{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31521183", "kind": "science-record", "revision": 8, "content_hash": "sha256:2a74cdebbe2655b84391e587db2138e1ecf0427542f1ddd7280a9dc637579edf", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:44:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comparative study of excretory-secretory proteins released by Schistosoma mansoni-resistant, susceptible and naïve Biomphalaria glabrata.", "doi": "10.1186/s13071-019-3708-0", "pmid": "31521183", "authors": ["Conor E Fogarty", "Min Zhao", "Donald P McManus", "Mary G Duke", "Scott F Cummins", "Tianfang Wang"], "journal": "Parasites & vectors", "year": 2019, "abstract": "BACKGROUND: Schistosomiasis is a harmful neglected tropical disease caused by infection with Schistosoma spp., such as Schistosoma mansoni. Schistosoma must transition within a molluscan host to survive. Chemical analyses of schistosome-molluscan interactions indicate that host identification involves chemosensation, including naïve host preference. Proteomic technique advances enable sophisticated comparative analyses between infected and naïve snail host proteins. This study aimed to compare resistant, susceptible and naïve Biomphalaria glabrata snail-conditioned water (SCW) to identify potential attractants and deterrents.\nMETHODS: Behavioural bioassays were performed on S. mansoni miracidia to compare the effects of susceptible, F1 resistant and naïve B. glabrata SCW. The F1 resistant and susceptible B. glabrata SCW excretory-secretory proteins (ESPs) were fractionated using SDS-PAGE, identified with LC-MS/MS and compared to naïve snail ESPs. Protein-protein interaction (PPI) analyses based on published studies (including experiments, co-expression, text-mining and gene fusion) identified S. mansoni and B. glabrata protein interaction. Data are available via ProteomeXchange with identifier PXD015129.\nRESULTS: A total of 291, 410 and 597 ESPs were detected in the susceptible, F1 resistant and naïve SCW, respectively. Less overlap in ESPs was identified between susceptible and naïve snails than F1 resistant and naïve snails. F1 resistant B. glabrata ESPs were predominately associated with anti-pathogen activity and detoxification, such as leukocyte elastase and peroxiredoxin. Susceptible B. glabrata several proteins correlated with immunity and anti-inflammation, such as glutathione S-transferase and zinc metalloproteinase, and S. mansoni sporocyst presence. PPI analyses found that uncharacterised S. mansoni protein Smp_142140.1 potentially interacts with numerous B. glabrata proteins.\nCONCLUSIONS: This study identified ESPs released by F1 resistant, susceptible and naïve B. glabrata to explain S. mansoni miracidia interplay. Susceptible B. glabrata ESPs shed light on potential S. mansoni miracidia deterrents. Further targeted research on specific ESPs identified in this study could help inhibit B. glabrata and S. mansoni interactions and stop human schistosomiasis.", "claims": [{"id": "claim-method", "statement": "A two-way ANOVA test was used to calculate P-values and evaluate the significance of behavioural modifications in response to pH-neutral water, susceptible and F1 resistant SCW.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31521183", "locator": "sections[5] \"Schistosoma mansoni miracidia isolation and behavioural bioassay\" paragraph 4", "quote": "A two-way ANOVA test was used to calculate P-values and evaluate the significance of behavioural modifications in response to pH-neutral water, susceptible and F1 resistant SCW."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [41] partner repository with the dataset identifier PXD015129. Other datasets analysed in this study are included in this published article and its additional files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31521183", "locator": "sections[24] \"Availability of data and materials\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [41] partner repository with the dataset identifier PXD015129. Other datasets analysed in this study are included in this published article and its additional files."