Evaluation

Chai-1 on How well ipTM tracks DockQ on cognate nanobody-antigen complexes (Smorodina et al. 2026)

Published comparison; transcribed, not reproduced.

Research readiness

These checks assess whether the evidence supports a reproducible investigation. A source-checked score alone does not meet these requirements.

Release 2026-10-10-6e93f504adfc · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
metric replay: verification is missing
annotations: verification is missing
dependence: verification is missing

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
recipe pinned: verification is missing
resource estimate: verification is missing

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

No verified artifact manifest is linked to this exact record.
artifact hashes: verification is missing
join integrity: verification is missing
score semantics: verification is missing
independent validation: verification is missing
overlap checked: verification is missing

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Read reviewed discrepancy investigations

Evaluation results

1 evaluation · 3 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Chai-1 0.6.1, 5 trunk x 10 diffusion samples, seed 42, ESM embeddings without MSAs (Smorodina et al. 2026)	Protocol: How well ipTM tracks DockQ on cognate nanobody-antigen complexes Dataset: Smorodina et al. 2026 nanobody-antigen benchmark: 106 cognate VHH-antigen complexes	0.612 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Chai-1 on How well ipTM tracks DockQ on cognate nanobody-antigen complexes (Smorodina et al. 2026) structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration Aggregation: Not reported Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores · Results P19, Chai-1: ipTM against DockQ for the best-DockQ sample of each complex
Configuration: Chai-1 0.6.1, 5 trunk x 10 diffusion samples, seed 42, ESM embeddings without MSAs (Smorodina et al. 2026)	Protocol: How well ipTM tracks DockQ on cognate nanobody-antigen complexes Dataset: Smorodina et al. 2026 nanobody-antigen benchmark: 106 cognate VHH-antigen complexes	-0.019 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Chai-1 on How well ipTM tracks DockQ on cognate nanobody-antigen complexes (Smorodina et al. 2026) structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration Aggregation: Not reported Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores · Results P21, Chai-1: change in ipTM against change in DockQ under saturation sampling
Configuration: Chai-1 0.6.1, 5 trunk x 10 diffusion samples, seed 42, ESM embeddings without MSAs (Smorodina et al. 2026)	Protocol: How well ipTM tracks DockQ on cognate nanobody-antigen complexes Dataset: Smorodina et al. 2026 nanobody-antigen benchmark: 106 cognate VHH-antigen complexes	24% proportion percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Chai-1 on How well ipTM tracks DockQ on cognate nanobody-antigen complexes (Smorodina et al. 2026) structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration Aggregation: Not reported Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores · Results P19, Chai-1: share of predictions with ipTM below 0.5 and DockQ at least 0.23 (unconfident successes, Q4)

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Evaluation procedure

structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration

Configuration: Chai-1 0.6.1, 5 trunk x 10 diffusion samples, seed 42, ESM embeddings without MSAs (Smorodina et al. 2026)
Protocol: How well ipTM tracks DockQ on cognate nanobody-antigen complexes
Dataset: Smorodina et al. 2026 nanobody-antigen benchmark: 106 cognate VHH-antigen complexes

origin: Independent external evaluation
configuration: Primary source as retrieved 2026-10-09
protocol id: structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration
dataset version: bioRxiv v1 benchmark
split: Mixed: systems inside and outside the tool's training data
inputs: VHH and antigen sequences
adaptation: None
population: 106 cognate complexes
metric implementation: Pearson correlation; DockQ v2.1.3
aggregation: Across complexes
budget: 50 samples per complex

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split: Mixed: systems inside and outside the tool's training data
Adaptation: None
Scoring implementation: Pearson correlation; DockQ v2.1.3

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

19 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance
attributes.comparison.adaptation None Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.adaptation` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.aggregation Across complexes Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.aggregation` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.budget 50 samples per complex Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.budget` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.dataset_version bioRxiv v1 benchmark Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.dataset_version` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.inputs VHH and antigen sequences Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.inputs` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.metric_implementation Pearson correlation; DockQ v2.1.3 Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.metric_implementation` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.population 106 cognate complexes Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.population` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.protocol_id structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.protocol_id` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.comparison.split Mixed: systems inside and outside the tool's training data Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.comparison.split` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact
attributes.limitations 2 values Run by authors who did not develop the tool. Not printed in the text for this tool: ipTM against DockQ for the first sample (sample0) of each complex; share of predictions with ipTM at least 0.5 and DockQ below 0.23 (confident failures, Q2). Context-only references	Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores Original source ↗ Results P19 and P21, values for 'Chai-1' Version: bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed Retrieved: 2026-10-09T21:25:48Z	not individually reviewed No individual claim review recorded independent paper Audit details Field: `attributes.limitations` Source artifact SHA-256: `0ad24054d98fd1888fa8bf3120f76e22f7bf6b1965261b16f045986d72c50732` Hash scope: JATS XML parse (xml.etree), by extract/extract_structural.py Inspected artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release history

Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores · Original source · bioRxiv version 1, posted 2026-03-03; Europe PMC preprint full text PPR1221387 (manuscript EMS215481); not peer reviewed

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: structural-20261009-eval-smorodina2026-vhh-iptm-dockq-calibration-chai1

areas: proteins-complexes
contexts: research
origin: independent_paper
protocol: structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration
version: Primary source as retrieved 2026-10-09
comparison: protocol id: structural-20261009-protocol-smorodina2026-vhh-iptm-dockq-calibration; dataset version: bioRxiv v1 benchmark; split: Mixed: systems inside and outside the tool's training data; inputs: VHH and antigen sequences; adaptation: None; population: 106 cognate complexes; metric implementation: Pearson correlation; DockQ v2.1.3; aggregation: Across complexes; budget: 50 samples per complex
source locator: Results P19 and P21, values for 'Chai-1'
limitations: Run by authors who did not develop the tool.; Not printed in the text for this tool: ipTM against DockQ for the first sample (sample0) of each complex; share of predictions with ipTM at least 0.5 and DockQ below 0.23 (confident failures, Q2).

Related records

Suggest a correction