{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40925600", "kind": "science-record", "revision": 1, "content_hash": "sha256:0ab83d3a21cf8417d10c72b750b153949f5b6e2ec3dbe638c506b4ad6c4e7147", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T10:25:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Temozolomide-Derived AIC Is Incorporated into Purine Synthesis in Glioblastoma.", "doi": "10.1021/acs.chemrestox.5c00196", "pmid": "40925600", "authors": null, "journal": "Chemical research in toxicology", "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:40925600"], "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:40925600", "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:40925600' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40925600", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.chemrestox.5c00196", "sha256": "sha256:c335de292035474b48e0c3c1ed46452c1eef07454e49e0ba3075e179e38607f1", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.chemrestox.5c00196", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40925600 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:40925600"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40925600"]}, "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": "c126541c4cf8b7670fc1c148143e265d834f65860c33786143319146377058a0", "source_hash": "c335de292035474b48e0c3c1ed46452c1eef07454e49e0ba3075e179e38607f1", "raw_response_sha256": "sha256:97394b88f3b61c3a4a91627c455da4609d8312fc65c74d0c9f81484e662aaeaf", "raw_response_chars": 5832}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "da224bc31574b8e7de19245aa9868572599f4ad7431365b3cca5ded5246f2919", "source_hash": "c335de292035474b48e0c3c1ed46452c1eef07454e49e0ba3075e179e38607f1", "raw_response_sha256": "sha256:31c1699c6e6a340a54cec6220b3c38b3f0d5bdd2b3db3ef6a6dc4ea09a3f3a18", "raw_response_chars": 76784}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "e6d6e6738a7652998042de0b67b7627d160f3e37b978729dabcdda6b9e71f1ea", "source_hash": "c335de292035474b48e0c3c1ed46452c1eef07454e49e0ba3075e179e38607f1", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper states that AIC derived from temozolomide is incorporated into AMP and NAD+ in glioblastoma cell lines and that de novo purine synthesis is upregulated in GBM relative to normal brain, but it reports no numerical value for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper states that AIC derived from temozolomide is incorporated into AMP and NAD+ in glioblastoma cell lines and that de novo purine synthesis is upregulated in GBM relative to normal brain, but it reports no numerical value for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:34:58.744149+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3877f81be39daba5ac4a8030c8d36f7ef60719ec87e93528892e684899c2617e", "source_hash": "c335de292035474b48e0c3c1ed46452c1eef07454e49e0ba3075e179e38607f1", "raw_response": "<think>We need answer JSON only. Need parse task carefully. Need identify single numerical result headline paper states for main finding, registered target vague: \"the headline numerical result the paper states for its main finding\". Supplied source text appears abstract/results, perhaps no headline numerical result for main finding except perhaps numerical values in methods: 1142 samples, 105, 158, etc. Need determine intended extraction. User asks read supplied paper text and find single numerical result that replication of registered target has to reproduce. Registered target: headline numerical result paper states for its main finding. Need report headline number only, value paper itself states, unit printed. Exact contiguous quotation containing number. If no number for registered target, number_stated false, parent_value 0, unit/evidence empty, target_result what text states instead.\n\nWe need infer whether source contains a headline numerical result for main finding. Text title and abstract says TMZ-derived AIC incorporated into AMP/NAD+, upregulated pathways, no quantitative headline number. Numerical results include 24 h, sample counts, GraphPad 10, etc. Main finding perhaps \"AIC derived from TMZ is incorporated into AMP and NAD+ in glioblastoma cell lines\"; no number attached. Thus likely false. But wording perhaps benchmark designed to extract a specific number from article, likely numerical result might be hidden in source? Let's inspect full supplied text exactly. It includes abstract, methods snippets, results. No figures/results quantitative values except sample counts. Registered target says \"the headline numerical result the paper states for its main finding\" perhaps target result is an item like \"X% of AIC...\" but source text maybe no headline numeric result. We must not mistake sample counts for headline main finding. Need output target_result describing what text states instead, exact evidence empty per instruction if no number. JSON fields.