CARA-native MusicGen Small
This is the Phase 2 CARA-native MusicGen Small checkpoint used in the CARA
cross-architecture attribution research. The fork adds a checkpoint-owned,
four-stream CARA suffix vocabulary and trains the expanded language model to
emit three (pool codeword, probability) pairs after the audio tokens.
The release is a peer-review reproduction artifact. A valid CARA suffix proves
that the rewritten output interface works mechanically; it does not prove that
the predicted pool is correct.
Contents
phase2/state_dict.bin: final native fine-tuned AudioCraft LM checkpoint.phase2/native_musicgen_training_report.json: saved training contract.registry/: the exact public CARA pool registry required to decode outputs.evidence/: authoritative score and suffix-structure reports.source/: an exact source snapshot used to load and evaluate this checkpoint.cara_model_manifest.json: byte sizes and SHA-256 values for release files.
Use the immutable phase2-v1 tag, or the Hub commit hash it resolves to, in
reproduction scripts.
Reload
1hf download sammoran-phd/cara-native-musicgen \
2 --revision phase2-v1 \
3 --local-dir cara-native-musicgen-release
4
5mkdir cara-native-musicgen-source
6tar -xzf cara-native-musicgen-release/source/cara-native-musicgen-source.tar.gz \
7 -C cara-native-musicgen-source
8cd cara-native-musicgen-source
9
10python scripts/benchmark_cara_native_musicgen.py \
11 --lm_checkpoint ../cara-native-musicgen-release/phase2/state_dict.bin \
12 --compression_checkpoint facebook/musicgen-small \
13 --cara_registry_path ../cara-native-musicgen-release/registry
The benchmark script has additional required manifest/output arguments; use the
tracked Phase 2 job specification in cara-native-musicmodels for the complete
locked invocation. The compression model remains the unmodified
facebook/musicgen-small codec and is downloaded separately.
Evaluation boundary
On the primary 780-waveform balanced fixed-audio core, the native suffix path
scored 5.38% exact top-1, 9.10% top-3, 21.28% family accuracy, and 100%
registry-valid output. ECE was 92.69%, so the checkpoint is severely
overconfident. On the earlier 320-row prompt-visible benchmark it scored 13.44%
exact top-1 and 16.56% top-3 with 100% registry validity.
The fixed-audio cohort is the primary estimate of audio-conditioned
attribution. Prompt-visible results include a strong semantic route from the
prompt and should not be interpreted as source identification.
Intended use and limitations
This release is intended for research reproduction, interface auditing, and
controlled attribution experiments. It is not a provenance, copyright
identification, royalty allocation, or safety system. The primary fixed-audio
core covers 39 of 98 pools, uses one source corpus, and represents one training
run.
License
The AudioCraft code is MIT licensed. The MusicGen model weights, including this
fine-tuned derivative, are released under CC BY-NC 4.0. See
LICENSE_weights. Commercial use is not granted by this release.
