{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29991752", "kind": "science-record", "revision": 4, "content_hash": "sha256:693c2ce82ef08395f87d6771dbd6d44d50aea89331e51504164b55527b1935c7", "created_at": "2026-11-01T15:40:35Z", "updated_at": "2026-11-01T21:21:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Hydrothermal chimneys host habitat-specific microbial communities: analogues for studying the possible impact of mining seafloor massive sulfide deposits.", "doi": "10.1038/s41598-018-28613-5", "pmid": "29991752", "authors": ["Yuchen Han", "Giorgio Gonnella", "Nicole Adam", "Axel Schippers", "Lia Burkhardt", "Stefan Kurtz", "Ulrich Schwarz-Schampera", "Henrike Franke", "Mirjam Perner"], "journal": "Scientific reports", "year": 2018, "abstract": "To assess the risk that mining of seafloor massive sulfides (SMS) from extinct hydrothermal vent environments has for changing the ecosystem irreversibly, we sampled SMS analogous habitats from the Kairei and the Pelagia vent fields along the Indian Ridge. In total 19.8 million 16S rRNA tags from 14 different sites were analyzed and the microbial communities were compared with each other and with publicly available data sets from other marine environments. The chimneys appear to provide habitats for microorganisms that are not found or only detectable in very low numbers in other marine habitats. The chimneys also host rare organisms and may function as a vital part of the ocean's seed bank. Many of the reads from active and inactive chimney samples were clustered into OTUs, with low or no resemblance to known species. Since we are unaware of the chemical reactions catalyzed by these unknown organisms, the impact of this diversity loss and bio-geo-coupling is hard to predict. Given that chimney structures can be considered SMS analogues, removal of sulfide deposits from the seafloor in the Kairei and Pelagia fields will most likely alter microbial compositions and affect element cycling in the benthic regions and probably beyond.", "claims": [{"id": "claim-method", "statement": "The UPGMA clustering of the samples, based on beta diversity analyses, yielded quite different results depending on whether de novo and/or reference-based OTUs were considered and whether the Sørensen-Dice or Bray-Curtis index was used for analyses (Fig. 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29991752", "locator": "sections[9] \"Specificity and relatedness of the different Kairei and Pelagia communities\" paragraph 2", "quote": "The UPGMA clustering of the samples, based on beta diversity analyses, yielded quite different results depending on whether de novo and/or reference-based OTUs were considered and whether the Sørensen-Dice or Bray-Curtis index was used for analyses (Fig. 1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Sequence data have been deposited in the National Center for Biotechnology Information Sequence Read Archive (SRA) under accession no. SRP120106.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29991752", "locator": "sections[21] \"Data availability\" paragraph 2", "quote": "Sequence data have been deposited in the National Center for Biotechnology Information Sequence Read Archive (SRA) under accession no. SRP120106."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using beta-diversity analyses of 19.8 million 16S rRNA tags from 14 sites, compared with publicly available marine datasets, the study found that hydrothermal chimneys host habitat-specific microorganisms and that their removal by SMS mining would most likely alter microbial compositions and affect element cycling.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29991752", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In total 19.8 million 16S rRNA tags from 14 different sites were analyzed and the microbial communities were compared with each other and with publicly available data sets from other marine environments."}, {"asset": "source:pmid:29991752", "locator": "sections[2] \"Results and Discussion\" paragraph 2", "quote": "Using beta diversity analyses we investigated the similarities and dissimilarities among the samples in the Kairei and Pelagia environments and illustrated their relation to samples from comparable biotopes available from the literature."}, {"asset": "source:pmid:29991752", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Given that chimney structures can be considered SMS analogues, removal of sulfide deposits from the seafloor in the Kairei and Pelagia fields will most likely alter microbial compositions and affect element cycling in the benthic regions and probably beyond."