{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40933599", "kind": "science-record", "revision": 2, "content_hash": "sha256:1e582949c3c3cfb0f8da0d52bdb10df2223c21b229ca142a0fa62243721dfa1a", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "In silico prediction of paradoxical effect for oxaliplatin in gastric cancer patients based on their transcriptomic profile.", "doi": "10.4103/rps.rps_148_24", "pmid": "40933599", "authors": null, "journal": "Research in pharmaceutical 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:40933599"], "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:40933599", "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:40933599' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40933599", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.4103/rps.rps_148_24", "sha256": "sha256:e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.4103/rps.rps_148_24", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40933599:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:12075a45f74b374fbb61ee4ea27246c9f4f0f592b71d27a7bfc15ff0d23f3cd7", "bytes": 1607, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#RPS.RPS_148_24-T1", "version": null, "note": "Survival-related genes in gastric cancer patients.", "structure": {"pmcid": "PMC12419565", "section_index": 14, "section_title": "Survival analysis", "row_count": 26, "column_count": 6}, "table": {"label": "Table 1", "caption": "Survival-related genes in gastric cancer patients.", "rows": [["Gene", "Up/down-regulated", "|Log2FC*|", "Log-rank p", "Hazard ratio", "95% Confidence interval"], ["PDGFD", "Down", "1.27", "0.00008", "2.03", "1.43, 2.88"], ["SERPINE1", "Up", "2.21", "0.0005", "1.8", "1.31, 2.63"], ["PLCXD3", "Down", "1.98", "0.0006", "1.83", "1.30, 2.59"], ["PDK4", "Down", "2.74", "0.0009", "1.80", "1.27, 2.55"], ["RECK", "Down", "1.28", "0.0009", "1.80", "1.27, 2.55"], ["GHR", "Down", "2.17", "0.002", "1.72", "1.22, 2.43"], ["SLC16A7", "Down", "1.5", "0.002", "1.75", "1.23, 2.48"], ["COL4A5", "Down", "1.99", "0.003", "1.69", "1.19, 2.40"], ["PCDH7", "Down", "0.77", "0.008", "1.59", "1.13, 2.25"], ["ANGPT1", "Down", "1.5", "0.012", "1.55", "1.10, 2.20"], ["LRRC17", "Down", "0.69", "0.012", "1.55", "1.10, 2.19"], ["CTHRC1", "Up", "3.46", "0.01356", "1.54", "1.09, 2.17"], ["TEAD4", "Up", "1.49", "0.014", "0.65", "0.46, 0.92"], ["AFF3", "Down", "1.74", "0.015", "1.53", "1.09, 2.17"], ["PTGER3", "Down", "1.51", "0.016", "1.53", "1.08, 2.15"], ["CD36", "Down", "2.23", "0.020", "1.50", "1.06, 2.11"], ["ADAMTS1", "Down", "2.07", "0.022", "1.49", "1.06, 2.11"], ["JAM2", "Down", "1.96", "0.022", "1.49", "1.06, 2.11"], ["CLIC6", "Down", "1.46", "0.022", "1.50", "1.06, 2.12"], ["DMD", "Down", "1.96", "0.029", "1.47", "1.04, 2.07"], ["COL10A1", "Up", "6.87", "0.032", "1.46", "1.03, 2.05"], ["GPX3", "Down", "2.47", "0.038", "1.44", "1.02, 2.03"], ["ADH1B", "Down", "2.48", "0.040", "1.43", "1.02, 2.02"], ["CPE", "Down", "1.29", "0.040", "1.43", "1.02, 2.02"], ["SPP1", "Up", "3.95", "0.045", "1.42", "1.01, 2.00"]], "row_count": 26, "column_count": 6, "numeric_cells": 105, "header_rows": 1, "locator": "section[14]/table-wrap[1]#RPS.RPS_148_24-T1"}}, {"id": "asset:table:pmid:40933599:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:07daf5c47157a1336eccc799487bcbdd42cbf2f434896341f9f61582ac478b75", "bytes": 797, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#RPS.RPS_148_24-T2", "version": null, "note": "Comparison between the gastric cancer mRNA expression of genes associated with identified pathways, with the Comparative Toxicogenomics Database detected binary interactions between OXA and the same group of genes.", "structure": {"pmcid": "PMC12419565", "section_index": 15, "section_title": "Oxaliplatin-interacting genes", "row_count": 15, "column_count": 3}, "table": {"label": "Table 2", "caption": "Comparison between the gastric cancer mRNA expression of genes associated with identified pathways, with the Comparative Toxicogenomics Database detected binary interactions between OXA and the same group of genes.", "rows": [["Gene name", "OXA-mRNA interaction", "mRNA expression in gastric cancer"], ["BIRC5*", "Low", "High"], ["BLVRB**", "Low", "Low"], ["CAV1*", "High", "Low"], ["CDH2*", "High", "Low"], ["CDKN1A", "High/Low", "Low"], ["CDKN2A**", "High", "High"], ["IL6*", "High", "Low"], ["JUN*", "High", "Low"], ["MAPK3**", "Low", "Low"], ["PLAU**", "High", "High"], ["PTGS2**", "High", "High"], ["SERPINB2*", "High", "Low"], ["SERPINE1**", "High", "High"], ["TYMS*", "Low", "High"]], "row_count": 15, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[15]/table-wrap[1]#RPS.RPS_148_24-T2"}}], "gaps": ["asset:source:pmid:40933599 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:40933599", "asset:table:pmid:40933599:1", "asset:table:pmid:40933599:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40933599"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "9e4fae045a860a52920eab76f3c8730b69a07af166e71f8f06fb0a8e6764b445", "source_hash": "e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e", "raw_response_sha256": "sha256:d1515c5fc672afd0324bbe22e954b17f0c5def86a8c727e83efbbdc4c74a74cb", "raw_response_chars": 49475}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "7ce41e1f41ac1106a7e34eed883335c50a30e66de250971c859c5495472cabb5", "source_hash": "e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e", "raw_response": "{\"parent_value\":151,\"unit\":\"dysregulated genes\",\"evidence\":\"A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.\",\"target_result\":\"The paper’s headline main finding is that 151 dysregulated genes were identified across the datasets.\",\"number_stated\":true}", "reading": {"parent_value": 151, "unit": "dysregulated genes", "evidence": "A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.", "target_result": "The paper’s headline main finding is that 151 dysregulated genes were identified across the datasets.", "number_stated": true, "source_locator": "chars 969-1094 of source sha256 e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e"}, "recorded_at": "2026-10-31T15:35:10.052097+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "fd82112c4659287726f82381ffe19516a791ea592b584e8913860f32b92c237a", "source_hash": "e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e", "raw_response": "<think>We need answer JSON only. Need determine registered target headline numerical result paper states for main finding. Need identify single number likely 151 dysregulated genes? Main finding maybe OXA paradoxical effect, headline numerical result perhaps 13 genes? User asks \"single numerical result that a replication of the registered target has to reproduce\" and registered target \"the headline numerical result the paper states for its main finding\". Need infer from source. Abstract reports multiple numbers. Need choose headline likely \"A total of 151 dysregulated genes were identified across datasets, comprising 112 down and 39 up.\" Main finding perhaps 13 potential prognostic biomarkers? Or 14 overlapping OXA/DEGs? Or reversal of 7 and promotion of 6. Need parse intent.\n\nThey explicitly ask \"the value the paper itself states for the registered target, not a value you calculated...\" This perhaps benchmark asking extract main headline metric. Source is paper abstract/conclusion. Registered target vague but says headline numerical result paper states for its main finding. Which is \"151 dysregulated genes\" perhaps opening Results sentence. Need output parent_value number, unit printed, exact contiguous quote containing number, whole clause. Likely 151 genes.\n\nLet's examine wording: Paper's main finding: in silico predict paradoxical effects of OXA. Key numerical finding: \"OXA interacted with 97 genes, of which 14 were linked to both OXA and differentially expressed genes in GC.\" Then \"OXA potentially reversed expression of seven genes... while promoting six...\" The headline numerical result might be 14? Replication target? Registered target says \"the headline numerical result the paper states for its main finding\" perhaps intentionally asking to select one. They expect extraction from source. Need decide.\n\nCould headline number be \"151 dysregulated genes\" as first sentence and central overall result. In abstracts, result often starts total 151, and 13 prognostic. Main finding in title is paradoxical effect; direct result: OXA reverses 7 and promotes 6. But one \"single numerical result\" could be 13 genes reversed? Yet that's calculated if summing, forbidden. Paper states both seven and six, not a singular combined count. User says value paper itself states for registered target. Perhaps target result asks a standard \"parent_value\" from tables? Maybe context from a task framework: They ask \"find the single numerical result that a replication of registered target has to reproduce.