{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38465231", "kind": "science-record", "revision": 4, "content_hash": "sha256:6c5060c1c0f015c7d686fd9ca79e183f0907d8371a97f29fcfa6a72c212a4130", "created_at": "2026-11-01T19:20:24Z", "updated_at": "2026-11-01T22:11:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Placebo-resistant gut bacteria: Akkermansia muciniphila spp. and Familial Mediterranean fever disease.", "doi": "10.3389/fcimb.2024.1336752", "pmid": "38465231", "authors": ["Elya Pepoyan", "Francesco Marotta", "Anahit Manvelyan", "Artak Galstyan", "Lena Stepanyan", "Hasmik Grigoryan", "Liana Grigoryan", "Mikayel Mikayelyan", "Marine Balayan", "Natalya Harutyunyan", "Susanna Mirzabekyan", "Vardan Tsaturyan", "Tamas Torok", "Astghik Pepoyan"], "journal": "Frontiers in cellular and infection microbiology", "year": 2024, "abstract": "Introduction: Despite numerous investigations into the impact of drugs/probiotics on the gut microbiota composition in Familial Mediterranean Fever (FMF) patients, the question as to whether there exists a significant bacterial diversity(ies) independent of the placebo effect that can be reliably considered in clinical and nutritional trials remains unresolved.\nMethods: This study represents the in augural analysis of the placebo's influence on the gut microbiota of both healthy individuals and FMF afflicted men, utilizing previously collected data from PhyloChip™ DNA microarray experiments. A total of 15 healthy and 15 FMF male volunteers, aged 18 to 50, participated in this partially randomized placebo trial, which is accessible through the GEO Series accession number GSE111835.\nResults and Discussion: Key findings from current investigations include i. the anticipated divergence in gut bacteria resistance to placebo between healthy and FMF individuals, ii. the minor impact of placebo on gut bacterial diversities in healthy individuals, with Enterobacteriaceae diversities identified as placebo-resistant among \"healthy\" gut bacteria, and iii. the comprehensive influence of placebo on all bacterial phyla in the gut microbiome of FMF patients, extending to nearly all bacterial genera, except for the resilience of gut Akkermansia muciniphila spp. to placebo in FMF patients. This study underscores the susceptibility of Faecalibacterium, Blautia, and Clostridium genera to placebo. Consequently, this investigation holds significance for the proper design of placebo-controlled trials and establishes a foundation for further exploration of the gut-brain axis. Furthermore, it contributes valuable insights to discussions regarding proposals for probiotic therapies, particularly focusing on Faecalibacterium spp., Blautia spp., and Clostridium spp.", "claims": [{"id": "claim-method", "statement": "Student’s t-test and Mann-Whitney test were used for statistical analyses.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38465231", "locator": "sections[2] \"Materials and methods\" paragraph 7", "quote": "Student’s t-test and Mann-Whitney test were used for statistical analyses."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: GEO Series accession number GSE111835.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38465231", "locator": "sections[19] \"Data availability statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: GEO Series accession number GSE111835."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:38465231"], "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": "complete", "blocked_on": null, "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": ["data:geo:GSE111835"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_mann_whitney", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE111835"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_mann_whitney"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38465231", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcimb.2024.1336752", "sha256": "sha256:76d276272ad5823d7d7bb8563494ad5a60088802a5979a3039dbbba26bde6271", "bytes": 59384, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcimb.2024.1336752", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10920240", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE111835", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE111835", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE111835", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: GEO Series accession number GSE111835.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: GEO Series accession number GSE111835.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3040616", "GSM3040617", "GSM3040618", "GSM3040619", "GSM3040620", "GSM3040621", "GSM3040622", "GSM3040623", "GSM3040624", "GSM3040625", "GSM3040626", "GSM3040627", "GSM3040628", "GSM3040629", "GSM3040630", "GSM3040631", "GSM3040632", "GSM3040633", "GSM3040634", "GSM3040635", "GSM3040636", "GSM3040637", "GSM3040638", "GSM3040639", "GSM3040640", "GSM3040641", "GSM3040642", "GSM3040643", "GSM3040644", "GSM3040645", "GSM3040646", "GSM3040647", "GSM3040648", "GSM3040649", "GSM3040650", "GSM3040651", "GSM3040652", "GSM3040653", "GSM3040654", "GSM3040655", "GSM3040656", "GSM3040657", "GSM3040658", "GSM3040659", "GSM3040660", "GSM3040661", "GSM3040662", "GSM3040663", "GSM3040664", "GSM3040665", "GSM3040666", "GSM3040667", "GSM3040668", "GSM3040669", "GSM3040670", "GSM3040671", "GSM3040672", "GSM3040673", "GSM3040674", "GSM3040675", "GSM3040676", "GSM3040677", "GSM3040678", "GSM3040679", "GSM3040680", "GSM3040681", "GSM3040682", "GSM3040