{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40141405", "kind": "science-record", "revision": 1, "content_hash": "sha256:412fecd546f321690638fa3ee0a2ecf1f6d3473644f6018282f4756ad47f138a", "created_at": "2026-11-01T10:25:50Z", "updated_at": "2026-11-01T10:25:50Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Seco-Duocarmycin SA in Aggressive Glioblastoma Cell Lines.", "doi": "10.3390/ijms26062766", "pmid": "40141405", "authors": null, "journal": "International journal of molecular sciences", "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:40141405"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40141405", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40141405' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40141405", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms26062766", "sha256": "sha256:f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms26062766", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40141405 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:40141405"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40141405"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "e5e776552621a1108fd9e596f718907f4345dcb3278b8116bb94c6487c48eade", "source_hash": "f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c", "raw_response_sha256": "sha256:27bf777ced8670b64ea4118b20895c18eccbb7b12047344008e17c4a01fed4c5", "raw_response_chars": 3999}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "5603fb944341673acc2d2bed163ca1a9e92cbdaedc93da717c63be9a2bacce9a", "source_hash": "f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c", "raw_response_sha256": "sha256:94db6be9bf9c220e5ef67cebb02a8ac26bca1666c5002674664e1fbf08c44b99", "raw_response_chars": 58065}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "e217017ef79eff5e397f010f6a1920d7136e2384aac6785996451b3adcc319e7", "source_hash": "f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c", "raw_response": "{\"parent_value\":48,\"unit\":\"proteins\",\"evidence\":\"In response to seco-DSA treatment, the most substantial differentially expressed proteins were unique to the cell cycle (48 proteins), followed by autophagy (45 proteins), suggesting that these cellular processes play a significant role in the cytotoxicity of seco-DSA.\",\"target_result\":\"48 proteins\",\"number_stated\":true}", "reading": {"parent_value": 48, "unit": "proteins", "evidence": "In response to seco-DSA treatment, the most substantial differentially expressed proteins were unique to the cell cycle (48 proteins), followed by autophagy (45 proteins), suggesting that these cellular processes play a significant role in the cytotoxicity of seco-DSA.", "target_result": "48 proteins", "number_stated": true, "source_locator": "chars 2906-3175 of source sha256 f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c"}, "recorded_at": "2026-10-31T15:36:19.843355+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "9704ffddcbf6d603f18dc21ed62fe394e870bfd09c1cb0aa912aa5c8f14941c1", "source_hash": "f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline numerical result paper states for main finding registered target. Source likely abstract says IC50 values lower but no exact values. Later proteomics numbers, 48 proteins etc. Need determine target likely headline numerical result for main finding. Maybe source text is partial, target wants numerical result paper itself states for registered target. Need extract exact contiguous quote with number. \"Furthermore, seco-DSA achieved its full cytotoxic effect within 8 h...\" Is 8 h headline numerical result main finding? Or proteomic finding \"most substantial ... cell cycle (48 proteins), followed by autophagy (45 proteins)\". Registered target phrased generic: \"the headline numerical result the paper states for its main finding\". We need infer from source. They ask \"single numerical result that a replication ... has to reproduce.\" Source has many numbers, but headline numerical likely perhaps 8 h. Need report number unit paper prints and quote clause whole attribution. Need think carefully.\n\nMaybe this is task from benchmark where source includes paper and target registered, perhaps target is an outcome from abstract, and ask exact number. We have title + abstract + sections. Main finding efficacy of seco-DSA in GBM cells. Abstract explicitly gives \"full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\" That's likely headline numeric result. Proteomics analysis is supplemental and numerical counts 48 proteins etc, but likely not headline result. Registered target deliberately says \"the headline numerical result the paper states for its main finding\", perhaps requires selecting one number. The phrase \"headline numerical result\" could point to 8 h as main finding in abstract. Yet title perhaps no exact IC50 values, only lower than natural counterpart. Single headline numerical result = 8 h.\n\nLet's parse wording: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nCould be a data extraction setup where target might refer to \"headline numerical result for main finding\". We need identify. In abstract: IC50 lower no values. Cell viability says sensitivity difference no numbers. Full cytotoxic effect within 8 h. This is only main finding with numerical value. Thus 8, unit \"h\" (paper prints \"8 h\"). Evidence exact contiguous quotation containing number, probably whole sentence: \"Furthermore, seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\" target_result concise same. JSON valid, no markdown.\n\nNeed ensure number type 8, unit \"h\" not \"hours\" because unit paper prints is h. Evidence exact quote. target_result perhaps \"seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\" Number stated true.