{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41443412", "kind": "science-record", "revision": 2, "content_hash": "sha256:8da9907db9eb9d6b7f8bf367743bcbb37d7d914fc4d9c70decf484d3a7952b60", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "TIM-3 inhibition enhances breast tumor progression and metastasis: A paradoxical immune checkpoint response.", "doi": "10.1016/j.jbc.2025.111096", "pmid": "41443412", "authors": null, "journal": "The Journal of biological chemistry", "year": 2025, "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:41443412"], "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:41443412", "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:41443412' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41443412", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.jbc.2025.111096", "sha256": "sha256:a7c79b846b2ed63804b81064b68d47071a9cd6060aeb1957f10655be3f823189", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.jbc.2025.111096", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41443412:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:404066e1f74f05f06b90ccaf2dfce04dff39f7f5529840f64122ec7d669a4244", "bytes": 2837, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tbl1", "version": null, "note": "Pathway enrichment analysis using gene ontology (GO) annotation showing significantly upregulated pathways and corresponding up regulated genes after treatment with TIM-3 antibody into murine breast tumor", "structure": {"pmcid": "PMC12856319", "section_index": 13, "section_title": "Blockades of TIM-3 upregulate Bat3 and TCR-activated gene expression", "row_count": 13, "column_count": 5}, "table": {"label": "Table 1", "caption": "Pathway enrichment analysis using gene ontology (GO) annotation showing significantly upregulated pathways and corresponding up regulated genes after treatment with TIM-3 antibody into murine breast tumor", "rows": [["Category", "Term", "Enrichment FDRa", "Fold enrichment", "Key upregulated genes"], ["PANTHER-PATHWAY", "P00034 -Integrin signaling pathway", "3.40E-15", "5.049677912", "Ptk2b Lama5 Rhoc Pxn Lama4 Ilk Mapk1 Mapk3 Mapk13 Map2k1 Actn4 Rap2c Dock1 Flnb Actg1 Col18a1 Col4a1 Col5a1 Col5a2 Crk Csk Flna Fn1 Grb2 Itga1 Itga2 Itga5 Itga6 Itgal Itgav Itgb1 Lamb1 Pik3r1 Rac1 Rap1a Rras Lamb3"], ["P04393-Ras Pathway", "9.15E-05", "4.198966408", "Stat3 Rps6ka1 Rhoc Pak2 Mapk1 Mapk3 Mapk13 Map2k1 Gsk3b Ralb Gsk3a Grb2 Rac1"], ["P00018-EGF receptor signaling pathway", "1.31E-06", "4.07996736", "Stat6 Stat5b Stat3 Ywhag Ywhah Ywhaz Pebp1 Mapk1 Mapk3 Mapk13 Map2k1 Ywhab Ywhaq Ywhae Egfr Grb2 Prkcd Plcg2 Rac1 Rras"], ["P00056-VEGF signaling pathway", "0.000261494", "4.009623095", "Pxn Pla2g4a Mapk1 Mapk3 Map2k1 Arhgap1 Hspb1 Nos3 Pik3r1 Prkcd Plcg2 Rac1"], ["P00053-T cell activation", "0.000303922", "3.875968992", "Ppp3ca Pak2 Mapk1 Mapk3 Map2k1 Csk Grb2 Cd74 Nfkb1 Pik3r1 Rac1 Vav1"], ["P00016-Cytoskeletal reg. by Rho GTPase", "0.000340001", "3.812428517", "Cfl2 Rhoc Tubb2a Diaph1 Pak2 Tubb6 Arpc4 Tubb2b Myh10 Arhgap1 Actg1 Rac1"], ["P00005- Angiogenesis", "0.00047917", "2.649043556", "Stat3 Rhoc Pxn Pla2g4a Pak2 Mapk1 Mapk3 Map2k1 Gsk3b Arhgap1 Ctnnb1 Crk Grb2 Hspb1 Rbpj Nos3 Pik3r1 Prkcd Plcg2"], ["KEGG-PATHWAY", "Path: mmu04512 ECM-receptor interaction", "1.66E-05", "2.862353", "Itga1 Npnt Col4a1 Dag1 Fn1 Itga2 Itga5 Itga6 Itgav Itgb1 Itgb5 Lama4 Lama5 Lamb1 Lamb3 Lamc2 Itgb4 Sdc1 Thbs1 Thbs2 Tnc Vwf Lamc1 Col6a4"], ["Path:mmu04370 VEGF signaling pathway", "0.005136536", "2.533347", "Hspb1 Nos3 Nras Pik3r1 Pla2g4a Ppp3ca Ptgs2 Pxn Rac1 Plcg2 Map2k1 Mapk1 Mapk13 Mapk3"], ["Path: mmu04066 HIF-1 signaling pathway", "5.30E-05", "2.507725", "Aldoa Egfr Eif4e Eno3 Hk1 Hk2 Ldha Ldhb Nfkb1 Nos3 Pdha1 Pgk1 Pik3r1 Rps6 Stat3 Hk3 Timp1 Tfrc Plcg2 Map2k1 Mapk1 Mapk3 Eno1b Pfkp Elob Pdhb Rps6kb1"], ["Path: mmu04151 P I3K-Akt signaling pathway", "0.016078686", "1.469929", "Prkaa1 Itga1 Col4a1 Egfr Eif4e Epha2 Fn1 Gnb1 Gnb2 Grb2 Gys1 Itga2 Itga5 Itga6 Itgav Itgb1 Itgb5 Lama4 Lama5 Lamb1 Lamb3 Lamc2 Nfkb1 Nos3 Nras Pik3r1 Pten Itgb4 Rac1 Rps6 Thbs1 Thbs2 Tnc Vwf Ywhae Ywhag Ywhah Ywhaq Ywhaz Lamc1 Map2k1 Mapk1 Mapk3 Ppp2r1a Ywhab Gsk3b Col6a4 Rps6kb1 Pck2 Eif4b"], ["REACTOME-PATHWAY", "R-MMU-5676590 NIK--noncanonical NF-kB signaling", "3.37E-10", "4.343545", "Ube2m Psmd4 Psmb4 Psmd2 Psmd3 Psmd11 Psmb6 Rps27a Psmc5 Psma6 Psmc1 Psmc6 Psmb8 Psmd13 Psmd1 Psma7 Psmb2 Psmc2 Cul1 Uba3 Psmd8 Psmc4 Psmb10 Psma4 Skp1 Psma5 Psmb3"]], "row_count": 13, "column_count": 5, "numeric_cells": 43, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tbl1"}}], "gaps": ["asset:source:pmid:41443412 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:41443412", "asset:table:pmid:41443412:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41443412"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "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": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"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", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:94e50afb371f3af14f961edaeb17c49a935d19a0060828a147f1d5cccd244115", "type": "sep_package", "label": "SEP v1 package for pmid:41443412"}], "activities": [{"id": "activity:conversion:pmid:41443412", "type": "conversion", "used": ["package:94e50afb371f3af14f961edaeb17c49a935d19a0060828a147f1d5cccd244115"], "agent": "agent:corpus-assay-engine"}], "agents": [{"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:41443412", "parent_hash": "sha256:7da196cca17a94429ed1eda00f14bef568f0d5552425535cc9214859b791e6c3", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41443412 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "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:41443412' 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":"2026-11-04T02:50:52+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}}}