{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40666499", "kind": "science-record", "revision": 2, "content_hash": "sha256:cf168355d4d7ab60fdd43395e17d6e551fb39425e71f7a67b95f62882c9ffe89", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Clinicopathologic and proteomic characteristics of low-grade undifferentiated spindle cell sarcoma.", "doi": "10.3389/fmolb.2025.1591644", "pmid": "40666499", "authors": null, "journal": "Frontiers in molecular biosciences", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 5600.0, "unit": "proteins", "tolerance": null, "source": "chars 595-639 of source sha256 fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb"}, "evidence": [{"asset": "source:pmid:40666499", "locator": "chars 595-639 of source sha256 fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "quote": "More than 5600 proteins could be identified."}]}], "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:40666499"], "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:40666499", "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:40666499' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40666499", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmolb.2025.1591644", "sha256": "sha256:fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmolb.2025.1591644", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40666499:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:be82906273238114a58af40a0fdc45011fbe451d3035ea06791860363c9ed72b", "bytes": 3620, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Summary of the baseline clinicopathologic characteristics of the low-grade undifferentiated spindle sarcoma.", "structure": {"pmcid": "PMC12259450", "section_index": 9, "section_title": "3.1 Clinicopathologic features of the low-grade USCSs", "row_count": 15, "column_count": 7}, "table": {"label": "TABLE 1", "caption": "Summary of the baseline clinicopathologic characteristics of the low-grade undifferentiated spindle sarcoma.", "rows": [["No", "Age", "Gender", "Anatomical location", "Immunohistochemistry", "Molecular testing", "Follow up"], ["T1", "29", "M", "tibia", "CK (+, focal), Vimentin (+), INI-1 (+), CD34 (+, partial), FLI-1 (−), EMA (+, partial, weak), S-100 (+, focal, weak), SOX10 (−), Ki-67 (20%+), MyoD1 (−), Myogenin (−), TL1-1 (+, focal), SATB2 (−), Desmin (−)", "ND", "20 (NED)"], ["T2", "77", "M", "saliva gland", "CK (−), CK19 (−), EMA (−), CD99 (−), CD34 (−), Bcl-2 (+, focal), STAT-6 (−), Actin (−), Calponin (−), Desmin (−), MyoD1 (−), Myogenin (−), CD117 (−), DOG-1 (−), S-100 (−), Ki-67 (50%+)", "SYT (−)", "50 (NED)"], ["T3", "32", "F", "calf", "Vimentin (+), H-Caldesmon (+, partial, weak), CD99 (+), CK (−), Actin (−), Desmin (−), CD31 (−), Calponin (−), S-100 (−), EMA (−), Bcl-2 (−), CD34 (−), CD68 (−), CD163 (−), CD10 (−), Ki-67 (10%+), P16 (−), CDK4 (−)", "MDM2/CEP12 (−)", "28 (NED)"], ["T4", "61", "F", "retroperitoneal", "CD34 (−), Actin (−), S-100 (−), EMA (−), ALK (−), ER (−), PR (−), HMB-45 (−), Melan-A (−), STAT-6 (−), Desmin (−), MyoD1 (−), Myogenin (−), CD21 (−), CD23 (−), CD68 (+), CK (−), H3K27Me3 (expression)", "MDM2/CEP12 (−), EWSR1 (−)", "NA"], ["T5", "12", "F", "abdominal and pelvic", "Myogenin (−), MyoD1 (−), ALK (D5F3) (−), ALK (D5F3)-Neg (−), CD30 (+), NTRK (−), Brg-1(SMARCA4) (expression), CD117 (−), DOG-1 (−), SDHB (expression), ALK (ALK1) (−), H-Caldesmon (−), Actin (−), Desmin (−), HMB-45 (−), Melan-A (−)", "ND", "22 (NED)"], ["T6", "37", "F", "scapula", "FLI-1 (+, focal), CD31 (−), CD34 (−), Actin (−), Desmin (−), MyoD1 (−), Myogenin (−), S-100 (−), Ki-67 (10%+), RB (expression), P16 (−), CDK4 (−), CK (−), P63 (−)", "ND", "67 (NED)"], ["T7", "56", "M", "liver", "CD117 (−), CD34 (−), DOG-1 (−), SDHB (+, weak), Actin (+, partial), Desmin (−), S-100 (−), Ki-67 (10%), H-Caldesmon (−), ALK (D5F3) (−), ALK (D5F3)-Neg (−), NTRK (−), STAT-6 (−), HMB-45 (−), Melan-A (−)", "SYT (−)", "3 (NED)"], ["T8a", "72", "M", "calf", "Actin (+), CD34 (−), INI-1 (expression), Desmin (−), CD31 (−), ERG (−), S-100 (−), CD68 (−), CD163 (−), Ki-67 (10%–20%+)", "USP6 (−)", "NA"], ["T8b", "72", "M", "calf", "Actin, Desmin (−), MyoD1 (−), Myogenin (−), S-100 (−), CD34 (−), SOX10 (−), P53 (40%+), Ki-67 (40%+)", "ND", "NA"], ["T9a", "66", "M", "groin", "P16 (+), CDK4 (+, focal), Actin (+, partial), Desmin (−), S-100 (−)", "MDM2/CEP12 (−), CHOP (−)", "7 (NED)"], ["T9b", "61", "M", "shoulder and back", "CD34 (−), Actin (+, partial), S-100 (−), EMA (−), Myogenin (−), MyoD1 (−), CK (−), INI-1 (expression), H3K27Me3 (expression)", "ND", "25 (NED)"], ["T10a", "76", "F", "forearm", "HMB-45 (−), Melan-A (−), ALK (ALK1) (−), NTRK (−), P16 (−), CDK4 (+, partial), ERG (−), STAT-6 (−), H3K27Me3 (expression), Brg-1(SMARCA4) (expression), INI-1 (expression)", "MDM2/CEP12 (−)", "60 (LR)"], ["T10b", "48", "M", "groin", "CD34 (−), Desmin (−), Actin (+, partial), Calponin (+), H3K27Me3 (expression), S-100 (+, focal), SOX-10 (−), Ki-67 (40%+)", "ND", "3 (AM)"], ["T11a", "58", "F", "ankle", "Actin (−), Desmin (−), S-100 (+, partial, weak), SOX10 (−), H3K27Me3 (expression), P16 (−), CDK4 (−), CD34 (+, partial), STAT-6 (−), MyoD1 (−), Myogenin (−), Ki-67 (20%+)", "SYT (−)", "4 (NED)"]], "row_count": 15, "column_count": 7, "numeric_cells": 46, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:40666499:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5a596c4648c7987b53a300e2a31f4cfa56d6714e75296526448200237f24f1a8", "bytes": 1360, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T2", "version": null, "note": "Comparison of the clinicopathological features in low-grade USCS and UPS patients.", "structure": {"pmcid": "PMC12259450", "section_index": 10, "section_title": "3.2 Comparison of the characteristics in low-grade USCSs and UPSs", "row_count": 26, "column_count": 5}, "table": {"label": "TABLE 2", "caption": "Comparison of the clinicopathological features in low-grade USCS and UPS patients.", "rows": [["Features", "Total (N = 118)", "Low-grade USCS (N = 14)", "UPS (N = 104)", "P USCS vs. UPS"], ["Age"], ["Mean", "54.2 ± 16.4", "54.1 ± 19.8", "54.22 ± 16.0", "0.975"], ["≤50y", "46 (39.0)", "5 (35.7)", "41 (39.4)", "0.789"], [">50y", "72 (61.0)", "9 (64.3)", "63 (60.6)"], ["Gender"], ["Female", "43 (36.4)", "5 (35.7)5", "38 (36.5)", "0.952"], ["Male", "75 (63.6)", "9 (64.3)", "66 (63.5)"], ["Tumor size"], ["Mean (cm)", "9.1 ± 5.2", "7.6 ± 6.5", "9.3 ± 5.0", "0.245"], ["Location"], ["abdomen", "16 (13.6)", "4 (28.6)", "12 (11.5)", "0.398"], ["axilla", "1 (0.8)", "0 (0.0)", "1 (0.8)"], ["back", "6 (5.1)", "1 (7.1)", "5 (4.8)"], ["chest", "5 (4.2)", "0 (0.0)", "5 (4.2)"], ["head and neck", "3 (2.5)", "1 (7.1)", "2 (1.9)"], ["kidney", "1 (0.8)", "0 (0.0)", "1 (0.8)"], ["liver", "2 (1.7)", "1 (0.8)", "1 (0.8)"], ["lower limb", "69 (58.5)", "5 (35.7)", "64 (61.5)"], ["supraclavicular fossa", "1 (0.8)", "0 (0.0)", "1 (1.0)"], ["upper limb", "14 (11.9)", "2 (14.3)", "12 (11.5)"], ["Distant metastasis"], ["Yes", "16 (13.6)", "1 (7.1)", "15 (14.4)", "0.681"], ["No", "69 (58.5)", "10 (71.4)", "59 (56.7)"], ["NA", "33 (28.0)", "3 (21.4)", "30 (28.8)"], ["Mean (cm)", "9.1 ± 5.2", "7.6 ± 6.5", "9.3 ± 5.0"]], "row_count": 26, "column_count": 5, "numeric_cells": 71, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:40666499:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ee7497eb289b2c1d6da507dd0d06971458f4c30753a6d96b1c57fd5c0660d630", "bytes": 910, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T3", "version": null, "note": "LME and GLIM analysis results.", "structure": {"pmcid": "PMC12259450", "section_index": 13, "section_title": "3.3.2 Protein profiling of low-grade USCSs", "row_count": 11, "column_count": 6}, "table": {"label": "TABLE 3", "caption": "LME and GLIM analysis results.", "rows": [["Protein", "Estimate", "Std. Error", "t value", "Pr (>|t|)", "FDR"], ["PHRF1", "13.60991", "7.628679", "1.784046", "0.14898", "0.372451"], ["RAPH1", "−0.19527", "1.673248", "−0.1167", "0.909971", "0.961097"], ["GGT7", "5.849877", "0.657358", "8.899076", "2.34E-06", "2.34E-05"], ["DIDO1", "10.6748", "3.992107", "2.673976", "0.019119", "0.095595"], ["PHF14", "0.323489", "0.415171", "0.779171", "0.492695", "0.961097"], ["IBA57", "−0.38219", "1.853945", "−0.20615", "0.843489", "0.961097"], ["FBXO2", "−6.05527", "2.741476", "−2.20876", "0.062912", "0.209707"], ["HMGN1", "1.130802", "3.720135", "0.303968", "0.768908", "0.961097"], ["IRF2BP1", "−0.06678", "1.340827", "−0.0498", "0.961097", "0.961097"], ["DDX39A", "−0.15762", "0.772589", "−0.20402", "0.84176", "0.961097"]], "row_count": 