{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41330006", "kind": "science-record", "revision": 2, "content_hash": "sha256:db4afdade8f5e8a28c2d3f00aa7457530567151a58931d292a797cd1839592ef", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Circular RNA circAHSA1 serves as a stable serum biomarker for the diagnosis and progression of gastric cancer.", "doi": "10.1016/j.tranon.2025.102620", "pmid": "41330006", "authors": null, "journal": "Translational oncology", "year": 2026, "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:41330006"], "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:41330006", "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:41330006' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41330006", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.tranon.2025.102620", "sha256": "sha256:c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.tranon.2025.102620", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41330006:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2e440e7dc6012cd5a64611aef75598ecf82ffff0d194761c1bcf205492f66fc9", "bytes": 299, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#tbl0001", "version": null, "note": "Intra‐ and interassay CV of circAHSA1.", "structure": {"pmcid": "PMC12719094", "section_index": 6, "section_title": "Validation of circAHSA1 structure and stability", "row_count": 3, "column_count": 3}, "table": {"label": "Table 1", "caption": "Intra‐ and interassay CV of circAHSA1.", "rows": [["", "circAHSA1", "18s rRNA"], ["Intra‐assay CV ( %)", "2.06", "1.87"], ["Intra‐assay CV ( %)", "1.99", "2.14"]], "row_count": 3, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[6]/table-wrap[1]#tbl0001"}}, {"id": "asset:table:pmid:41330006:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e08857b6f1c3922cb9edb3e84b15212b1c9160b6621ff62746c326d18de36293", "bytes": 1174, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#tbl0002", "version": null, "note": "Clinicopathological analysis of circAHSA1 in GC.", "structure": {"pmcid": "PMC12719094", "section_index": 18, "section_title": "Association between serum circAHSA1 levels and clinicopathological characteristics of GC patients", "row_count": 23, "column_count": 6}, "table": {"label": "Table 2", "caption": "Clinicopathological analysis of circAHSA1 in GC.", "rows": [["Parameter", "No. of patients", "circAHSA1(high)", "circAHSA1(low)", "P-value"], ["Age(years)", "≤60", "42", "19", "23", "0.574"], ["", ">60", "85", "45", "40"], ["Sex", "Male", "61", "29", "32", "0.536"], ["", "Female", "66", "31", "35"], ["Grade", "Well-moderate", "52", "18", "34", "<0.001"], ["", "Poor-undifferentiat", "75", "49", "26"], ["T stage", "T1-T2", "68", "30", "38", "0.152"], ["", "T3-T4", "59", "38", "21"], ["Tumor size", ">5", "59", "38", "21", "0.214"], ["", "≤5", "68", "25", "43"], ["Lymph node status", "Positive", "74", "52", "22", "<0.001"], ["", "Negative", "53", "18", "35"], ["TNM stage", "Ⅰ-Ⅱ", "54", "16", "38", "<0.001"], ["", "Ⅲ-Ⅳ", "73", "49", "24"], ["Nerve/vascular invasion", "Positive", "48", "22", "26", "0.487"], ["", "Negative", "79", "41", "38"], ["Depth of infiltration", "Muscular layer and below", "87", "66", "21", "<0.001"], ["", "submucosa and above", "40", "31", "9"], ["Ki67", "Positive", "85", "42", "43", "0.251"], ["", "Negative", "42", "20", "22"], ["CK", "Positive", "66", "34", "32", "0.148"], ["", "Negative", "61", "27", "34"]], "row_count": 23, "column_count": 6, "numeric_cells": 82, "header_rows": 1, "locator": "section[18]/table-wrap[1]#tbl0002"}}, {"id": "asset:table:pmid:41330006:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:59f19f521d99b0462a1dbc22cfe0fa3124bffb49842e4cecb0b4f4e40166fce9", "bytes": 907, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#tbl0003", "version": null, "note": "Diagnostic performance of circAHSA1, CEA, CA199, and CA724 in differentiating GC patients from healthy donors.", "structure": {"pmcid": "PMC12719094", "section_index": 19, "section_title": "circAHSA1 as a novel serum biomarker for differentiating GC from controls and gastritis patients", "row_count": 9, "column_count": 8}, "table": {"label": "Table 3", "caption": "Diagnostic performance of circAHSA1, CEA, CA199, and CA724 in differentiating GC patients from healthy donors.", "rows": [["Model", "Cutoff", "SEN", "SPE", "ACCU", "PPV", "NPV", "P (vs