{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34248362", "kind": "science-record", "revision": 2, "content_hash": "sha256:f04a690d864015a4cd68c0e1b1bbc1f5c6f7a8de1e0a470c48c203852401c1ec", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:31Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Real-World Outcomes and Clinical Predictors of Immune Checkpoint Inhibitor Monotherapy in Advanced Lung Cancer", "doi": "10.1177/11795549211004489", "pmid": "34248362", "authors": null, "journal": "Clinical Medicine Insights. Oncology", "year": 2021, "abstract": null, "claims": [{"id": "claim-1", "statement": "the median overall survival of patients with advanced non-small-cell lung cancer treated with immune checkpoint inhibitor monotherapy", "kind": "quantitative", "state": "complete", "target": {"value": 12.4, "unit": "months", "tolerance": null, "source": "chars 8249-8744 of source sha256 c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf"}, "evidence": [{"asset": "source:pmid:34248362", "locator": "chars 8249-8744 of source sha256 c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "quote": "In the NSCLC cohort, the objective response rate (ORR) was 32.0% (95% CI, 25.6%-39.0%). Ten (5.0%) patients had complete response, and 54 (27.0%) had partial response (Table 3). Median PFS was 3.8 months (4.7 months for first-line therapy and 3.7 months for subsequent-line therapy). The estimated rate of PFS was 38.8% at 6 months, 27.8% at 12 months, and 18.2% at 24 months (Figure 1). Median OS was 12.4 months (15.6 months for first-line therapy and 11.5 months for subsequent-line therapy)."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the median overall survival of patients with advanced non-small-cell lung cancer treated with immune checkpoint inhibitor monotherapy", "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:34248362"], "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:accession_absent", "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": "method:epidemiological_modelling_incidence_rate", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the source data behind the published result in pmid:34248362"], "outputs": ["the registered result"], "instruments": [], "reagents": []}, {"id": "provide_capability_bench_workcell", "order": 4, "name": "Provide General bench workcell (liquid transfer, plate handling, incubation)", "kind": "computational", "state": "blocked", "blocked_on": "instrument not yet purchased", "description": "Make this capability available to the experiment: amplicon_seq, animal_model, apoptosis_assay, cell_culture, cell_imaging, chip_seq, clinical_cohort, clinical_trial, elisa, flow_cytometry, ihc, image_quantification, mass_spectrometry, methylation_array, microarray, qpcr, rna_seq, transfection, western_blot", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": [], "instruments": [], "reagents": []}], "materials": ["the source data behind the published result in pmid:34248362", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:epidemiological_modelling_incidence_rate"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34248362", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1177/11795549211004489", "sha256": "sha256:c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1177/11795549211004489", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind the published result in pmid:34248362", "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 source data behind the published result in pmid:34248362", "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"}}, {"id": "asset:table:pmid:34248362:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a81e900d9ce470ab9201aae2a1252684f8c3321f23a5aa0c9359c1e71a323d05", "bytes": 218, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#table1-11795549211004489", "version": null, "note": "Patient demographic and disease characteristics.", "structure": {"pmcid": "PMC8237437", "section_index": 7, "section_title": "Patient and disease characteristics", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1.", "caption": "Patient demographic and disease characteristics.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[7]/table-wrap[1]#table1-11795549211004489"}}, {"id": "asset:table:pmid:34248362:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a08d00d10f84231c0a390de07a94e02687669796c580c467d38fcf7af9b4c189", "bytes": 196, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#table2-11795549211004489", "version": null, "note": "Molecular characteristics.", "structure": {"pmcid": "PMC8237437", "section_index": 7, "section_title": "Patient and disease characteristics", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2.", "caption": "Molecular characteristics.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[7]/table-wrap[2]#table2-11795549211004489"}}, {"id": "asset:table:pmid:34248362:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a31e0ac4c36ba57def663b55c252421f961f303b489cb53b7a9bde336ead2dd6", "bytes": 190, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#table3-11795549211004489", "version": null, "note": "Summary of response.", "structure": {"pmcid": "PMC8237437", "section_index": 8, "section_title": "Treatment outcomes", "row_count": 0, "column_count": 0}, "table": {"label": "Table 3.", "caption": "Summary of response.