11, "column_count": 6, "numeric_cells": 53, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T3"}}], "gaps": ["asset:source:pmid:40666499 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:40666499", "asset:table:pmid:40666499:1", "asset:table:pmid:40666499:2", "asset:table:pmid:40666499:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40666499"]}, "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": "347553f4c3998360d17e6cdcddda5fe3ef3b1b13dcec687e9f55d84ddfc66876", "source_hash": "fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "raw_response_sha256": "sha256:fef1bf89a49c21617782ccb78bf22c82d340cb28142eb4977b7e1da48cb20b1b", "raw_response_chars": 4015}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "a5b375c3fc53b3307b5dbee2147dc759c35713ce026d37068707cb15b0524a51", "source_hash": "fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "raw_response_sha256": "sha256:7ea9f6fd155329ba5f839ef57d164fa58d9ddb660eecb02dcef40434539246e4", "raw_response_chars": 52325}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "84f20f3cbf33f1b99ec82b3bd04e2085860727436985edfea9ed4f70fc0f4f10", "source_hash": "fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "raw_response": "{\"parent_value\":5600,\"unit\":\"proteins\",\"evidence\":\"More than 5600 proteins could be identified.\",\"target_result\":\"More than 5600 proteins could be identified.\",\"number_stated\":true}", "reading": {"parent_value": 5600, "unit": "proteins", "evidence": "More than 5600 proteins could be identified.", "target_result": "More than 5600 proteins could be identified.", "number_stated": true, "source_locator": "chars 595-639 of source sha256 fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb"}, "recorded_at": "2026-10-31T15:20:49.214510+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "ec577fd55e3bdb68855d52d97e8c8967cb0c260a55a7f52d093cbbe844495510", "source_hash": "fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Ambiguity. Need infer likely target = headline numerical result in abstract? Paper says 14 low-grade USCS and 104 UPS; &gt;5600 proteins identified; low-grade had 353 upregulated and 500 downregulated. Registered target \"headline numerical result the paper states for its main finding.\" They expect perhaps 5600 proteins? Need carefully parse request. They ask \"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.\" Target supplied vague: \"the headline numerical result the paper states for its main finding\". Need identify likely headline numerical result based on source. In abstract: \"More than 5600 proteins could be identified.\" This might be headline numerical result. Or 353 upregulated and 500 downregulated proteins = two numbers, not single. Sample sizes 14 and 104, two. The singular main numerical result perhaps 6,677 proteins identified / 5,687 comparison, but results section. Yet \"headline numerical result\" likely abstract's standout number, 5600 proteins. They want number perhaps 5600 and unit proteins. Need quote exact contiguous clause: \"More than 5600 proteins could be identified.\" Parent value numeric 5600, unit \"proteins\". target_result maybe \"More than 5600 proteins could be identified.\" Or target result field text description. number_stated true.\n\nBut perhaps headline result is \"Low-grade USCSs had 353 upregulated and 500 downregulated proteins compared to corresponding normal tissue.\" That is main finding, yet not single number. They explicitly singular \"single numerical result\". Registered target perhaps benchmark extraction where target label itself refers to something broad? Usually prompt generation asks \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\" and source. Need find likely one number. Could be sample count 14? Let's understand expected schema naming parent_value perhaps used in tasks to extract value attached to target. Target_result textual. \"number_stated\" if no number. Here target is tautological, likely intended headline number from abstract. The abstract's prominent quantitative conclusion: &gt;5600 proteins identified. Later says 6,677 total and 5,687 available comparison. But headline says \"More than 5600 proteins could be identified.