circAHSA1)"], ["circAHSA1", "1.551", "0.756", "0.706", "0.732", "0.733", "0.73", "–"], ["CEA", "1.965", "0.811", "0.504", "0.663", "0.636", "0.714", "0.019"], ["CA199", "12.780", "0.504", "0.899", "0.695", "0.842", "0.629", "0.009"], ["CA724", "5.510", "0.543", "0.807", "0.671", "0.75", "0.623", "0.045"], ["circAHSA1+CEA", "0.419", "0.772", "0.689", "0.732", "0.726", "0.739", "0.819"], ["circAHSA1+CA199", "0.484", "0.669", "0.874", "0.768", "0.85", "0.712", "0.020"], ["circAHSA1+CA724", "0.387", "0.811", "0.739", "0.776", "0.769", "0.786", "0.010"], ["circAHSA1+CEA+CA199+CA724", "0.356", "0.866", "0.739", "0.805", "0.78", "0.838", "< 0.001"]], "row_count": 9, "column_count": 8, "numeric_cells": 60, "header_rows": 1, "locator": "section[19]/table-wrap[1]#tbl0003"}}, {"id": "asset:table:pmid:41330006:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:98012e0b59cf86bcc3322a8ee14c9932756a469f62610ab571afe371cb211573", "bytes": 907, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[2]#tbl0004", "version": null, "note": "Diagnostic performance of circAHSA1, CEA, CA199, and CA724 in differentiating GC patients from gastritis patients.", "structure": {"pmcid": "PMC12719094", "section_index": 19, "section_title": "circAHSA1 as a novel serum biomarker for differentiating GC from controls and gastritis patients", "row_count": 9, "column_count": 8}, "table": {"label": "Table 4", "caption": "Diagnostic performance of circAHSA1, CEA, CA199, and CA724 in differentiating GC patients from gastritis patients.", "rows": [["Model", "Cutoff", "SEN", "SPE", "ACCU", "PPV", "NPV", "P (vs circAHSA1)"], ["circAHSA1", "2.042", "0.669", "0.804", "0.729", "0.81", "0.661", "–"], ["CEA", "1.820", "0.819", "0.588", "0.716", "0.712", "0.723", "0.040"], ["CA199", "8.455", "0.543", "0.304", "0.437", "0.493", "0.348", "< 0.001"], ["CA724", "16.920", "0.213", "1", "0.563", "1", "0.505", "< 0.001"], ["circAHSA1+CEA", "0.484", "0.717", "0.716", "0.716", "0.758", "0.67", "0.355"], ["circAHSA1+CA199", "0.460", "0.772", "0.706", "0.742", "0.766", "0.713", "0.456"], ["circAHSA1+CA724", "0.494", "0.717", "0.765", "0.738", "0.791", "0.684", "0.239"], ["circAHSA1+CEA+CA199+CA724", "0.458", "0.764", "0.725", "0.747", "0.776", "0.712", "0.228"]], "row_count": 9, "column_count": 8, "numeric_cells": 60, "header_rows": 1, "locator": "section[19]/table-wrap[2]#tbl0004"}}], "gaps": ["asset:source:pmid:41330006 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:41330006", "asset:table:pmid:41330006:1", "asset:table:pmid:41330006:2", "asset:table:pmid:41330006:3", "asset:table:pmid:41330006:4"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41330006"]}, "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": "25b3b5009f12f9c0fb2f1ab4b9400001ad314662a491ef95981ac16edbf4c3c1", "source_hash": "c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa", "raw_response_sha256": "sha256:f6b557b49c0d9983ad4e5b58ff2a38d8c454a89c82500961781f50d58d026c9d", "raw_response_chars": 3582}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "ac6f1f056e4309dd618252e0e2a8c100ce8972210af92811f64d119772201f85", "source_hash": "c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa", "raw_response_sha256": "sha256:afcb540f73d84b884fdc5e1554667fd10903c5bb21a9e750eb007dffe50d8564", "raw_response_chars": 28483}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "5745042dce66ba1167efd703dfa7a7aa8b285fe6f05ee7e2b981d04b2c2065d0", "source_hash": "c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa", "raw_response": "{\"parent_value\":0.787,\"unit\":\"AUC\",\"evidence\":\"Serum circAHSA1 effectively discriminated GC from healthy controls (AUC = 0.787) and gastritis patients (AUC = 0.752), outperforming conventional markers, with statistical superiority confirmed by DeLong analysis.\",\"target_result\":\"Serum circAHSA1 discriminated gastric cancer from healthy controls with an AUC of 0.787.