{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38972051", "kind": "science-record", "revision": 2, "content_hash": "sha256:3e39482f98d82ee1de30bd8f36f49bb4414e2379ba2b49e5cb9571dee58e5cf2", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:32Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Piperine inhibits the proliferation of colorectal adenocarcinoma by regulating ARL3-mediated endoplasmic reticulum stress.", "doi": "10.17305/bb.2024.10525", "pmid": "38972051", "authors": null, "journal": "Biomolecules & biomedicine", "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:38972051"], "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:38972051", "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:38972051' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38972051", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.17305/bb.2024.10525", "sha256": "sha256:cb1f4880a42866e4bb158d938e17559a190699788f37e891ffdcfa49a4cdeee8", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.17305/bb.2024.10525", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:38972051:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:03ffd2e24e512e1397bc40b0f74eee6597871ae546f629557844e54547d3d8e7", "bytes": 1419, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#TB1", "version": null, "note": "Comparison of characteristics of the COAD patients with high and low ARL3 expression", "structure": {"pmcid": "PMC11734826", "section_index": 24, "section_title": "Supplemental data", "row_count": 48, "column_count": 5}, "table": {"label": "Table S1", "caption": "Comparison of characteristics of the COAD patients with high and low ARL3 expression", "rows": [["Parameter", "N", "ARL3-high", "ARL3-low", "P value"], ["Status"], ["Alive", "353", "186", "167", ""], ["Dead", "102", "42", "60", "0.053"], ["Gender"], ["Female", "215", "104", "111", ""], ["Male", "240", "124", "116", "0.543"], ["Race"], ["Asian", "11", "6", "5", ""], ["Black", "60", "24", "36", ""], ["White", "212", "118", "94", "0.099"], ["T stage"], ["T1", "11", "10", "1", ""], ["T2", "77", "44", "33", ""], ["T3", "310", "144", "166", ""], ["T4", "28", "13", "15", ""], ["T4a", "19", "12", "7", ""], ["T4b", "9", "5", "4", ""], ["Tis", "1", "", "1", "0.034"], ["N stage"], ["N0", "268", "137", "131", ""], ["N1", "73", "35", "38", ""], ["N1a", "15", "14", "1", ""], ["N1b", "15", "7", "8", ""], ["N1c", "2", "1", "1", ""], ["N2", "61", "22", "39", ""], ["N2a", "8", "4", "4", ""], ["N2b", "13", "8", "5", "0.017"], ["M stage"], ["M0", "333", "170", "163", ""], ["M1", "52", "20", "32", ""], ["M1a", "9", "5", "4", ""], ["M1b", "3", "1", "2", ""], ["MX", "51", "27", "24", "0.474"], ["TNM stage"], ["I", "74", "45", "29", ""], ["II", "30", "15", "15", ""], ["IIA", "136", "66", "70", ""], ["IIB", "10", "5", "5", ""], ["IIC", "1", "1", "", ""], ["III", "20", "3", "17", ""], ["IIIA", "8", "6", "2", ""], ["IIIB", "59", "31", "28", ""], ["IIIC", "41", "22", "19", ""], ["IV", "45", "16", "29", ""], ["IVA", "17", "9", "8", ""], ["IVB", "2", "1", "1", ""], ["IA", "1", "", "1", "0.034"]], "row_count": 48, "column_count": 5, "numeric_cells": 124, "header_rows": 1, "locator": "section[24]/table-wrap[1]#TB1"}}], "gaps": ["asset:source:pmid:38972051 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:38972051", "asset:table:pmid:38972051:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:38972051"]}, "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": "52f57c0e12e645a8828e1bd786a8f69f19d64ae46cc55edbc8136443d6e57ed1", "source_hash": "cb1f4880a42866e4bb158d938e17559a190699788f37e891ffdcfa49a4cdeee8", "raw_response_sha256": "sha256:49bf3b3bcc9b875b6415b0eb9a5361cf10020d6648d8b61a4925df167d0b1e81", "raw_response_chars": 5660}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "ee54319b405d2aa042ee7254c5e97b6cadba5541e967fc3f0f234a796cb536d7", "source_hash": "cb1f4880a42866e4bb158d938e17559a190699788f37e891ffdcfa49a4cdeee8", "raw_response_sha256": "sha256:d69c00d1df3341cfe8d361948536a4f6623b85a3d8f640596a2fa3f90f6279d1", "raw_response_chars": 39384}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "b57399ed32180967a2e451e5db3ad798576b288b286e18c500b7240e6ce740b4", "source_hash": "cb1f4880a42866e4bb158d938e17559a190699788f37e891ffdcfa49a4cdeee8", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"No headline numerical result is stated for the main finding. The text instead reports that Piperine inhibited COAD cell proliferation in a concentration- and time-dependent manner, induced S-phase cell cycle arrest and apoptosis, downregulated ARL3 expression, suppressed TGF-β-induced EMT, and attenuated ARL3-mediated ER stress.