{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33717423", "kind": "science-record", "revision": 2, "content_hash": "sha256:c7a7f7e3c3b1a8257abe2b4a79a2d25917a99de40d3ce78419abcbf92d0444d5", "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": "Identification and validation of a prognostic signature and combination drug therapy for immunotherapy of head and neck squamous cell carcinoma", "doi": "10.1016/j.csbj.2021.01.046", "pmid": "33717423", "authors": null, "journal": "Computational and Structural Biotechnology Journal", "year": 2021, "abstract": null, "claims": [{"id": "claim-1", "statement": "the hazard ratio for survival associated with the prognostic signature in head and neck squamous cell carcinoma", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the hazard ratio for survival associated with the prognostic signature in head and neck squamous cell carcinoma", "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:33717423"], "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:differential_expression_limma_voom", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the analysis programme that recomputes the published estimate"], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": ["the source data behind pmid:33717423, which the paper says are available from the authors on request", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:differential_expression_limma_voom"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33717423", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.csbj.2021.01.046", "sha256": "sha256:960e4977ff64bee899f19f7ef3d14890b4bf89cf23f12ce5b8c6f297bafa9abd", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.csbj.2021.01.046", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind pmid:33717423, which the paper says are available from the authors on request", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "restricted", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind pmid:33717423, which the paper says are available from the authors on request", "structure": {"material_kind": "dataset", "access_state": "restricted"}}, {"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": "data:availability", "role": "raw", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "The datasets obtained in this study or materials are available from the corresponding authors on reasonable request.", "structure": {"access_route": "request_on_author", "location": "section [data-availability-statement]: Data Availability Statement"}}, {"id": "asset:table:pmid:33717423:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:431d085ee4e16d5d8b68ed4cb48f42680bfb19312856b62a2f933f4610071c76", "bytes": 1737, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#t0005", "version": null, "note": "Univariate and multivariate Cox regression analyses of IRGPI and other clinicopathological factors for OS in entire TCGA cohort and GSE65858 cohort.", "structure": {"pmcid": "PMC7921014", "section_index": 19, "section_title": "Relationship between IRGPI and patient prognosis", "row_count": 20, "column_count": 7}, "table": {"label": "Table 1", "caption": "Univariate and multivariate Cox regression analyses of IRGPI and other clinicopathological factors for OS in entire TCGA cohort and GSE65858 cohort.", "rows": [["Overall survival", "Univariate analysis", "Multivariate analysis"], ["", "HR", "95%CI", "P-value", "HR", "95%CI", "P-value"], ["Entire TCGA cohort"], ["Age", "1.011", "0.993–1.028", "0.228", "1.011", "0.992–1.030", "0.259"], ["Gender (male vs. female)", "0.765", "0.514–1.137", "0.185", "0.705", "0.463–1.074", "0.103"], ["Tumor status (with tumor vs. tumor free)", "9.330", "6.242–13.947", "<0.001", "6.463", "4.246–9.839", "<0.001"], ["Tumor grade", "1.184", "0.884–1.587", "0.257", "0.950", "0.695–1.299", "0.749"], ["Pathological stage", "1.866", "1.399–2.489", "<0.001", "1.266", "0.801–2.001", "0.313"], ["T stage", "1.361", "1.121–1.653", "0.002", "0.954", "0.721–1.262", "0.740"], ["N stage", "1.748", "1.424–2.146", "<0.001", "1.382", "1.048–1.822", "0.022"], ["IRGPI (high-risk vs. low-risk)", "3.178", "2.265–4.458", "<0.001", "2.068", "1.416–3.022", "<0.001"], [""], ["GSE65858 cohort"], ["Age", "1.027", "1.006–1.048", "0.013", "1.028", "1.007–1.051", "0.011"], ["Gender (male vs. female)", "1.046", "0.617–1.771", "0.868", "1.086", "0.637–1.852", "0.762"], ["UICC stage", "1.615", "1.204–2.168", "0.001", "1.177", "0.735–1.887", "0.497"], ["T stage", "1.512", "1.222–1.872", "<0.001", "1.234", "0.937–1.625", "0.135"], ["N stage", "1.415", "1.129–1.774", "0.003", "1.195", "0.867–1.648", "0.275"], ["M stage", "3.705", "1.634–8.400", "0.002", "2.254", "0.907–5.599", "0.080"], ["IRGPI (high-risk vs. low-risk)", "1.739", "1.186–2.552", "0.005", "1.815", "1.219–2.702", "0.003"]], "row_count": 20, "column_count": 7, "numeric_cells": 93, "header_rows": 2, "locator": "section[19]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:33717423:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2cd7cc9ca56ee80b2b12d6b2d47bea4ee0793d2c87abf47992fedb8d0247b2f7", "bytes": 