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[8]/table-wrap[1]#table3-11795549211004489"}}, {"id": "asset:table:pmid:34248362:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:93b85d2069a96acb9b9f022ffd622ac001b6ede501a229c64a7529b7a3c15b89", "bytes": 200, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#table4-11795549211004489", "version": null, "note": "Immune-related adverse events.", "structure": {"pmcid": "PMC8237437", "section_index": 9, "section_title": "Immune-related adverse events", "row_count": 0, "column_count": 0}, "table": {"label": "Table 4.", "caption": "Immune-related adverse events.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[9]/table-wrap[1]#table4-11795549211004489"}}, {"id": "asset:table:pmid:34248362:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1a58c8b1bd01d7a6b33f6bae8f3b365e697c9e548de7303992a039f780b37f44", "bytes": 301, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#table5-11795549211004489", "version": null, "note": "Cox proportional hazard regression analysis of the effect of various parameters on progression-free survival and overall survival.", "structure": {"pmcid": "PMC8237437", "section_index": 12, "section_title": "Predictive factors associated with survival outcomes in NSCLC", "row_count": 0, "column_count": 0}, "table": {"label": "Table 5.", "caption": "Cox proportional hazard regression analysis of the effect of various parameters on progression-free survival and overall survival.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#table5-11795549211004489"}}], "gaps": ["asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:34248362 not verified", "asset:source:pmid:34248362 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox regression", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Medical records of patients with advanced lung cancer who started ICI monotherapy were reviewed for data collection. Treatment outcomes included objective response rate, progression-free survival (PFS), and overall survival (OS). Immune-related adverse events (irAEs) were assessed. Multiple Cox regression models were fit to investigate the predictive factors for survival outcomes."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 12.4, "unit": "months", "tolerance": null, "state": "complete"}], "gaps": []}, "capability": {"state": "partial", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}, {"capability_id": "capability:bench_workcell", "label": "General bench workcell (liquid transfer, plate handling, incubation)", "assay_families": ["amplicon_seq", "animal_model", "apoptosis_assay", "cell_culture", "cell_imaging", "chip_seq", "clinical_cohort", "clinical_trial", "elisa", "flow_cytometry", "ihc", "image_quantification", "mass_spectrometry", "methylation_array", "microarray", "qpcr", "rna_seq", "transfection", "western_blot"], "availability_state": "purchasable", "tier_unlocked": "R3", "candidate": "Supplier-neutral 96/384-well liquid handler"}], "gaps": ["capability:capability:bench_workcell purchasable"]}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"axis": "method", "tier": "R1", "blocker": null, "detail": {"outcome": "determined", "family": "survival_analysis", "specific_method": "cox_proportional_hazards", "required_operations": ["cox_ph"], "basis": "Every DSL operation this method needs already exists."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "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": ["cox_ph"], "assets": ["source:pmid:34248362", "asset:table:pmid:34248362:1", "asset:table:pmid:34248362:2", "asset:table:pmid:34248362:3", "asset:table:pmid:34248362:4", "asset:table:pmid:34248362:5"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": ["capability:bench_workcell"], "data_gaps": ["source:pmid:34248362", "materials:the source data behind the published result in pmid:34248362", "materials:the analysis programme that recomputes the published estimate"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "passed", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "c0c64e571bae1f6795c3dfc12736e0b860eaf4d65f2936e1eaacdd2996130d39", "source_hash": "c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "raw_response_sha256": "sha256:5d1df3b52cf6e134e37c0ea75f23a8e27e1a5baea24fd28bd42dc18ac41f8bad", "raw_response_chars": 1033}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "10a417df5f5271d628c2f7d81a8b0a0bcd778bd280883b4442fcc49e178c76a6", "source_hash": "c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "raw_response_sha256": "sha256:d601d2c22d2bf15801002cea305131c35c314707f2608986dd75556f95826e68", "raw_response_chars": 1884}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "0db7475e2238931f85fbd25027fcf973ae65bae9e8fb151448027420a0034c89", "source_hash": "c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "raw_response": "{\"parent_value\":12.4,\"unit\":\"months\",\"evidence\":\"In the NSCLC cohort, the objective response rate (ORR) was 32.0% (95% CI, 25.6%-39.0%). Ten (5.0%) patients had complete response, and 54 (27.0%) had partial response (Table 3). Median PFS was 3.8 months (4.7 months for first-line therapy and 3.7 months for subsequent-line therapy). The estimated rate of PFS was 38.8% at 6 months, 27.8% at 12 months, and 18.2% at 24 months (Figure 1). Median OS was 12.4 months (15.6 months for first-line therapy and 11.5 months for subsequent-line therapy).