absent", "Absent"], ["4672724", "59", "Male", "5*2.8", "Colon", "T4a", "Present", "Present"], ["4673143", "63", "Male", "4*3", "Colon", "T3", "Absent", "Absent"], ["4673502", "61", "Female", "4*4", "Colon", "T3", "Absent", "Present"], ["4672637", "46", "Female", "3*3", "Colon", "T3", "Present", "Absent"], ["4831533", "56", "Male", "6*4", "Colon", "T3", "Present", "Absent"], ["4832474", "61", "Male", "4*3.5", "Colon", "T3", "Present", "Absent"], ["4831603", "82", "Female", "4.5*4.3", "Colon", "T3", "Absent", "Absent"], ["4831626", "71", "Female", "4.5*4", "Colon", "T3", "Present", "Absent"], ["4834073", "67", "Female", "3.9*3", "Colon", "T3", "Absent", "Absent"], ["4832133", "65", "Female", "4.5*4.5", "Rectum", "T3", "Absent", "Absent"], ["4833061", "77", "Male", "5.3*4.7", "Rectum", "T2", "Absent", "Absent"], ["4830659", "64", "Male", "3*2.5", "Rectum", "T2", "Absent", "Absent"]], "row_count": 16, "column_count": 8, "numeric_cells": 45, "header_rows": 1, "locator": "section[17]/table-wrap[1]#t0003"}}], "gaps": ["asset:source:pmid:41367897 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:41367897", "asset:table:pmid:41367897:1", "asset:table:pmid:41367897:2", "asset:table:pmid:41367897:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41367897"]}, "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:6db87eb078f3b77fc0aa4c213a11259e037d0fb34d4d1c61f075d3b7074244b7", "type": "sep_package", "label": "SEP v1 package for pmid:41367897"}], "activities": [{"id": "activity:conversion:pmid:41367897", "type": "conversion", "used": ["package:6db87eb078f3b77fc0aa4c213a11259e037d0fb34d4d1c61f075d3b7074244b7"], "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:41367897", "parent_hash": "sha256:5dc3aa928717d14d931379644cfb920d6215da9bad657c10804a6e6607b47033", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41367897 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:accession_absent", "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:41367897' 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":"2026-11-04T03:05:39+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}}}