\" Target likely extracted from a paper and could refer to a headline statistic. Here generic target descriptor. We need identify the paper's headline numerical result. Usually answer is the first/main count in abstract, 151 dysregulated genes. Unit \"genes\". Evidence exact contiguous quote. target_result likely prose \"A total of 151 dysregulated genes were identified across the datasets.\" number_stated true.\n\nNeed ensure JSON schema, parent_value 151, unit \"genes\", evidence exact quote perhaps \"A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.\" This number directly attached. Target_result maybe same or description. Since number stated true. Could mention \"151 dysregulated genes\". Exact quote no ellipsis.\n\nBut let's not rush. Need interpret \"registered target: the headline numerical result the paper states for its main finding\". Could be title/abstract's most headline result. Maybe \"13 genes emerged as potential prognostic biomarkers for overall survival.\" Since SERPINE1 main finding, but 13 count. Or \"SERPINE1 showed a strong correlation with overall survival\" no number. Therefore if target is main finding, perhaps headline numerical result is 13 prognostic biomarkers? Let's assess likely data-generation setup.\n\nThis appears one of extraction tasks where user provides target and source, asks numeric result. REGISTERED TARGET may be generic label due anonymization? They want a single headline result, perhaps from paper's abstract. Need rely source wording. The strongest broad headline is \"A total of 151 dysregulated genes...\" Typically the first sentence under Results is considered headline numerical result. The source has repeated Findings. Main finding actually OXA reversal of 7 genes and progression of 6. If replication of \"registered target\" means replicate headline numerical result, perhaps 151 genes is foundational result.\n\nMaybe \"parent_value\" suggests perhaps a hierarchical numerical extraction where parent value is a paper result and units. Registered target could be any row. They expect exactly one. We need output only JSON.\n\nLet's inspect units: \"151 dysregulated genes\" obvious unit. If 13, also genes. If 14, \"genes\". Need clue in wording: \"the headline numerical result the paper states for its main finding\" likely asks to find *the* single numerical result. In abstract, \"A total of 151 dysregulated genes...\" is clearly headline total. Other counts are component results. So 151.\n\nEvidence exact contiguous quotation from source, whole clause. Quote full sentence. target_result can say \"A total of 151 dysregulated genes were identified across the datasets.\"</think>\n\n{\"parent_value\":151,\"unit\":\"genes\",\"evidence\":\"A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.\",\"target_result\":\"A total of 151 dysregulated genes were identified across the datasets.\",\"number_stated\":true}", "reading": {"parent_value": 151, "unit": "genes", "evidence": "A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.", "target_result": "A total of 151 dysregulated genes were identified across the datasets.", "number_stated": true, "source_locator": "chars 969-1094 of source sha256 e274ee927538c21f339e925ae5cd3628ba881350ae27247e8b0aeb4f259cf15e"}, "recorded_at": "2026-10-31T15:35:15.545565+00:00"}], "agreement": false, "disagreements": {"unit": {"minimax": "dysregulated genes", "minimax_alt": "genes", "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": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted statement is absent from the supplied text", "raw_response": "{\"target_result\":\"OXA potentially reversed the expression of seven GC-associated genes and promoted the expression of six others; 14 genes were linked to both OXA and differentially expressed genes in GC, and SERPINE1 showed a strong correlation with overall survival.