2101, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#t0010", "version": null, "note": "Potential targeted therapeutic drugs for IRGPI based on CMap analysis.", "structure": {"pmcid": "PMC7921014", "section_index": 25, "section_title": "Screening of small-molecule drugs", "row_count": 28, "column_count": 7}, "table": {"label": "Table 2", "caption": "Potential targeted therapeutic drugs for IRGPI based on CMap analysis.", "rows": [["CMap name", "Mean connective score", "n", "Enrichment", "P-Value", "Specificity", "Percent non-null"], ["Arachidonic acid", "−0.592", "3", "−0.812", "0.0133", "0.0128", "100"], ["Doxorubicin", "−0.57", "3", "−0.798", "0.01695", "0.2181", "100"], ["Xamoterol", "−0.536", "3", "−0.806", "0.01462", "0.0343", "100"], ["Levodopa", "−0.51", "5", "−0.703", "0.00505", "0.0152", "80"], ["Camptothecin", "−0.499", "3", "−0.773", "0.024", "0.2614", "100"], ["Ranitidine", "−0.498", "5", "−0.661", "0.01059", "0", "80"], ["Piromidic acid", "−0.489", "4", "−0.772", "0.00547", "0.0214", "100"], ["Minaprine", "−0.483", "5", "−0.617", "0.02233", "0.0236", "80"], ["Ethaverine", "−0.47", "4", "−0.721", "0.01239", "0.0191", "75"], ["Daunorubicin", "−0.47", "4", "−0.66", "0.03032", "0.1754", "75"], ["Lomefloxacin", "−0.465", "6", "−0.639", "0.00638", "0.0051", "83"], ["Captopril", "−0.463", "5", "−0.607", "0.02637", "0.0423", "80"], ["Clonidine", "−0.462", "4", "−0.631", "0.04518", "0.0148", "75"], ["Dihydroergocristine", "−0.449", "4", "−0.74", "0.00897", "0.0308", "75"], ["Vorinostat", "−0.412", "12", "−0.552", "0.00068", "0.3097", "66"], ["Ribavirin", "−0.407", "4", "−0.688", "0.02039", "0.0921", "75"], ["Levonorgestrel", "−0.402", "6", "−0.525", "0.04676", "0.1913", "66"], ["Fluorometholone", "−0.4", "4", "−0.651", "0.03503", "0.057", "75"], ["Apigenin", "−0.379", "4", "−0.686", "0.02103", "0.1304", "75"], ["Doxycycline", "−0.308", "5", "−0.587", "0.03507", "0.0622", "80"], ["Norfloxacin", "−0.289", "5", "−0.614", "0.02357", "0.0263", "60"], ["Tretinoin", "−0.272", "22", "−0.342", "0.00826", "0.1397", "50"], ["Wortmannin", "−0.269", "18", "−0.321", "0.04013", "0.3758", "50"], ["Trichostatin A", "−0.264", "182", "−0.441", "0", "0.2772", "51"], ["Etilefrine", "−0.254", "4", "−0.653", "0.03428", "0.0426", "50"], ["Cyanocobalamin", "−0.243", "4", "−0.642", "0.03945", "0.0432", "50"], ["Pyrithyldione", "−0.207", "4", "−0.657", "0.03191", "0.0986", "50"]], "row_count": 28, "column_count": 7, "numeric_cells": 162, "header_rows": 1, "locator": "section[25]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:33717423:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:607d5c23186e85c091f6591016f76bdf6e2b282900243ea14ad0b06a9af77652", "bytes": 764, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[1]#t0015", "version": null, "note": "The results of molecular docking.", "structure": {"pmcid": "PMC7921014", "section_index": 27, "section_title": "Molecular docking", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "The results of molecular docking.", "rows": [["Rank", "Pubchem CID", "Compound name", "Glide gscore"], ["1", "31703", "Doxorubicin", "−8.062"], ["2", "30323", "Daunorubicin", "−8.018"], ["3", "3306", "Etilefrine", "−6.63"], ["4", "107715", "Dihydroergocristine", "−6.512"], ["5", "6047", "Levodopa", "−6.132"], ["6", "4539", "Norfloxacin", "−5.891"], ["7", "54671203", "Doxycycline", "−5.578"], ["8", "24360", "Camptothecin", "−5.507"], ["9", "4855", "Piromidic Acid", "−5.357"], ["10", "5311498", "Cyanocobalamin", "−4.993"], ["Native ligand", "137349240", "3-Azanyl-5-(Azepan-1-Yl)-N-Carbamimidoyl-6-(Furan-2-Yl)Pyrazine-2-Carboxamide", "−7.457"]], "row_count": 12, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[27]/table-wrap[1]#t0015"}}], "gaps": ["asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:33717423, which the paper says are available from the authors on request not verified", "asset:source:pmid:33717423 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox proportional hazards", "label": "", "dsl_operations": [], "missing_operations": [], "expressible": false, "parameters": {}, "data_shapes": [], "evidence": {"score": 0.0, "band": "low", "quote": "Among these DEIRGs, the prognosis-related IRGs were identified and subjected to subsequent analysis. Firstly, the univariate Cox proportional hazard regression model was used to analyze the correlation between DEIRGs and overall survival (OS) in the training set, followed by the Least Absolute Shrinkage and Selection Operator (LASSO) penalized Cox proportional hazards regression for selecting the optimal subset of prognosis-related IRGs [17]. The risk score was then calculated using expression data multiplied by the regression coefficient from the LASSO regression model. The formula was as follows: risk score = [Expression level of Gene 1 * coefficient] + [Expression level of Gene 2 * coefficient] + … + [Expression level of Gene n * coefficient]. Patients were additionally separated into high- and low- risk groups according to the median value of risk score."