rewire.it
Model

MIMIC

MIMIC represents DNA, RNA, protein and associated molecular measurements in a shared multimodal model.

Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Results are available for configurations using this model. Their fitted heads, extra inputs and evaluation settings are kept separate below.

1 evaluated configuration using this model

How it worksMIMIC workflow
MIMIC workflow1. Observed modalities. Then: 2. Shared encoder. Then: 3. Track-aware decoder. Then: 4. Embeddings or generated tracksMIMIC workflow1. Observed modalities. Then: 2. Shared encoder. Then: 3. Track-aware decoder. Then: 4. Embeddings or generated tracksMIMIC workflow1. Observed modalities. Then: 2. Shared encoder. Then: 3. Track-aware decoder. Then: 4. Embeddings or generated tracks

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Overview

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

Related configurations, pipelines and services

These configurations, services and pipelines use this model within their own configurations. Their results, where available, are not assigned to the underlying model.

  • MIMIC Pipeline · 7 metric rows

Use this model

How it works, versions and access

How it works

How it works

MIMIC represents DNA, RNA, protein and associated molecular measurements in a shared multimodal model. Transformer encoder-decoder: 20 encoder layers and 12 decoder layers, width 1,536, rotary positional embeddings, mixed attention and five register tokens. The documented inputs are co-observed molecular modalities and optional text context, grouped into nucleic, protein and text tracks. The output consists of embeddings or generated modalities, such as residue solvent accessibility or splice-site classes.

Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Versions and reproducibility

MIMIC 1.0; load_pretrained(version="1.0") example. Training curriculum increases encoder context from 1k to 10k tokens; the released configuration specifies 10,000 input tokens and 1,000 target tokens.

Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Strengths, limitations and unresolved questions

Strengths and limitations

Limitations and conditions

Profile review details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Stable record: catalog-model-mimic

Specifications

Inputs, training, access and other details

Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
PropertyDescription and evidence
Model typeMultimodal biomolecular transformer encoder-decoder
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
ArchitectureTransformer encoder-decoder: 20 encoder layers and 12 decoder layers, width 1,536, rotary positional embeddings, mixed attention and five register tokens.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
InputsCo-observed molecular modalities and optional text context, grouped into nucleic, protein and text tracks.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
OutputsEmbeddings or generated modalities, such as residue solvent accessibility or splice-site classes.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
ParametersApproximately 1.25 billion.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Known versionsMIMIC 1.0; load_pretrained(version="1.0") example.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Training dataLORE aligns approximately 15.5M proteins and 13M RNA transcripts from over 6,000 organisms with associated molecular measurements and over 4B text tokens. Missing modalities are retained as partially observed examples.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Training cutoffLORE protein/transcript linking uses UniProt release 2024_04. This component version does not establish a common latest-data date for all molecular and text tracks.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Context limitsTraining curriculum increases encoder context from 1k to 10k tokens; the released configuration specifies 10,000 input tokens and 1,000 target tokens.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Weights licenceMIT; model card explicitly covers both model and source code.
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
AccessOfficial downloadable model/card and usage examples: https://huggingface.co/polymathic-ai/MIMIC
Sources (4)polymathic-ai/MIMIC: README.md; polymathic-ai/MIMIC: config.json; PolymathicAI/MIMIC: README.md; mimic: Primary paper PDF · MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens
Code licenceMIT
SourcesPolymathicAI/MIMIC: LICENSE · LICENSE: licence text

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.

77 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-23-2b89723c6dd9
Property and statementOriginal source and locationReview and provenance
Diagram caption
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Individual claims
mimic: Primary paper PDF

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 2604.24506v1
Retrieved: 2026-09-16T20:04:04.776851+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 0ba8639b263f0e7f736bbd4564a8b1acca1f66acc4300cffd3c26e6bf2e93ffe

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram caption
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Individual claims
polymathic-ai/MIMIC: config.json

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 72e63a1ece34928422fd46f89b6a6580ace99a97
Retrieved: 2026-09-16T19:46:20.846683+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 687e182e410fbfa235e24c337f51411c6fff583d3135fdbac202b08b0e63a8ef

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram caption
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Individual claims
polymathic-ai/MIMIC: README.md