\",\"work_type\":\"analysis_only_for_target\",\"physical_methods\":[],\"analysis_methods\":[\"GEO2R\",\"DESeq2\",\"Comparative Toxicogenomics Database (CTD) interaction comparison\",\"Kaplan-Meier survival analysis\",\"Univariate survival analysis\",\"Maximal Clique Centrality (MCC)\",\"Pathway enrichment analysis with Bonferroni step-down correction\"],\"statistical_method\":\"GEO2R and DESeq2 for differential gene expression; Kaplan-Meier survival analysis with log-rank P-value and hazard ratio criteria for overall-survival association\",\"method_evidence\":\"Differential gene expression was identified using GEO2R and DESeq2. We utilized Kaplan-Meier survival curves to identify differentially expressed genes. Statistically significant thresholds were determined based on a log-rank P-value of less than 0.05 and a hazard ratio (HR) not equal to 1.\",\"repositories\":[{\"repository\":\"Gene Expression Omnibus (GEO)\",\"accession\":\"GSE26942\",\"data_description\":\"RNA-sequencing data used to analyze differentially expressed genes in gastric cancer.\",\"evidence\":\"RNA-sequencing data from GSE26942, GSE66229, and TCGA-STAD datasets were analyzed.\",\"publicly_downloadable\":false},{\"repository\":\"Gene Expression Omnibus (GEO)\",\"accession\":\"GSE66229\",\"data_description\":\"RNA-sequencing data used to analyze differentially expressed genes in gastric cancer.\",\"evidence\":\"RNA-sequencing data from GSE26942, GSE66229, and TCGA-STAD datasets were analyzed.\",\"publicly_downloadable\":false},{\"repository\":\"The Cancer Genome Atlas (TCGA)\",\"accession\":\"TCGA-STAD\",\"data_description\":\"TCGA stomach adenocarcinoma dataset used for differential expression and overall-survival analysis.\",\"evidence\":\"RNA-sequencing data from GSE26942, GSE66229, and TCGA-STAD datasets were analyzed.\",\"publicly_downloadable\":false}],\"availability_statement\":\"\",\"data_on_request\":false,\"source_claims\":[\"A total of 151 dysregulated genes were identified across the datasets, comprising 112 downregulated and 39 upregulated genes.\",\"OXA interacted with 97 genes, of which 14 were linked to both OXA and differentially expressed genes in GC.\",\"OXA potentially reversed the expression of seven genes associated with GC progression (BIRC5, CAV1, CDH2, IL6, JUN, SERPINB2, TYMS), while promoting the expression of six others (BLVRB, CDKN2A, MAPK3, PLAU, PTGS2, SERPINE1).\",\"Notably, SERPINE1 showed a strong correlation with overall survival.\",\"Interactions between OXA and GC-related genes were retrieved from the CTD database and compared with DEGs.\"],\"missing_information\":[\"The source text does not explicitly state that GSE26942, GSE66229, or TCGA-STAD data can be downloaded publicly without an application, embargo, or request.\",\"The source text does not state that any repository data are available on request.\",\"No statistical test is explicitly named for the comparison of CTD OXA interactions with differentially expressed genes that produced the seven reversed and six promoted genes.\"],\"evidence_spans\":[\"RNA-sequencing data from GSE26942, GSE66229, and TCGA-STAD datasets were analyzed. Differential gene expression was identified using GEO2R and DESeq2.\",\"Interactions between OXA and GC-related genes were retrieved from the CTD database and compared with DEGs.\",\"OXA interacted with 97 genes, of which 14 were linked to both OXA and differentially expressed genes in GC. OXA potentially reversed the expression of seven genes associated with GC progression (BIRC5, CAV1, CDH2, IL6, JUN, SERPINB2, TYMS), while promoting the expression of six others (BLVRB, CDKN2A, MAPK3, PLAU, PTGS2, SERPINE1). Notably, SERPINE1 showed a strong correlation with overall survival.\",\"We utilized Kaplan-Meier survival curves to identify differentially expressed genes. Statistically significant thresholds were determined based on a log-rank P-value of less than 0.05 and a hazard ratio (HR) not equal to 1.\"]}"}]}}, {"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:53b30de840cf12de45e95679d81e565ebc02c4a99fbec67ce637cfcd02e586e5", "type": "sep_package", "label": "SEP v1 package for pmid:40933599"}], "activities": [{"id": "activity:conversion:pmid:40933599", "type": "conversion", "used": ["package:53b30de840cf12de45e95679d81e565ebc02c4a99fbec67ce637cfcd02e586e5"], "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:40933599", "parent_hash": "sha256:138a6e7f4205087c7d00cbf450b15acbb2cc05be219cbed9ea20d068dc45c70e", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40933599 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:40933599' 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":"2026-11-04T03:03:43+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}}}