}}], "targets": [], "gaps": ["method.corpus_not_determined", "method.operations", "targets"]}, "capability": {"state": "complete", "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"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"axis": "method", "tier": "R4", "blocker": "method:not_determinable", "detail": {"outcome": "not_determinable", "reason": "No specific statistical method is stated in recognised wording. Full methods review is required.", "basis": "The title, abstract and methods text do not carry the method, so a person has to read the paper before it can be programmed."}}, "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": [], "assets": ["source:pmid:33717423", "asset:table:pmid:33717423:1", "asset:table:pmid:33717423:2", "asset:table:pmid:33717423:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["unknown", "xml"], "capabilities": [], "data_gaps": ["source:pmid:33717423", "materials:the source data behind pmid:33717423, which the paper says are available from the authors on request", "materials:the analysis programme that recomputes the published estimate", "data:availability"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "peer-review-reading-v1", "prompt_hash": "8077008b7c38190a8f0e42c45551a902ef3ff71144928004518acfcc02c271b9", "source_hash": "960e4977ff64bee899f19f7ef3d14890b4bf89cf23f12ce5b8c6f297bafa9abd", "raw_response_sha256": "sha256:da01776dd38d88dc4dddc14848facfb5cf6b56da5204c06e1e66b64950855e1d", "raw_response_chars": 1961}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "54a1416f8878b9c64910ea1aaf848e6e65f3db87ed0d6aa09f59d6df38ef2900", "source_hash": "960e4977ff64bee899f19f7ef3d14890b4bf89cf23f12ce5b8c6f297bafa9abd", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that IRGPI was significantly associated with overall survival and could be used as an independent prognostic predictor, but it does not state a numerical hazard ratio for the registered target.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that IRGPI was significantly associated with overall survival and could be used as an independent prognostic predictor, but it does not state a numerical hazard ratio for the registered target.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T14:34:53.970226+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "5c61dcf65cd4eafcbf7bf2e63b27fd7e1856d4a879ca253718e86dbed10dc128", "source_hash": "960e4977ff64bee899f19f7ef3d14890b4bf89cf23f12ce5b8c6f297bafa9abd", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The supplied text states that IRGPI was significantly associated with overall survival in univariate and multivariate analyses in the entire TCGA cohort and the GSE65858 cohort, and could be used as an independent prognostic predictor. Although hazard ratios are reported in Table 1, no numerical hazard ratio for IRGPI is included in the supplied text.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The supplied text states that IRGPI was significantly associated with overall survival in univariate and multivariate analyses in the entire TCGA cohort and the GSE65858 cohort, and could be used as an independent prognostic predictor. Although hazard ratios are reported in Table 1, no numerical hazard ratio for IRGPI is included in the supplied text.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T14:35:11.533984+00:00"}], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": []}, "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 reading stage and the target extraction did not both return two readings, so the package claims no agreement.", "evidence": {"provider_errors": [{"provider": "minimax-m3", "model": "MiniMax-M3", "reason": "a quoted span is absent from the supplied text"}]}}, {"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:814c93eae493214cdd0d25599dcd743fe00cc008e22daba8633027010b343b3a", "type": "sep_package", "label": "SEP v1 package for pmid:33717423"}], "activities": [{"id": "activity:conversion:pmid:33717423", "type": "conversion", "used": ["package:814c93eae493214cdd0d25599dcd743fe00cc008e22daba8633027010b343b3a"], "agent": "agent:corpus-assay-engine"}], "agents": [{"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:33717423", "parent_hash": "sha256:cb44f18affc378d7a5a7b15c4f4d98488c71986c3f0280e3df8f435f55fea370", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:33717423, which the paper says are available from the authors on request not verified", "asset:source:pmid:33717423 not verified", "authors", "execution.not_run", "method.corpus_not_determined", "method.operations", "method:not_determinable", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:differential_expression_limma_voom", "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":"2026-11-04T03:10:33+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}}}