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 72e63a1ece34928422fd46f89b6a6580ace99a97
Retrieved: 2026-09-16T19:46:20.846683+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 462acc643cba24d1d4c6f1419838402c5f3196e94260039baf61a59ef0a0a107

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram caption
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Individual claims
PolymathicAI/MIMIC: README.md

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 9e652f16491e6c2e3881111e24b285c288554275
Retrieved: 2026-09-16T20:04:02.231308+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 694bed54356d27cf087890ed80649c08ef4520a0eb5c85374a7347138a6cbb2f

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram steps
  • Observed modalities
  • Shared encoder
  • Track-aware decoder
  • Embeddings or generated tracks
Individual claims
mimic: Primary paper PDF

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 2604.24506v1
Retrieved: 2026-09-16T20:04:04.776851+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 0ba8639b263f0e7f736bbd4564a8b1acca1f66acc4300cffd3c26e6bf2e93ffe

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram steps
  • Observed modalities
  • Shared encoder
  • Track-aware decoder
  • Embeddings or generated tracks
Individual claims
polymathic-ai/MIMIC: config.json

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 72e63a1ece34928422fd46f89b6a6580ace99a97
Retrieved: 2026-09-16T19:46:20.846683+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 687e182e410fbfa235e24c337f51411c6fff583d3135fdbac202b08b0e63a8ef

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram steps
  • Observed modalities
  • Shared encoder
  • Track-aware decoder
  • Embeddings or generated tracks
Individual claims
polymathic-ai/MIMIC: README.md

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 72e63a1ece34928422fd46f89b6a6580ace99a97
Retrieved: 2026-09-16T19:46:20.846683+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 462acc643cba24d1d4c6f1419838402c5f3196e94260039baf61a59ef0a0a107

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram steps
  • Observed modalities
  • Shared encoder
  • Track-aware decoder
  • Embeddings or generated tracks
Individual claims
PolymathicAI/MIMIC: README.md

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 9e652f16491e6c2e3881111e24b285c288554275
Retrieved: 2026-09-16T20:04:02.231308+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 694bed54356d27cf087890ed80649c08ef4520a0eb5c85374a7347138a6cbb2f

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram title
MIMIC workflow
Individual claims
mimic: Primary paper PDF

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 2604.24506v1
Retrieved: 2026-09-16T20:04:04.776851+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 0ba8639b263f0e7f736bbd4564a8b1acca1f66acc4300cffd3c26e6bf2e93ffe

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Diagram title
MIMIC workflow
Individual claims
polymathic-ai/MIMIC: config.json

Original source ↗

MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens

Shared locator for this statement’s cited sources; not a separate locator for each citation.

Version: 72e63a1ece34928422fd46f89b6a6580ace99a97
Retrieved: 2026-09-16T19:46:20.846683+00:00

source checked

automated source review · 2026-09-16

Audit details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 687e182e410fbfa235e24c337f51411c6fff583d3135fdbac202b08b0e63a8ef

Hash scope: SHA-256 of retrieved original artifact bytes

Format: original_artifact

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-23-2b89723c6dd9 · Record review: discovered

6 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: catalog-model-mimic

areas
rna-transcriptomes; proteins-complexes
method types
foundation model
entity level
family
version
1.0
reported name
MIMIC
access
Public MIT code and 1.25B-parameter weights; large local memory requirement.
method type
foundation model
historical missing metadata
checkpoint revision: not_yet_extracted; training data: not_yet_extracted; licence: not_yet_extracted
metadata review scope
historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
entity classification
review date: 2026-09-17; rationale: The cited profile describes a named learned biological predictor or representation model/family. Preserve this identity separately from task-specific fitting, individual checkpoints, pipelines and hosted access.; source ids: evidence-official-af8da643e933eae36a68; evidence-official-4565e66fdeb787b99afa; evidence-official-c14c0e6a0fdbe1479658; evidence-official-0ffe1031786a71400ffd; source locator: MIMIC paper Section 3 and Discussion; official model-card Architecture and License; config.json num_input_tokens and num_target_tokens; ambiguities: None recorded
Related records

Suggest a correction