\",\"number_stated\":true}", "reading": {"parent_value": 0.787, "unit": "AUC", "evidence": "Serum circAHSA1 effectively discriminated GC from healthy controls (AUC = 0.787) and gastritis patients (AUC = 0.752), outperforming conventional markers, with statistical superiority confirmed by DeLong analysis.", "target_result": "Serum circAHSA1 discriminated gastric cancer from healthy controls with an AUC of 0.787.", "number_stated": true, "source_locator": "chars 1374-1587 of source sha256 c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa"}, "recorded_at": "2026-10-31T15:15:10.201182+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "02332c74fa29f62066712be9b40c670a9a1078a1c1a983eee908ea59596540eb", "source_hash": "c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline main finding. Paper source. Need determine likely headline number: combined detection AUC=0.871? \"headline numerical result paper states for registered target\" Registered target vague: headline numerical result for main finding. Main finding title circAHSA1 stable serum biomarker diagnosis/progression. Results include AUC healthy 0.787, gastritis 0.752, combined 0.871. Which single headline number? Need infer likely \"combined detection further improved diagnostic accuracy (AUC = 0.871)\" as headline numerical result. They ask singular numerical result registered target perhaps benchmark task where identify parent_value from paper. Need report headline number only, printed unit. AUC dimensionless, unit maybe \"AUC\" or empty? They explicitly unit must be unit paper prints. Since AUC is metric, could unit be \"AUC\". parent_value 0.871. Evidence exact contiguous quote containing number. \"Combined detection further improved diagnostic accuracy (AUC = 0.871).\" Exact sentence. target_result perhaps concise \"AUC = 0.871\". number_stated true. Need ensure evidence quote perhaps whole clause. JSON valid. Could headline instead AUC 0.787 for serum circAHSA1 discriminating GC from healthy controls. Main finding perhaps circAHSA1 diagnostic performance, and combined panel further improved. Registered target phrasing broad. They likely expect one number likely 0.871 because that's combined model's headline. Let's deeply inspect wording.\n\nPrompt: \"find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints.\" REGISTERED TARGET: \"the headline numerical result the paper states for its main finding\". They want extract headline numerical result. Source has abstract-like intro and Results. Main finding: circAHSA1 significantly upregulated, serum detects; distinguishes; combination improves; silencing etc. Single headline numerical result perhaps \"Combined detection further improved diagnostic accuracy (AUC = 0.871).\" Since highest and explicit summary. Need not quote abstract because no number there. Evidence exact contiguous quote.\n\nWhat should unit string be? AUC has no physical unit. They might expect unit \"\" and parent_value 0.871. Schema says unit string; \"The unit must be the unit the paper prints.\" Paper prints \"AUC\", arguably unit as metric label. Usually these tasks output {\"parent_value\":..., \"unit\":\"...\", \"evidence\":\"...\", ...}. For AUC, unit could \"AUC\" because metric. But \"unit\" often expect e.g. \"%\", \"mg/L\", etc. Here no unit printed, so empty string likely. Yet target_result states AUC = 0.871. Need interpret \"Report headline number only: value... unit must be unit paper prints.\" They insist number only perhaps parent_value, unit. For dimensionless AUC, unit likely \"AUC\". Could output unit: \"AUC\" as paper prints it. Evidence sentence.\n\nLet's ensure target_result maybe \"Combined detection further improved diagnostic accuracy (AUC = 0.871).\" Or target_result \"AUC = 0.871 for combined detection\". Evidence exact. Number stated true. \"headline number only\" likely target_result should only say \"AUC = 0.871\". Fine.\n\nNeed no markdown, valid JSON. Use escaped unicode? Regular okay. Exact quote can omit period? Exact contiguous quotation. Quote exact entire sentence, including punctuation. Ensure source: \"Combined detection further improved diagnostic accuracy (AUC = 0.871).\" yes.\n\nPotential concern main finding may be AUC=0.787 (circAHSA1 alone). Let's analyze wording hierarchy. Abstract (source intro) says:\n- circAHSA1 significantly upregulated...\n- Serum circAHSA1 distinguishes...\n- Combined ... improves...\n- silencing...\n- correlates...\nNo numerical numbers in abstract. Results:\n\"Serum circAHSA1 effectively discriminated GC from healthy controls (AUC = 0.787) and gastritis patients (AUC = 0.752), outperforming conventional markers, with statistical superiority confirmed by DeLong analysis. Combined detection further improved diagnostic accuracy (AUC = 0.871).