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "No headline numerical result is stated for the main finding. The text instead reports that Piperine inhibited COAD cell proliferation in a concentration- and time-dependent manner, induced S-phase cell cycle arrest and apoptosis, downregulated ARL3 expression, suppressed TGF-β-induced EMT, and attenuated ARL3-mediated ER stress.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:17:19.317882+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "77440e9e7cc1a27bd2e1b86e3cc521f1de5e28d69a84fdf2f6b44b4a3e570b42", "source_hash": "cb1f4880a42866e4bb158d938e17559a190699788f37e891ffdcfa49a4cdeee8", "raw_response": "<think>We need answer JSON object. Need inspect source. User asks single numerical result replication registered target headline numerical result paper states for main finding. Source is abstract/conclusion, no specific headline numerical result except P&lt;0.05, maybe thresholds, datasets names contain numbers (GSE39582 etc). Need determine no number for registered target, output false parent 0 unit/evidence empty and target_result say what text states instead. Need ensure exact schema, JSON valid. We need reason whether \"P &lt; 0.05\" is a numerical result? Registered target headline numerical result paper states for main finding. The source doesn't state actual result value, only qualitative findings and statistical threshold. They explicitly instruct if text states no number for registered target, false. likely answer.\n\nNeed formulate target_result perhaps \"The text states that Piperine inhibits COAD cell proliferation in a concentration- and time-dependent manner, induces S-phase arrest and apoptosis, downregulates ARL3, suppresses TGF-β-induced EMT, and attenuates ARL3-mediated ER stress; it reports only a statistical-significance threshold (P &lt; 0.05), not a headline numerical result.\" Is mentioning P &lt; 0.05 potentially evidence? unit empty. They ask say what text does state instead. We can state no numerical result, qualitative findings. Need perhaps avoid quote requirement irrelevant when false. JSON only.\n\nLet's parse wording: \"Read 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 text's own wording... If text states no number for 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\nSource has \"P &lt; 0.05\" and \"mean ± standard deviation (SD)\" but no headline numerical effect. Need false. target_result could be concise: \"No headline numerical result is stated; the text reports that Piperine treatment inhibited COAD cell proliferation in a concentration- and time-dependent manner, reduced Ki-67 levels and colony-forming ability, induced S-phase arrest and apoptosis, downregulated ARL3, suppressed TGF-β-induced EMT, and attenuated ARL3-mediated ER stress.\" This is based text. Should we mention P threshold? They ask what text states instead perhaps state qualitative findings, not threshold perhaps threshold is numerical but not target result. Could include \"It reports qualitative findings ... and gives P &lt; 0.05 only as the statistical-significance threshold.\" This makes clear. Evidence empty exactly.\n\nNeed output required fields. parent_value number 0. unit \"\". evidence \"\". number_stated false. target_result string. Ensure no extra properties. Could target result quote? No need. Let's formulate.\n\nBut need consider possibility registered target \"headline numerical result the paper states for its main finding\" perhaps abstract omitted results section and numerical result is P&lt;0.05? They may expect find \"P &lt; 0.05\" as only numerical result? Let's deeply assess task patterns. This likely benchmark asks extract target number from paper source, often registered target generated from article metadata, source text perhaps abstract. Need identify numeric headline result. Here source text explicitly includes no percentages or quantitative values, only \"P &lt; 0.05\" in statistical analysis. Instructions emphasize if no number, false. So yes.\n\nNeed perhaps target_result say \"The text reports qualitative effects of Piperine ... but no numerical headline result for the main finding.\" Good.\n\nLet's ensure JSON escapes perhaps no special issue. Final only JSON.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"No headline numerical result is stated for the main finding. The text reports that Piperine treatment inhibited COAD cell proliferation in a concentration- and time-dependent manner, reduced Ki-67 levels and colony-forming ability, induced S-phase cell-cycle arrest and apoptosis, downregulated ARL3 expression, suppressed TGF-β-induced EMT, and attenuated ARL3-mediated ER stress; P < 0.05 is given only as the statistical-significance threshold.