\",\"target_result\":\"Median overall survival was 12.4 months.\",\"number_stated\":true}", "reading": {"parent_value": 12.4, "unit": "months", "evidence": "In the NSCLC cohort, the objective response rate (ORR) was 32.0% (95% CI, 25.6%-39.0%). Ten (5.0%) patients had complete response, and 54 (27.0%) had partial response (Table 3). Median PFS was 3.8 months (4.7 months for first-line therapy and 3.7 months for subsequent-line therapy). The estimated rate of PFS was 38.8% at 6 months, 27.8% at 12 months, and 18.2% at 24 months (Figure 1). Median OS was 12.4 months (15.6 months for first-line therapy and 11.5 months for subsequent-line therapy).", "target_result": "Median overall survival was 12.4 months.", "number_stated": true, "source_locator": "chars 8249-8744 of source sha256 c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf"}, "recorded_at": "2026-10-31T14:36:01.691365+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "ec191c6d678aa915fdb9ce9cfc92245db97428fca1fa3bf9c9fd69b30a933564", "source_hash": "c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf", "raw_response": "{\"parent_value\":12.4,\"unit\":\"months\",\"evidence\":\"In NSCLC, median PFS was 3.8 months (4.7 months for first line and 3.7 months for subsequent line). Median OS was 12.4 months (15.6 months for first line therapy and 11.5 months for subsequent line).\",\"target_result\":\"Median overall survival was 12.4 months.\",\"number_stated\":true}", "reading": {"parent_value": 12.4, "unit": "months", "evidence": "In NSCLC, median PFS was 3.8 months (4.7 months for first line and 3.7 months for subsequent line). Median OS was 12.4 months (15.6 months for first line therapy and 11.5 months for subsequent line).", "target_result": "Median overall survival was 12.4 months.", "number_stated": true, "source_locator": "chars 1044-1243 of source sha256 c896e7fb83e4c1316132a9d317c903bc2ede63bdfd73689c1cc743353dd42eaf"}, "recorded_at": "2026-10-31T14:36:10.722441+00:00"}], "agreement": true, "disagreements": {"target_result": {"minimax-m3-1-flash": "Median overall survival was 12.4 months in patients with advanced NSCLC treated with immune checkpoint inhibitor monotherapy.", "minimax-m3": "Median overall survival was 12.4 months in the advanced NSCLC cohort treated with immune checkpoint inhibitor monotherapy.", "decisive": false}, "analysis_methods": {"minimax-m3-1-flash": ["Kaplan-Meier estimation of overall survival", "Multiple Cox regression analysis"], "minimax-m3": ["Retrospective medical-record review of a consecutive advanced lung cancer cohort", "Kaplan-Meier estimation of overall survival and progression-free survival", "Multiple Cox regression modeling of prognostic factors for survival outcomes"], "decisive": false}, "source_claims": {"minimax-m3-1-flash": ["In the NSCLC cohort, median PFS was 3.8 months (4.7 months for first-line therapy and 3.7 months for subsequent-line therapy).", "Median OS was 12.4 months (15.6 months for first-line therapy and 11.5 months for subsequent-line therapy).", "Overall survival (OS) was defined as time from the start of ICI treatment to death due to any cause.", "Kaplan-Meier curves were calculated for OS and PFS."], "minimax-m3": ["The study retrospectively reviewed medical records of 220 patients with advanced lung cancer who received single-agent atezolizumab, nivolumab, or pembrolizumab.", "In the NSCLC cohort, median OS was 12.4 months.", "Median OS was 15.6 months for first-line therapy and 11.5 months for subsequent-line therapy.", "Kaplan-Meier curves were calculated for OS and PFS, and Cox regression was used to model prognostic factors."], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": ["analysis_methods", "source_claims", "target_result"]}, "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": "passed", "reason": null, "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.passed"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:7b08e8e16e2d1051f325081abca3a53fec0dff0838350ad3f04b8761f04e3821", "type": "sep_package", "label": "SEP v1 package for pmid:34248362"}], "activities": [{"id": "activity:conversion:pmid:34248362", "type": "conversion", "used": ["package:7b08e8e16e2d1051f325081abca3a53fec0dff0838350ad3f04b8761f04e3821"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"id": "agent:minimax-m3-1-flash", "type": "model", "label": "minimax-m3-1-flash"}, {"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:34248362", "parent_hash": "sha256:4d38fd2f33287ea1d7f6070b05ce902811ad5ab84633a9d5d8bce674adafe941", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind the published result in pmid:34248362 not verified", "asset:source:pmid:34248362 not verified", "authors", "capability:capability:bench_workcell purchasable", "data:accession_absent", "execution.not_run", "review.human_critique", "review.machine_critique.passed", "step:obtain_source_data blocked on data:accession_absent", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:epidemiological_modelling_incidence_rate"]},"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":"2026-11-04T04:13:42+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}}}