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:31521183"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31521183", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s13071-019-3708-0", "sha256": "sha256:413b5a54eb9818bf16493e6ffb965da556076cef83ee36ea2845fe6ea88257c7", "bytes": 74161, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s13071-019-3708-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6744689", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:31521183:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86287af3937d2519686dfd365e057dfe90b71964966bb83d1e89f3725c28a838", "bytes": 1444, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab1", "version": null, "note": "High confidence non-redundant ESPs ([− 10lgP] > 30) with putative anti-pathogen function identified in resistant B. glabrata SCW. Details of coverage, peptide match number and BLAST confidence (e-value) are shown", "structure": {"pmcid": "PMC6744689", "section_index": 14, "section_title": "Biomphalaria glabrata ESP annotation and gene ontology analysis", "row_count": 12, "column_count": 8}, "table": {"label": "Table 1", "caption": "High confidence non-redundant ESPs ([− 10lgP] > 30) with putative anti-pathogen function identified in resistant B. glabrata SCW. Details of coverage, peptide match number and BLAST confidence (e-value) are shown", "rows": [["Description", "− 10lgP", "Coverage (%)a", "No. of peptides", "No. uniqueb", "Avg. mass", "BLASTp e-value", "Accession No."], ["Leukocyte elastase inhibitor-like", "73.93", "15", "2", "1", "15593", "1.01E−98", "BGLB007529-PB"], ["Haemoglobin type 1", "69.56", "12", "4", "1", "20380", "4.65E−130", "BGLB026333-PA"], ["Superoxide dismutase [Cu-Zn]", "59.07", "14", "2", "2", "16447", "4.39E−104", "BGLB000035-PA"], ["Adenosine deaminase CECR1", "58.36", "8", "2", "2", "25076", "3.34E−159", "BGLB033953-PA"], ["Glutathione peroxidase-like", "50.23", "12", "2", "2", "22859", "1.85E−151", "BGLB008980-PC"], ["Heat-shock 70 kDa protein cognate 4", "45.56", "5", "4", "4", "71177", "0", "BGLB007783-PB"], ["Enolase-phosphatase E1", "42.13", "13", "2", "2", "19313", "4.05E−119", "BGLB029757-PA"], ["Peroxiredoxin 1", "39.55", "4", "1", "1", "27567", "0", "BGLB000120-PA"], ["Rho GDP-dissociation inhibitor 1", "32.87", "4", "1", "1", "23176", "2.75E−143", "BGLB011409-PB"], ["Carboxypeptidase B", "32.85", "12", "1", "1", "12298", "2.51E−73", "BGLB037596-PA"], ["Putative tyrosinase-like protein tyr-1", "31.61", "2", "1", "1", "67700", "0", "BGLB030046-PA"]], "row_count": 12, "column_count": 8, "numeric_cells": 83, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31521183:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ade14208a1415dc843274206ff4b2cb0fc0643e0eeb91bc4741c0e321e8206c3", "bytes": 1902, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#Tab2", "version": null, "note": "High confidence non-redundant ESPs (-10lgP > 30) identified in the susceptible B. glabrata SCW. Details of coverage, peptide match number and BLAST confidence (e-value) are shown", "structure": {"pmcid": "PMC6744689", "section_index": 14, "section_title": "Biomphalaria glabrata ESP annotation and gene ontology analysis", "row_count": 17, "column_count": 8}, "table": {"label": "Table 2", "caption": "High confidence non-redundant ESPs (-10lgP > 30) identified in the susceptible B. glabrata SCW. Details of coverage, peptide match number and BLAST confidence (e-value) are shown", "rows": [["Description", "− 10lgP", "Coverage (%)a", "No. of peptides", "No. uniqueb", "Avg. mass", "BLASTp e-value", "Accession No."], ["Zinc metalloproteinase/disintegrin-like", "178.26", "42", "21", "20", "51345", "0", "BGLB040280-PA"], ["Endothelin-converting enzyme 1-like isoform X2", "111.23", "11", "6", "6", "56937", "0", "BGLB029484-PA"], ["DUF4347 domain-containing protein", "105.24", "34", "4", "4", "24685", "9.89E−168", "BGLB031575-PA"], ["Solute carrier family 35-member E4", "99.19", "26", "3", "3", "14320", "8.17E−89", "BGLB032352-PA"], ["Proactivator polypeptide-like", "91.36", "8", "6", "5", "68048", "0", "BGLB024213-PA"], ["Probable serine carboxypeptidase CPVL", "84.31", "9", "4", "4", "51401", "0", "BGLB030391-PA"], ["Phospholipase B1, membrane-associated-like", "79.92", "8", "3", "3", "44658", "0", "BGLB030448-PB"], ["Chitinase-like protein PB1E7.04c", "78", "4", "4", "2", "117976", "0", "BGLB017725-PA"], ["Endothelin-converting enzyme 2-like", "73.3", "13", "2", "2", "17072", "5.67E−106", "BGLB034604-PA"], ["Cathepsin L1-like", "39.16", "7", "2", "2", "26721", "0", "BGLB006210-PB"], ["Collagen alpha-3(VI) chain-like isoform X1", "35.7", "3", "1", "1", "34307", "0", "BGLB016458-PA"], ["Probable glutathione S-transferase 7", "35.27", "8", "2", "2", "23436", "9.5E−150", "BGLB004187-PC"], ["Mucin-like protein", "34.76", "0", "1", "1", "200228", "0", "BGLB016329-PA"], ["Bypass of stop codon protein 1-like", "34.45", "7", "1", "1", "16031", "8.96E−99", "BGLB034270-PA"], ["ADAM family mig-17-like", "32.27", "2", "1", "1", "51159", "0", "BGLB040281-PA"], ["Glyceraldehyde-3-phosphate dehydrogenasec", "27.37", "3", "1", "1", "25914", "1.03E−176", "BGLB010592-PB"]], "row_count": 17, "column_count": 8, "numeric_cells": 123, "header_rows": 