\" If asked headline numerical result for main finding, which is headline? The headline may be combined detection AUC 0.871. Usually paper's abstract might report specific AUC perhaps source transformed? The registered target wording perhaps generated generic target, and intended numerical result extraction benchmark has one \"headline\" number. They might consider \"AUC = 0.787\" the key performance of circAHSA1 itself, while 0.871 is combination. Title biomarker circAHSA1, so main finding's headline number could be 0.787 (healthy) or 0.752 (gastritis). But \"headline numerical result the paper states for its main finding\" likely asks select strongest main result from source. Need infer expected target result singular.\n\nLet's parse user's wording carefully: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nREGISTERED TARGET: the headline numerical result the paper states for its main finding\n\nThis is meta target, likely they expect model to pick one. \"single numerical result\" perhaps one explicitly designated headline. The source itself likely synthetic abstract and methods. Among results, multiple AUCs. Maybe \"Combined detection further improved diagnostic accuracy (AUC = 0.871)\" is clearly headline/highest. Replication main finding (diagnostic panel) needs reproduce 0.871. Main title finding serum biomarker, though combined panel includes CEA etc.\n\nCould answer 0.871. Let's examine phrase \"headline number only\" often in benchmark prompts where registered target e.g. \"the headline numerical result the paper states for its main finding.\" They expect a key metric in abstract, often AUC. Here source's Results paragraph gives 0.787, 0.752, 0.871. \"headline\" likely last and best performance. \"Combined detection further improved diagnostic accuracy (AUC = 0.871)\" can be headline result. If replication target is main finding (circAHSA1 as stable serum biomarker), perhaps AUC 0.787 in GC vs healthy and 0.752 gastritis are two related values, not single. To meet single number, select combined 0.871 because single metric. This seems intended.\n\nUnit maybe \"AUC\".</think>\n\n{\"parent_value\":0.871,\"unit\":\"AUC\",\"evidence\":\"Combined detection further improved diagnostic accuracy (AUC = 0.871).\",\"target_result\":\"AUC = 0.871\",\"number_stated\":true}", "reading": {"parent_value": 0.871, "unit": "AUC", "evidence": "Combined detection further improved diagnostic accuracy (AUC = 0.871).", "target_result": "AUC = 0.871", "number_stated": true, "source_locator": "chars 1588-1658 of source sha256 c324bb09f17c2875efaf9eae71acfc90d758220e4200b35d9cf4507971d34efa"}, "recorded_at": "2026-10-31T15:15:19.085960+00:00"}], "agreement": false, "disagreements": {"physical_methods": {"minimax": ["qRT-PCR", "ROC curve analysis", "proliferation, apoptosis, migration, and invasion assays", "nuclear–cytoplasmic fractionation"], "minimax_alt": ["qRT-PCR for circAHSA1 (hsa_circ_0032777) measurement in GC tissues, serum, and cell lines"], "decisive": false}, "analysis_methods": {"minimax": ["DeLong test", "Student’s t-test", "one-way analysis of variance (ANOVA)", "chi-square (χ²) test", "Pearson or Spearman correlation methods", "Youden index"], "minimax_alt": ["2−ΔΔCt relative-expression calculation", "Receiver operating characteristic (ROC) curve analysis with area under the curve (AUC)", "DeLong test for ROC curve and AUC comparisons", "Youden index for optimal cut-off selection"], "decisive": false}, "statistical_method": {"minimax": "DeLong test", "minimax_alt": "ROC curve analysis with AUC comparisons performed using the DeLong test", "decisive": true}, "parent_value": {"minimax": 0.787, "minimax_alt": 0.871, "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:d4575ede973a35f6585b52a4a06498b613295dd2dffc3efcd41a3ca7a03360fb", "type": "sep_package", "label": "SEP v1 package for pmid:41330006"}], "activities": [{"id": "activity:conversion:pmid:41330006", "type": "conversion", "used": ["package:d4575ede973a35f6585b52a4a06498b613295dd2dffc3efcd41a3ca7a03360fb"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41330006", "parent_hash": "sha256:e02f683c1c1bbb4497323507f22053244c818271d3654af6932fdda2e42e39c2", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41330006 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:41330006' 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":"2026-11-04T01:48:46+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}}}