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Using beta-diversity analyses of 19.8 million 16S rRNA tags from 14 sites, compared with publicly available marine datasets, the study found that hydrothermal chimneys host habitat-specific microorganisms and that their removal by SMS mining would most likely alter microbial compositions and affect element cycling.", "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:29991752"], "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_unresolved", "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:SRP120106"], "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": ["data:geo:SRP120106"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29991752", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-018-28613-5", "sha256": "sha256:e4d8c7b588f414bb6b4f5c4c9ec72689d864d75b8ce0ca2ac363ba695921bd7e", "bytes": 66717, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-018-28613-5", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6039533", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:SRP120106", "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=SRP120106", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP120106", "version": null, "note": "Sequence data have been deposited in the National Center for Biotechnology Information Sequence Read Archive (SRA) under accession no. SRP120106.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Sequence data have been deposited in the National Center for Biotechnology Information Sequence Read Archive (SRA) under accession no. SRP120106.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29991752:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f73fd33000ff761fcde12fbd65f26c6d08abe24cc0ad5af310350d8634929386", "bytes": 1575, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Semi-quantitative distribution of sulfide minerals and main element compositions of hydrothermal precipitates from the Kairei and Pelagia hydrothermal vent fields.", "structure": {"pmcid": "PMC6039533", "section_index": 3, "section_title": "Mineralogical and geochemical relations of hydrothermal precipitates", "row_count": 10, "column_count": 5}, "table": {"label": "Table 1", "caption": "Semi-quantitative distribution of sulfide minerals and main element compositions of hydrothermal precipitates from the Kairei and Pelagia hydrothermal vent fields.", "rows": [["Sample", "", "Semi-quantitative mineral composition", "Quantitative main element composition", "Description"], ["Kairei area"], ["INDEX2016-06ROV03-A", "S1", "ccp+++py/mrc+sp++", "Cu: 12.6–25.8 wt.%Fe: 18.5–25.6 wt.%Zn: 10.3–29.7 wt.%", "fragment of inactive chimney,Kairei active zone"], ["INDEX2016-06ROV03-N", "S2", "ccp 0py/mrc+++sp+++iso 0", "Cu: 0.3–0.4 wt.%Fe: 23.8–28.3 wt.%Zn: 28.9–31.7 wt.%", "inactive beehive shaped chimney,Kairei inactive zone"], ["INDEX2016-12ROV06-E", "S7", "ccp +++py/mrc+sp++", "Cu: 18.1–26.2 wt.%Fe: 21.2–28.4 wt.%Zn: 6.8–24.3 wt.%", "inactive chimney edifice,Kairei active zone"], ["INDEX2016-12ROV06-F", "S8", "ccp+++py/mrc+sp++anh 0", "Cu: 25.3–26.5 wt.%Fe: 27.1–29.0 wt.%Zn: 6.5–10.7 wt.%", "fragment of active chimney,Kairei HF"], ["Pelagia area"], ["INDEX2016-16ROV08-E", "S5", "ccp+py/mrc+++sp +", "Cu: 1.3–7.4 wt.%Fe: 33.3–44.4 wt.%Zn: 0.9–12.2 wt.%", "active beehive shaped chimney,Pelagia HF"], ["INDEX2016-20ROV10-G", "S6", "ccp 0py/mrc+++po+sp++iso +", "Cu: 1.5–1.7 wt.%Fe: 41.5–42.2 wt.%Zn: 7.0–7.1 wt.%", "fragment of active chimney,Pelagia HF"], ["INDEX2016-20ROV10-J", "S4", "ccp 0py/mrc+++sp+", "Cu: 0.1–0.8 wt.%Fe: 29.9–36.2 wt.%Zn: 0.5–3.3 wt.%", "fragment of beehive shaped inactive chimney,Pelagia HF"]], "row_count": 10, "column_count": 5, "numeric_cells": 18, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:29991752:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5f38b07c8665e9533508808528bd0db110cf56a247bfb6ba0c5d056373be1621", "bytes": 1855, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab2", "version": null, "note": "Total cell counts and number of analyzed 16S rRNA genes.", "structure": {"pmcid": "PMC6039533", "section_index": 4, "section_title": "Bacterial and archaeal communities of the Kairei and Pelagia areas", "row_count": 20, "column_count": 6}, "table": {"label": "Table 2", "caption": "Total cell counts and number of analyzed 16S rRNA genes.", "rows": [["Sample name", "Sample name", "Location and sample types", "Cell number per ml", "Number of 16S rRNA sequences"], ["bacteria", "archaea"], ["open ocean sample"], ["INDEX2016-01PS", "RF1", "sea water, depth 2180 m, approx. 