\n\nCould potentially identify \"24 h after supplementation\" as numerical result? It's methodological time point, not headline result. \"all enzymes ... significantly upregulated\" no number. No p-value or fold-change. \"In total, 1142 ... 105 ... 158...\" not main finding headline. \"GraphPad PRSIM 10\" version. \"Figure S1\" etc. The prompt explicitly gives fallback if no number for registered target. Likely answer false.\n\nNeed formulate target_result: \"The text states that AIC derived from TMZ is incorporated into AMP and NAD+ in glioblastoma cell lines and that de novo and salvage purine synthesis pathways are active/upregulated in GBM; it does not state a numerical value for this main finding.\" Evidence must be empty because no number stated. unit empty, parent 0. JSON valid, no extra.\n\nBut ensure \"headline number only\" perhaps target result expected from paper's main finding maybe \"24 h\" is stated number linked to experiment. Yet prompt says registered target is \"the headline numerical result the paper states for its main finding\", perhaps benchmark asks identify numerical result perhaps in abstract omitted? Let's explore possibility article abstract's main quantitative finding not visible due truncation? Supplied source starts title and abstract, likely entire extraction only excerpt up through results. There may be headline number in figure not text. User intentionally says if no number, false. We should assess.\n\nCould \"the single numerical result\" refer to main finding likely \"AIC is incorporated into AMP and NAD+\" and perhaps numerical metric like 20% incorporation, but source does not give. Exact contiguous quote must include number and attach target. No such. Therefore false.\n\nNeed return only JSON object. target_result perhaps concise. Ensure schema number parent_value 0, booleans. Unit \"\", evidence \"\". Let's compose.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that TMZ-derived AIC is incorporated into AMP and NAD+ in glioblastoma cell lines and that purine synthesis pathways are upregulated in GBM, but it gives no numerical value for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that TMZ-derived AIC is incorporated into AMP and NAD+ in glioblastoma cell lines and that purine synthesis pathways are upregulated in GBM, but it gives no numerical value for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:35:02.484586+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "No headline numerical result is stated for the main finding. The paper's main conclusion is that temozolomide-derived AIC is incorporated into AMP and NAD+ in glioblastoma cell lines and that de novo purine synthesis is upregulated in GBM relative to normal brain.", "minimax_alt": "The supplied text states the main finding qualitatively rather than numerically: AIC derived from TMZ is incorporated into AMP and NAD+ in glioblastoma cell lines, and de novo purine synthesis is upregulated in GBM relative to the normal brain. No numerical headline effect estimate is provided.", "decisive": false}, "physical_methods": {"minimax": ["Targeted mass spectrometry assay", "Isotope-enriched metabolite supplementation and tracer analysis", "Isotope-labeled temozolomide tracing"], "minimax_alt": ["Targeted mass spectrometry assay to quantify isotopic enrichment of AMP and NAD+", "Isotope-labeled TMZ tracing of AIC incorporation", "Cell-culture supplementation with isotope-enriched metabolites followed by tracking of label incorporation after 24 h"], "decisive": false}, "analysis_methods": {"minimax": ["RNA-sequencing gene-expression analysis", "UCSC Xena TCGA-GBM versus GTEx comparison", "Kaplan–Meier survival analysis", "Log-rank test", "GraphPad Prism 10"], "minimax_alt": ["Comparative analysis of log2-transformed “RSEM expected_count (DESeq2 standardized)” gene-expression data from TCGA-GBM and GTEx", "Kaplan–Meier survival analysis using median-split high- and low-expression cohorts", "Log-rank test"], "decisive": false}, "statistical_method": {"minimax": "Kaplan–Meier analysis with the log-rank test", "minimax_alt": "", "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:54d3ed2733ef88588ce173285d377383b52f22ac94762a683c714fe3c2eca6fd", "type": "sep_package", "label": "SEP v1 package for pmid:40925600"}], "activities": [{"id": "activity:conversion:pmid:40925600", "type": "conversion", "used": ["package:54d3ed2733ef88588ce173285d377383b52f22ac94762a683c714fe3c2eca6fd"], "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": "3bd77af9-c2f2-4930-9108-5501013ae06b", "parent_hash": "54d3ed2733ef88588ce173285d377383b52f22ac94762a683c714fe3c2eca6fd", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40925600 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:40925600' 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":"2026-11-04T02:12:25+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}}}