683", "GSM3040684", "GSM3040685", "GSM3040686", "GSM3040687", "GSM3040688", "GSM3040689", "GSM3040690", "GSM3040691", "GSM3040692", "GSM3040693", "GSM3040694", "GSM3040695", "GSM3040696", "GSM3040697", "GSM3040698", "GSM3040699", "GSM3040700", "GSM3040701", "GSM3040702", "GSM3040703", "GSM3040704", "GSM3040705", "GSM3040706", "GSM3040707", "GSM3040708", "GSM3040709", "GSM3040710", "GSM3040711", "GSM3040712", "GSM3040713", "GSM3040714", "GSM3040715", "GSM3040716", "GSM3040717", "GSM3040718", "GSM3040719", "GSM3040720", "GSM3040721", "GSM3040722", "GSM3040723", "GSM3040724", "GSM3040725", "GSM3040726", "GSM3040727", "GSM3040728", "GSM3040729", "GSM3040730", "GSM3040731", "GSM3040732", "GSM3040733", "GSM3040734", "GSM3040735", "GSM3040736", "GSM3040737", "GSM3040738", "GSM3040739", "GSM3040740", "GSM3040741", "GSM3040742", "GSM3040743", "GSM3040744", "GSM3040745", "GSM3040746", "GSM3040747", "GSM3040748", "GSM3040749", "GSM3040750", "GSM3040751", "GSM3040752", "GSM3040753", "GSM3040754", "GSM3040755", "GSM3040756", "GSM3040757", "GSM3040758", "GSM3040759", "GSM3040760", "GSM3040761", "GSM3040762", "GSM3040763", "GSM3040764", "GSM3040765", "GSM3040766", "GSM3040767", "GSM3040768", "GSM3040769", "GSM3040770", "GSM3040771", "GSM3040772", "GSM3040773", "GSM3040774", "GSM3040775", "GSM3040776", "GSM3040777", "GSM3040778", "GSM3040779", "GSM3040780", "GSM3040781"], "sample_count": 166, "group_sizes": null, "group_sizes_basis": null, "platform": "24736", "taxon": "human gut metagenome; Archaea; Bacteria", "title": "PhyloChip-based characterization of stool samples from Familial Mediterranean Fever patients and the effects of probiotic Lactobacillus acidophilus INMIA 9602 Er 317/402", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE111835 not downloaded", "asset:data:geo:GSE111835 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Student’s t-test and Mann-Whitney test were used for statistical analyses."}}], "targets": [], "gaps": ["method.group_comparison_mann_whitney"]}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: mann_whitney."}, "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": "R1", "reachable": true, "accessions": ["GSE111835"], "resolved_accessions": ["GSE111835"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: GEO Series accession number GSE111835."], "basis": "The paper names GSE111835 in GEO Series and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:38465231", "data:geo:GSE111835"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_mann_whitney", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE111835"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:11:35Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17752, "completion_tokens": 1013, "cached_tokens": 256}}, "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:38465231", "type": "paper", "label": "pmid:38465231"}, {"id": "source:pmid:38465231", "type": "manuscript", "label": "PMID 38465231 full text"}, {"id": "data:geo:GSE111835", "type": "dataset", "label": "GEO GSE111835"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38465231", "type": "paper", "label": "pmid:38465231"}, {"id": "source:pmid:38465231", "type": "manuscript", "label": "PMID 38465231 full text"}, {"id": "data:geo:GSE111835", "type": "dataset", "label": "GEO GSE111835"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38465231", "type": "extraction", "used": ["source:pmid:38465231"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE111835", "type": "accession_resolution", "used": ["data:geo:GSE111835"], "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:38465231", "parent_hash": "sha256:45a6709dfc6ff8d398b4e799ff70273215c1aae03e421d0718d856fde508d44b", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE111835 licence not read", "asset:data:geo:GSE111835 not downloaded", "execution.not_run", "method.group_comparison_mann_whitney", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_mann_whitney"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["reviously collected data from PhyloChip™ DNA microarray experiments. A total of 15 healthy and 15 FM", "lyzed by leveraging the prior PhyloChip™ DNA-microarray-based data (Tsaturyan et al., 2023; Pepoyan", "ation, culture-independent, high-density DNA microarray analysis (PhyloChip™; Affymetrix, Santa Clar", "density DNA microarray analysis (PhyloChip™; Affymetrix, Santa Clara, CA, USA), according to the inv"], "order_basis": "paper_text_order:633", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_trial", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ged 18 to 50, participated in this partially randomized placebo trial, which is accessible through the GEO Series", "holds significance for the proper design of placebo-controlled trials and establishes a foundation for furt", "5) aged 18 to 50 took part in this partially randomized placebo trial accessible through GEO Series accession numb"], "order_basis": "paper_text_order:753", "id": "assay:2"}, {"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ectrophoresis. gDNA was extracted/amplified (16S rRNA gene) from fecal materials frozen at -80оC.", "he primer sequences used for microarrays and 16S rRNA clone libraries were: 27f.jgi (Bacteria-spec"], "order_basis": "paper_text_order:3962", "id": "assay:3"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Student’s t-test and Mann-Whitney test were used for statistical analyses."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T03:10:59+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}}}