{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:12962150", "kind": "science-record", "revision": 2, "content_hash": "sha256:711eddb2dfdc62d4d46c0568c9a93872f4e93e89610a3e63c7516b2cf8af0161", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T10:25:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Semiquantitative RT-PCR method coupled to capillary electrophoresis to study 5alpha-reductase mRNA isozymes in rat ventral prostate in different androgen status.", "doi": "10.1023/a:1024902419502", "pmid": "12962150", "authors": null, "journal": "Molecular and cellular biochemistry", "year": 2003, "abstract": null, "claims": [{"id": "claim-1", "statement": "relative mRNA level of the 5alpha-reductase type 2 isozyme in rat ventral prostate", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "relative mRNA level of the 5alpha-reductase type 2 isozyme in rat ventral prostate", "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:12962150"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the study data behind the published pooled estimate", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The published estimate cannot be recomputed without the data the review pooled.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the pooled study data with its provenance"], "instruments": [], "reagents": []}, {"id": "provide_capability_animal_model", "order": 3, "name": "Provide In-vivo animal model work", "kind": "computational", "state": "blocked", "blocked_on": "capability:animal_model", "description": "The corpus blocks this paper on this capability, so the experiment cannot start until it is available.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": [], "instruments": [], "reagents": []}], "materials": ["the study data pooled behind the published estimate in pmid:12962150", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_animal_model blocked on capability:animal_model"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:12962150", "role": "manuscript", "format": "txt", "media_type": "text/plain", "uri": "https://doi.org/10.1023/a:1024902419502", "sha256": "sha256:c3d8c197c8d120c8ccf543a154eb95604cb2ddddf74e0fefb799c9311102e8ce", "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "reader_required", "identifier": "10.1023/a:1024902419502", "version": null, "note": "Source read by the package builder: abstract_only.", "structure": {"access_state": "abstract_only"}}, {"id": "materials:the study data pooled behind the published estimate in pmid:12962150", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the study data pooled behind the published estimate in pmid:12962150", "structure": {"material_kind": "dataset", "access_state": "not_identified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the study data pooled behind the published estimate in pmid:12962150 not verified", "asset:source:pmid:12962150 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "method.evidence_rejected", "operations", "targets"]}, "capability": {"state": "partial", "requirements": [{"capability_id": "capability:animal_model", "label": "In-vivo animal model work", "assay_families": ["animal_model"], "availability_state": "unavailable", "tier_unlocked": "R4", "candidate": null}], "gaps": ["capability:capability:animal_model unavailable"]}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "capability", "blocked_on": "capability:animal_model", "axes": {"method": {"axis": "method", "tier": "R4", "blocker": "method:not_determinable", "detail": {"outcome": "not_determinable", "reason": "The evidence this method was read from does not name the method under the corpus's own vocabulary.", "basis": "The phrase the method was read from names something else, so the claim is withdrawn and a person has to read the paper before it can be programmed."}}, "capability": {"axis": "capability", "tier": "R4", "blocker": "capability:animal_model", "detail": {"families": ["animal_model"], "capability_id": "capability:animal_model", "availability_state": "unavailable", "considered": [{"family": "animal_model", "capability_id": "capability:bench_workcell", "availability_state": "purchasable", "tier_unlocked": "R3"}, {"family": "animal_model", "capability_id": "capability:animal_model", "availability_state": "unavailable", "tier_unlocked": "R4"}], "basis": "The equipment register names no animal-facility capability at any gate. In-vivo work needs a specialist facility and an ethical approval, which is a collaboration rather than a purchase."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": [], "assets": [], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["txt", "unknown"], "capabilities": ["capability:animal_model"], "data_gaps": ["source:pmid:12962150", "materials:the study data pooled behind the published estimate in pmid:12962150", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["capability:animal_model", "method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "7e7a5a1191c97e6b55c552c9e1779b1bfb05a0220ef3bfa96c8dcb82c1877a5f", "source_hash": "c3d8c197c8d120c8ccf543a154eb95604cb2ddddf74e0fefb799c9311102e8ce", "raw_response_sha256": "sha256:2314b31ddba37ec05143f82366907772b043375204c8e9ab4fd490b386c62e38", "raw_response_chars": 1768}, {"provider": "qwen_remote", "model": "qwen3.8:27b-codex128k", "prompt_version": "peer-review-reading-v1", "prompt_hash": "5332ea68993cb01c2b46426fade8e86444d33b5d1b3d69d03cefd47224b62840", "source_hash": "c3d8c197c8d120c8ccf543a154eb95604cb2ddddf74e0fefb799c9311102e8ce", "raw_response_sha256": "sha256:984716a1c6668e21d71c6b55bfaf9c9018d326a7fbff60b456a078f5900cb7ce", "raw_response_chars": 1761}], "target_providers": null, "agreement": false, "disagreements": {"target_result": {"minimax": "Testosterone controls the expression of the 5alpha-reductase type 2 isozyme in rat ventral prostate; the direction and magnitude of the relative mRNA-level change are unclear from the supplied text.", "qwen_remote": "unknown"}, "physical_methods": {"minimax": ["Collection of ventral prostate tissue from rats with different androgen statuses", "Measurement of 5alpha-reductase isozyme mRNA levels"], "qwen_remote": ["semiquantitative PCR", "laser-induced fluorescence capillary electrophoresis (LIF-CE)"]}, "source_claims": {"minimax": ["The study presents measurements of mRNA levels of steroid 5alpha-reductase isozymes in the ventral prostate of rats with different androgen statuses.", "Both 5alpha-reductase isozymes are expressed in the prostate.", "The authors report that testosterone controls the expression of the 5alpha-reductase type 2 isozyme in rat prostate."], "qwen_remote": ["The authors present measurements of mRNA levels of steroid 5alpha-R isozymes in the ventral prostate of rats of different androgen status.", "They used a novel method combining the high specificity of semiquantitative PCR with the sensitivity of laser-induced fluorescence capillary electrophoresis (LIF-CE).", "They demonstrated that testosterone controls the expression of the 5alpha-R2 isozyme in rat prostate."]}}, "agreement_basis": null, "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:3f890a1bb470ba9bcbd261e12e5ec2a9b7b8389e5bbe284fe303a0ffa0c524c9", "type": "sep_package", "label": "SEP v1 package for pmid:12962150"}], "activities": [{"id": "activity:conversion:pmid:12962150", "type": "conversion", "used": ["package:3f890a1bb470ba9bcbd261e12e5ec2a9b7b8389e5bbe284fe303a0ffa0c524c9"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:qwen_remote", "type": "model", "label": "qwen_remote"}, {"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:12962150", "parent_hash": "sha256:91d5299ccdac4124df61de88ca1bd737fa37041e8371317f53d47bd95b6e5fbd", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the study data pooled behind the published estimate in pmid:12962150 not verified", "asset:source:pmid:12962150 not verified", "authors", "capability:animal_model", "capability:capability:animal_model unavailable", "execution.not_run", "method", "method.evidence_rejected", "method:not_determinable", "operations", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_animal_model blocked on capability:animal_model", "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":"2026-11-04T00:46:07+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}}}