{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NNHAX3QVBWEST5EJVOP2CPUVCR","short_pith_number":"pith:NNHAX3QV","canonical_record":{"source":{"id":"2406.10056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ee7bd0ec8009d1ed5ed728c3200620fc8a83f118c4ba2ea04e6bb9306b731ee1","abstract_canon_sha256":"6943b16faa0983890dd732f04a61fa7a5ec1a3333f59f1ee3c978eac3ed8e411"},"schema_version":"1.0"},"canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","source":{"kind":"arxiv","id":"2406.10056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10056","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10056v1","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10056","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"NNHAX3QVBWES","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"NNHAX3QVBWEST5EJ","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"NNHAX3QV","created_at":"2026-07-05T08:32:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NNHAX3QVBWEST5EJVOP2CPUVCR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ee7bd0ec8009d1ed5ed728c3200620fc8a83f118c4ba2ea04e6bb9306b731ee1","abstract_canon_sha256":"6943b16faa0983890dd732f04a61fa7a5ec1a3333f59f1ee3c978eac3ed8e411"},"schema_version":"1.0"},"canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:03.918567Z","signature_b64":"mRxDlpCrxz6LlWMpval7JxNjr14NVnU4i+VhO7T3Qmua07wozZ/Ti3mBs1Fq70LS7+Tt/jmaKKFLyl0g2hiKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","last_reissued_at":"2026-07-05T08:32:03.918092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:03.918092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10056","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhVD3bIAsRBtH3RVzt/B75DYLFB37sikALYwi5S17weRUiRZFrcP+y+cka7sZNKApzM7p19BCYL8giMvnae/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:06:26.244632Z"},"content_sha256":"491fc1006337b4bb3e3c01bbad9911ae418d3580cdc09d21beebdf20be4d12cd","schema_version":"1.0","event_id":"sha256:491fc1006337b4bb3e3c01bbad9911ae418d3580cdc09d21beebdf20be4d12cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NNHAX3QVBWEST5EJVOP2CPUVCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Xiang Li, Xixin Wu, Xu Tan, Yuanyuan Wang","submitted_at":"2024-06-14T14:13:18Z","abstract_excerpt":"The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \\textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10056","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.10056/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TjzMvXq6/b2GtIGc4zih38CG09+49RIeXsCn2maRuXcjnfwZkhYKREYx9UDdT5/NQC1WgNVa/BKBWY4ydU+SDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:06:26.246054Z"},"content_sha256":"9160c574f606cf87e43511a4dadb786627f2d5098afb1c8059dc8599a8d4ebe5","schema_version":"1.0","event_id":"sha256:9160c574f606cf87e43511a4dadb786627f2d5098afb1c8059dc8599a8d4ebe5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/bundle.json","state_url":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T16:06:26Z","links":{"resolver":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR","bundle":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/bundle.json","state":"https://pith.science/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNHAX3QVBWEST5EJVOP2CPUVCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NNHAX3QVBWEST5EJVOP2CPUVCR","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":"6943b16faa0983890dd732f04a61fa7a5ec1a3333f59f1ee3c978eac3ed8e411","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","title_canon_sha256":"ee7bd0ec8009d1ed5ed728c3200620fc8a83f118c4ba2ea04e6bb9306b731ee1"},"schema_version":"1.0","source":{"id":"2406.10056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10056","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10056v1","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10056","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"NNHAX3QVBWES","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"NNHAX3QVBWEST5EJ","created_at":"2026-07-05T08:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"NNHAX3QV","created_at":"2026-07-05T08:32:03Z"}],"graph_snapshots":[{"event_id":"sha256:9160c574f606cf87e43511a4dadb786627f2d5098afb1c8059dc8599a8d4ebe5","target":"graph","created_at":"2026-07-05T08:32:03Z","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/2406.10056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \\textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high ","authors_text":"Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Xiang Li, Xixin Wu, Xu Tan, Yuanyuan Wang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10056","kind":"arxiv","version":1},"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":"sha256:491fc1006337b4bb3e3c01bbad9911ae418d3580cdc09d21beebdf20be4d12cd","target":"record","created_at":"2026-07-05T08:32:03Z","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":"6943b16faa0983890dd732f04a61fa7a5ec1a3333f59f1ee3c978eac3ed8e411","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:13:18Z","title_canon_sha256":"ee7bd0ec8009d1ed5ed728c3200620fc8a83f118c4ba2ea04e6bb9306b731ee1"},"schema_version":"1.0","source":{"id":"2406.10056","kind":"arxiv","version":1}},"canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b4e0bee150d8929f489ab9fa13e95147dd1db8141148a6bf2382e0aaeac7897","first_computed_at":"2026-07-05T08:32:03.918092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:03.918092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mRxDlpCrxz6LlWMpval7JxNjr14NVnU4i+VhO7T3Qmua07wozZ/Ti3mBs1Fq70LS7+Tt/jmaKKFLyl0g2hiKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:03.918567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:491fc1006337b4bb3e3c01bbad9911ae418d3580cdc09d21beebdf20be4d12cd","sha256:9160c574f606cf87e43511a4dadb786627f2d5098afb1c8059dc8599a8d4ebe5"],"state_sha256":"1a1fab44c86bf64fcec8b772df8eab251842482f018c8ce562a023bcf9255696"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D81Jj4RZYV/8xmp5tWp3BuMf+eeT4XhSTKij4JQcVz222nUKJYDxSC25hY8cQD+wJVnp5ffa3b6XEexrbGwaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:06:26.254108Z","bundle_sha256":"0017351a826b5b4b8c23601dcb76fc13f820956c0254ed9ab43e251ae43125fe"}}