1, "locator": "section[14]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:31521183:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:28e076176bd9eb610e31269526f0d67525e614327c3c44fbd8727aaca45a5ae6", "bytes": 1520, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab3", "version": null, "note": "A list of non-redundant S. mansoni ESPs identified in susceptible SCW. Details of sequence coverage, average mass, number of peptides and unique peptides and accession names are shown", "structure": {"pmcid": "PMC6744689", "section_index": 15, "section_title": "Schistosoma mansoni proteins identified from susceptible SCW of B. glabrata", "row_count": 14, "column_count": 8}, "table": {"label": "Table 3", "caption": "A list of non-redundant S. mansoni ESPs identified in susceptible SCW. Details of sequence coverage, average mass, number of peptides and unique peptides and accession names are shown", "rows": [["Description", "− 10lgP", "Coveragea (%)", "No. of peptides", "No. uniqueb", "Avg. mass", "BLASTp e-value", "Accession No."], ["Uncharacterised protein", "66.61", "8", "3", "3", "31951", "0", "Smp_179420.1"], ["Egg protein CP391B-like", "54.01", "6", "1", "1", "25520", "4.00E−157", "Smp_193380.1"], ["Glyceraldehyde-3-phosphate dehydrogenase", "44.08", "7", "3", "1", "33808", "0", "Smp_056970.4"], ["Putative zinc finger protein", "37.91", "1", "3", "1", "286355", "0", "Smp_132000.1"], ["Uncharacterised protein", "28.51", "19", "2", "2", "7535", "3.00E−41", "Smp_202190.1"], ["Uncharacterised protein", "21.49", "1", "1", "1", "228220", "0", "Smp_198230.1"], ["Uncharacterised protein", "21.43", "2", "1", "1", "48135", "0", "Smp_137420.1"], ["Putative nicotinate phosphoribosyltransferase", "20.87", "1", "1", "1", "60943", "0", "Smp_035460.1"], ["Tfiif-alpha", "20.19", "1", "1", "1", "92315", "0", "Smp_088460.1"], ["Uncharacterised protein", "20.01", "4", "1", "1", "28284", "0", "Smp_093980.1"], ["Uncharacterised protein", "19.55", "2", "1", "1", "47835", "0", "Smp_130330.1"], ["Proline–serine–threonine phosphatase interacting protein", "19.54", "1", "1", "1", "141331", "0", "Smp_028140.1"], ["Uncharacterised protein", "18.4", "1", "1", "1", "83862", "0", "Smp_142140.1"]], "row_count": 14, "column_count": 8, "numeric_cells": 94, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab3"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A two-way ANOVA test was used to calculate P-values and evaluate the significance of behavioural modifications in response to pH-neutral water, susceptible and F1 resistant SCW."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-protein interaction"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [41] partner repository with the dataset identifier PXD015129. Other datasets analysed in this study are included in this published article and its additional files."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:31521183", "asset:table:pmid:31521183:1", "asset:table:pmid:31521183:2", "asset:table:pmid:31521183:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:49:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 58373, "completion_tokens": 1298, "cached_tokens": 792}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:31521183", "type": "paper", "label": "pmid:31521183"}, {"id": "source:pmid:31521183", "type": "manuscript", "label": "PMID 31521183 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31521183", "type": "paper", "label": "pmid:31521183"}, {"id": "source:pmid:31521183", "type": "manuscript", "label": "PMID 31521183 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31521183", "type": "extraction", "used": ["source:pmid:31521183"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:31521183", "parent_hash": "sha256:4b46098488adf3f5e7af8ac1544dffdc401acc5c48bee404643593115e77ecc3", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["fractionated using SDS-PAGE, identified with LC-MS/MS and compared to naïve snail ESPs. Protein-pr", "thods Availability of data and materials The mass spectrometry proteomics data have been deposited to the P", "osensation, including naïve host preference. Proteomic technique advances enable sophisticated comp", "of data and materials The mass spectrometry proteomics data have been deposited to the ProteomeXcha"], "order_basis": "paper_text_order:445", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A two-way ANOVA test was used to calculate P-values and evaluate the significance of behavioural modifications in response to pH-neutral water, susceptible and F1 resistant SCW."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:15:03+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}}}