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "No headline numerical result is stated for the main finding. The text reports that Piperine treatment inhibited COAD cell proliferation in a concentration- and time-dependent manner, reduced Ki-67 levels and colony-forming ability, induced S-phase cell-cycle arrest and apoptosis, downregulated ARL3 expression, suppressed TGF-β-induced EMT, and attenuated ARL3-mediated ER stress; P < 0.05 is given only as the statistical-significance threshold.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:17:26.132537+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "No headline numerical result is reported in the supplied text. The main finding is that Piperine inhibits colorectal adenocarcinoma cell proliferation and exerts anti-cancer effects by downregulating ARL3, inducing S-phase arrest and apoptosis, suppressing EMT, and attenuating ARL3-mediated endoplasmic reticulum stress.", "minimax_alt": "unknown (no headline numerical value is reported); Piperine treatment inhibited COAD cell proliferation in a concentration- and time-dependent manner, as indicated by reduced Ki-67 levels and decreased colony-forming ability.", "decisive": false}, "physical_methods": {"minimax": ["Immunohistochemistry using Human Protein Atlas data", "Cell proliferation assay", "Colony-forming assay", "Ki-67 measurement", "Cell-cycle analysis", "Apoptosis assay", "Western blot analysis of Bax, Bcl-2, cleaved caspase-3, cleaved PARP, BiP, p-IRE1α, ATF6, and CHOP", "Piperine treatment of COAD cells", "TGF-β-induced EMT analysis"], "minimax_alt": ["COAD cells were treated with Piperine, and in vitro assays evaluated cell proliferation, apoptosis, EMT marker expression, and ER stress (ERS) responses.", "Piperine treatment inhibited COAD cell proliferation in a concentration- and time-dependent manner, as indicated by reduced Ki-67 levels and decreased colony-forming ability.", "Piperine induced S-phase cell cycle arrest and facilitated apoptosis in COAD cells, evidenced by changes in Bax, Bcl-2, cleaved caspase-3, and cleaved Poly (ADP-ribose) polymerase (PARP) levels.", "Moreover, Piperine downregulated ARL3 expression in COAD cells, thereby suppressing transforming growth factor beta (TGF-β)-induced EMT.", "Additionally, Piperine attenuated the ARL3-mediated ER stress response, significantly reducing binding immunoglobulin protein (BiP), inositol-requiring enzyme 1 alpha (p-IRE1α), activating transcription factor 6 (ATF6), and C/EBP homologous protein (CHOP) levels."], "decisive": false}, "analysis_methods": {"minimax": ["Bioinformatics analysis of The Cancer Genome Atlas (TCGA)–COAD, GSE39582, and GSE44861 datasets", "Prognostic and clinicopathological association analysis", "R statistical analysis using the Limma package"], "minimax_alt": ["Bioinformatics analysis of The Cancer Genome Atlas (TCGA)–COAD, GSE39582, and GSE44861 datasets assessed ARL3 expression levels.", "Immunohistochemical data from the Human Protein Atlas (HPA) database confirmed ARL3 overexpression in COAD.", "The association of ARL3 with COAD clinical parameters and prognosis was also examined.", "Statistical analysis was performed using the R program with the R package “Limma.”"], "decisive": false}, "statistical_method": {"minimax": "For comparisons between two independent groups, the student's t-test was used. Multiple-group comparisons used one-way ANOVA paired with the Tukey post hoc test, and non-parametric paired data were analyzed with the Wilcoxon matched pairs signed rank test.", "minimax_alt": "The paper reports R with the “Limma” package, student’s t-test for comparisons between two independent groups, one-way ANOVA paired with the Tukey post hoc test for multiple-group comparisons, and the Wilcoxon matched pairs signed rank test for non-parametric paired data; significance was defined as P < 0.05. The supplied text does not explicitly map one of these methods to the unavailable headline numerical target.", "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:b53c78f75fe7b2cf6e22d34ac226a68b245b7cd3e9e5d17537701839d4922d9c", "type": "sep_package", "label": "SEP v1 package for pmid:38972051"}], "activities": [{"id": "activity:conversion:pmid:38972051", "type": "conversion", "used": ["package:b53c78f75fe7b2cf6e22d34ac226a68b245b7cd3e9e5d17537701839d4922d9c"], "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": "pmid:38972051", "parent_hash": "sha256:5f9ca2ceb64b2aff88d91e983c51e028c207814fb5bfb1661d837de0a33a7692", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:38972051 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:38972051' 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":"2026-11-04T01:48:55+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}}}