\" Since replication of main finding likely reproduce number of identified proteins, perhaps 5600. They emphasize value paper itself states, not calculated/converted/averaged/reconstructed. So use printed \"5600\" (not 6,677? Both printed). Unit paper prints \"proteins\". Exact quote.\n\nNeed ensure JSON valid and no extra. parent_value 5600 number, unit \"proteins\", evidence exact quote. target_result perhaps \"More than 5600 proteins could be identified.\" Should we mention \"more than\" because parent_value can't encode inequality except 5600. Unit must exact unit printed. target_result can be same. number_stated true.\n\nCould evidence include whole clause perhaps \"We conducted a comprehensive mass spectrometry (MS) proteomic analysis on USCSs and compared the clinicopathologic characteristics of low-grade USCSs and UPSs. More than 5600 proteins could be identified.\" They say quote whole clause if attribution via wording. \"More than 5600 proteins could be identified.\" itself enough attribution? Yes target main finding and subject implied from prior sentence. To allow reader check, perhaps quote two sentences, but exact contiguous. Yet target registered = headline numerical result main finding; no named target. The quote with method identifies context. However evidence must contain number and exact contiguous; can include preceding sentence. \"We conducted ... More than 5600 proteins could be identified.\" This helps attribution. Should we use abstract occurrence. Unit \"proteins\" exact.\n\nCould target_result be \"More than 5600 proteins could be identified.\" Fine.\n\nLet's answer.</think>\n\n{\"parent_value\":5600,\"unit\":\"proteins\",\"evidence\":\"We conducted a comprehensive mass spectrometry (MS) proteomic analysis on USCSs and compared the clinicopathologic characteristics of low-grade USCSs and UPSs. More than 5600 proteins could be identified.\",\"target_result\":\"More than 5600 proteins could be identified.\",\"number_stated\":true}", "reading": {"parent_value": 5600, "unit": "proteins", "evidence": "We conducted a comprehensive mass spectrometry (MS) proteomic analysis on USCSs and compared the clinicopathologic characteristics of low-grade USCSs and UPSs. More than 5600 proteins could be identified.", "target_result": "More than 5600 proteins could be identified.", "number_stated": true, "source_locator": "chars 435-639 of source sha256 fc752977cf3ff13ad66a20a2ea348c5b131bb0d097569a121ac8a8eb1ffec9cb"}, "recorded_at": "2026-10-31T15:20:50.804263+00:00"}], "agreement": false, "disagreements": {"work_type": {"minimax": "analysis_plus_physical_validation", "minimax_alt": "physical_data_generation", "decisive": true}, "analysis_methods": {"minimax": ["differential protein analysis", "KEGG pathway enrichment analysis", "GO enrichment analysis", "Reactome enrichment analysis", "WikiPathways enrichment analysis", "protein domain enrichment analysis", "protein interaction network analysis"], "minimax_alt": ["quantitative analysis of protein intensity values", "GO, KEGG, protein domain, Reactome and WikiPathways enrichment analyses", "protein interaction network analysis", "DrugBank drug target prediction"], "decisive": false}}, "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:c5491a654b26965bef36b115f08968a83730b9d8132be497a91d73b18438f515", "type": "sep_package", "label": "SEP v1 package for pmid:40666499"}], "activities": [{"id": "activity:conversion:pmid:40666499", "type": "conversion", "used": ["package:c5491a654b26965bef36b115f08968a83730b9d8132be497a91d73b18438f515"], "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:40666499", "parent_hash": "sha256:79011f04aca003c80e503d391b6394400c48dcbba93531b71dfc154a8986e5b4", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40666499 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:40666499' 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":"2026-11-04T03:35:07+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}