{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A2MOFVC2RJ23EMXRQEN53KLUIV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9f1786519a720b938e35f38c4f6d73d32abc3a18158fdee153fb4a36e7abec1e","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T16:46:18Z","title_canon_sha256":"aa840ec4aa143b9907bcb03eb9479d07ed0a285034c67c66ed9d9c2233d12ac9"},"schema_version":"1.0","source":{"id":"2409.06635","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06635","created_at":"2026-07-05T10:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06635v4","created_at":"2026-07-05T10:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06635","created_at":"2026-07-05T10:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"A2MOFVC2RJ23","created_at":"2026-07-05T10:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"A2MOFVC2RJ23EMXR","created_at":"2026-07-05T10:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"A2MOFVC2","created_at":"2026-07-05T10:51:25Z"}],"graph_snapshots":[{"event_id":"sha256:456a5dc4c719e4c04cacf6b9984a5c1e1d460f88cf2fd54d4d1292da3e65cfef","target":"graph","created_at":"2026-07-05T10:51:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.06635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text. Existing AudioLLMs typically combine a pre-trained audio encoder with a pre-trained LLM, which are subsequently finetuned on specific audio tasks. However, the pre-trained audio encoder has constrained capacity to capture features for new tasks and datasets. To address this, we propose to incorporate mixtures of `weak' encoders (MoWE) into the AudioLLM framework.","authors_text":"Ai Ti Aw, Bin Wang, Geyu Lin, Nancy F. Chen, Shuo Sun, Wenyu Zhang, Xunlong Zou, Yingxu He, Zhuohan Liu","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T16:46:18Z","title":"MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06635","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0333a640cd0e8bd7dbce49ada5931119f8a83fe8552a4217999cd6d6520e106","target":"record","created_at":"2026-07-05T10:51:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9f1786519a720b938e35f38c4f6d73d32abc3a18158fdee153fb4a36e7abec1e","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T16:46:18Z","title_canon_sha256":"aa840ec4aa143b9907bcb03eb9479d07ed0a285034c67c66ed9d9c2233d12ac9"},"schema_version":"1.0","source":{"id":"2409.06635","kind":"arxiv","version":4}},"canonical_sha256":"0698e2d45a8a75b232f1811bdda974456adfb9d23ac347ec7d095dfb86e462f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0698e2d45a8a75b232f1811bdda974456adfb9d23ac347ec7d095dfb86e462f8","first_computed_at":"2026-07-05T10:51:25.391728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:25.391728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WPhDu1nImfDkzlzBe2k3Caah/2zM4sIIvP1acSm88AC6LbHkfYVvipwL7SXKuFD+MNyJjqNVPXhPWuVr+uGECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:25.392279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06635","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0333a640cd0e8bd7dbce49ada5931119f8a83fe8552a4217999cd6d6520e106","sha256:456a5dc4c719e4c04cacf6b9984a5c1e1d460f88cf2fd54d4d1292da3e65cfef"],"state_sha256":"466dad2497f24ba13337b588591eed20d2abf94daf4b80a9cda2554529952e4c"}