10 km away from Kairei venting site", "1.62E +04 ± 3.61E+03", "631890", "766553"], ["INDEX2016-15PS", "RF4", "sea water, depth 3566 m; approx. 10 km away from Pelagia venting site", "1.30E +04 ± 1.56E+03", "679918", "641362"], ["Kairei area"], ["INDEX2016-09PS", "F5", "water sample from just above the plume, 2327 m depth", "1.50E +04 ± 1.80E+03", "815297", "879790"], ["INDEX2016-06ROV-03-KIPS-B", "F1", "low temperature hydrothermal diffuse fluids (23 °C)", "1.23E +05 ± 5.74E+04", "757618", "940285"], ["INDEX2016-12ROV06-F", "S8", "active chimney", "no data", "542480", "315288"], ["INDEX2016-06ROV03-A", "S1", "inactive chimney, Kairei active zone", "no data", "920258", "1140926"], ["INDEX2016-06ROV-03-N", "S2", "inactive chimney, Kairei inactive zone", "no data", "619471", "no data"], ["INDEX2016-12ROV06-E", "S7", "inactive chimney, Kairei active zone", "no data", "575095", "504492"], ["Pelagia area"], ["INDEX2016-17PS plume max", "F9", "plume water sample, 3643 m depth", "1.38E +04 ± 8.01E+03", "897847", "1044117"], ["INDEX2016-16ROV08-B", "S3", "sulfide talus", "no data", "921885", "853219"], ["INDEX2016-16ROV08-KIPS-B", "F6", "hydrothermal diffuse fluid (153 °C)", "3.89E +04 ± 4.29E+03", "980269", "966748"], ["INDEX2016-16ROV08-E", "S5", "active chimney", "no data", "637597", "420015"], ["INDEX2016-20ROV10-G", "S6", "active chimney", "no data", "600895", "422585"], ["INDEX2016-20ROV10-J", "S4", "inactive chimney", "no data", "717195", "697248"], ["TOTAL", "", "", "", "10297715", "9592628"]], "row_count": 20, "column_count": 6, "numeric_cells": 56, "header_rows": 2, "locator": "section[4]/table-wrap[1]#Tab2"}}], "gaps": ["asset:data:geo:SRP120106 not downloaded", "asset:data:geo:SRP120106 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "UPGMA clustering based on beta diversity analyses using Sørensen-Dice and Bray-Curtis distances", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The UPGMA clustering of the samples, based on beta diversity analyses, yielded quite different results depending on whether de novo and/or reference-based OTUs were considered and whether the Sørensen-Dice or Bray-Curtis index was used for analyses (Fig. 1)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (UPGMA clustering based on beta diversity analyses using Sørensen-Dice and Bray-Curtis distances), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["SRP120106"], "resolved_accessions": [], "statements": ["Sequence data have been deposited in the National Center for Biotechnology Information Sequence Read Archive (SRA) under accession no. SRP120106."], "basis": "The paper names SRP120106, but the accession does not resolve in the repository (not_in_ncbi_sra), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29991752", "data:geo:SRP120106", "asset:table:pmid:29991752:1", "asset:table:pmid:29991752:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:SRP120106"]}, "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": "2026-10-31T18:34:56Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 138557, "completion_tokens": 3855, "cached_tokens": 2088}}, "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:29991752", "type": "paper", "label": "pmid:29991752"}, {"id": "source:pmid:29991752", "type": "manuscript", "label": "PMID 29991752 full text"}, {"id": "data:geo:SRP120106", "type": "dataset", "label": "GEO SRP120106"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29991752", "type": "paper", "label": "pmid:29991752"}, {"id": "source:pmid:29991752", "type": "manuscript", "label": "PMID 29991752 full text"}, {"id": "data:geo:SRP120106", "type": "dataset", "label": "GEO SRP120106"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29991752", "type": "extraction", "used": ["source:pmid:29991752"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-SRP120106", "type": "accession_resolution", "used": ["data:geo:SRP120106"], "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:29991752", "parent_hash": "sha256:4839378d60dd7a03a1575b37e7d7aa7bf5d05385ba3f8f435a759afaaf5bfd53", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:SRP120106 licence not read", "asset:data:geo:SRP120106 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["long the Indian Ridge. In total 19.8 million 16S rRNA tags from 14 different sites were analyzed a"], "order_basis": "paper_text_order:389", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:16:43+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}}}