\n\nBut let's not rush. Could headline numerical result refer to proteomics main finding: \"most substantial differentially expressed proteins were unique to the cell cycle (48 proteins), followed by autophagy (45 proteins)\". The main finding of paper perhaps mechanism due cell cycle disruption; in proteomics analysis, headline result 48 proteins. However title main finding may be cytotoxicity and mechanism. There is also dose 0.1 nM. Which is \"headline numerical result\"? Need infer likely evaluation expectations. Perhaps user wants \"single numerical result that a replication of registered target has to reproduce\" from article. The registered target isn't a named metric but generic descriptor. Maybe generated from a question like \"What was the IC50?\" Yet source omits actual IC50. They warn if no number, say false and what text states. Could be trick: abstract says IC50 values lower than natural DSA counterpart but no actual numbers; if registered target means headline numerical result perhaps maybe expected to find 8 h. Why include all these details? Let's understand source structure.\n\nTitle \"Seco-Duocarmycin SA in Aggressive Glioblastoma Cell Lines\". Abstract states:\n- efficacy seco-DSA novel DNA alkylating\n- colony assay IC50 values lower than natural DSA\n- cell viability LN18 more sensitive to DSA than T98G\n- full cytotoxic effect within 8 h\n- concentration-dependent apoptosis, not fully explain viability\n- significant cell cycle arrest S/G2/M\n- mechanism primarily disruption cell cycle\n- proteomic dysregulation proteins senescence apoptosis DNA repair\n- dataset ID.\n\nThen methods/proteomics findings. The \"headline numerical result\" in title/abstract is indeed 8 h. They might expect 8 h. The proteomic counts are not abstract's headline and section 2.7 perhaps from results but less central.\n\n\"Registered target: the headline numerical result the paper states for its main finding\" seems intentionally broad, perhaps an evaluator asks us to select a numerical result. Single numerical result likely a \"time to full cytotoxic effect\". A replication would reproduce 8 h. Use exact quote.\n\nCould parent_value perhaps 8.0? JSON number 8.\n\nNeed target_result not paraphrase? Only evidence exact quote constraints; target_result can concise. Could quote it as well. Ensure evidence exact, contiguous. Let's verify punctuation and Unicode: SOURCE: \"Furthermore, seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\" Use curly apostrophe irrelevant. Exact.\n\nUnit perhaps \"h\" as printed. target_result perhaps \"Full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\" This states result.\n\nReturn object only.</think>\n\n{\"parent_value\":8,\"unit\":\"h\",\"evidence\":\"Furthermore, seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\",\"target_result\":\"Full cytotoxic effect within 8 h of drug incubation in GBM cell lines.\",\"number_stated\":true}", "reading": {"parent_value": 8, "unit": "h", "evidence": "Furthermore, seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.", "target_result": "Full cytotoxic effect within 8 h of drug incubation in GBM cell lines.", "number_stated": true, "source_locator": "chars 610-715 of source sha256 f6acce6e87f070ec5e6bb23e118c7b4f78bcc9ff6dbdecf29b4059129dfa757c"}, "recorded_at": "2026-10-31T15:36:27.139460+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "seco-DSA achieved its full cytotoxic effect within 8 h of drug incubation in GBM cell lines.", "minimax_alt": "In response to seco-DSA treatment, the most substantial differentially expressed proteins were unique to the cell cycle (48 proteins), followed by autophagy (45 proteins), suggesting that these cellular processes play a significant role in the cytotoxicity of seco-DSA.", "decisive": false}, "physical_methods": {"minimax": ["Colony formation assay", "Cell viability assay", "Apoptosis assay", "Flow cytometry with FxCycle PI/RNase staining", "LC-MS/MS proteomic analysis"], "minimax_alt": ["Protein isolation and LC-MS/MS proteomic analysis of treated and control LN18 cells", "Cell-cycle analysis by flow cytometry after FxCycleTM PI/RNase staining using a MACSQuant® Analyzer 10 cytometer", "Colony formation assay", "Cell viability assay"], "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis using log-fold change relative to control peak intensity", "clusterProfiler biological processes ontology annotation", "UpSetR visualization", "Two-tailed unpaired t-test"], "minimax_alt": ["Differential expression analysis of LC-MS/MS peak-intensity data using Log-Fold Change values relative to control, with a baseline threshold of 2 LFC", "Biological-process ontology annotation of differentially expressed proteins using clusterProfiler in R version 4.4.1", "UpSet-plot visualization using UpSetR", "FlowJo software analysis of flow-cytometry cell-cycle data"], "decisive": false}, "statistical_method": {"minimax": "Two-tailed unpaired t-test", "minimax_alt": "", "decisive": true}, "parent_value": {"minimax": 48, "minimax_alt": 8, "decisive": true}, "unit": {"minimax": "proteins", "minimax_alt": "h", "decisive": true}}, "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": []}}, {"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"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:04ea4e69abb23903d64ef29fdf14225d27527134f789f63b65da8be092b9e270", "type": "sep_package", "label": "SEP v1 package for pmid:40141405"}], "activities": [{"id": "activity:conversion:pmid:40141405", "type": "conversion", "used": ["package:04ea4e69abb23903d64ef29fdf14225d27527134f789f63b65da8be092b9e270"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"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": "326c10b6-3e65-442b-9699-e7587aa3f12e", "parent_hash": "04ea4e69abb23903d64ef29fdf14225d27527134f789f63b65da8be092b9e270", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40141405 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40141405' 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":"2026-11-04T02:36:25+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}}}