{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IEHH33UU4SPVC757CTA665O4DB","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":"9f878704f65c864f30c3f74414d16baaa65166af894a6b1764e8541ae647fe03","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T17:20:56Z","title_canon_sha256":"57832b3160b858c06e8a69fc570f7484872d85fab493c29098c6563b3a046e76"},"schema_version":"1.0","source":{"id":"2305.11834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11834","created_at":"2026-07-05T07:35:18Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11834v2","created_at":"2026-07-05T07:35:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11834","created_at":"2026-07-05T07:35:18Z"},{"alias_kind":"pith_short_12","alias_value":"IEHH33UU4SPV","created_at":"2026-07-05T07:35:18Z"},{"alias_kind":"pith_short_16","alias_value":"IEHH33UU4SPVC757","created_at":"2026-07-05T07:35:18Z"},{"alias_kind":"pith_short_8","alias_value":"IEHH33UU","created_at":"2026-07-05T07:35:18Z"}],"graph_snapshots":[{"event_id":"sha256:1b7d4194a63a8f2b77762fed56246bc0fa55ddae64bdf4190ddf84a328f0ce95","target":"graph","created_at":"2026-07-05T07:35:18Z","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/2305.11834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the domain of audio processing, Transfer Learning has facilitated the rise of Self-Supervised Learning and Zero-Shot Learning techniques. These approaches have led to the development of versatile models capable of tackling a wide array of tasks, while delivering state-of-the-art performance. However, current models inherently lack the capacity to produce the requisite language for open-ended tasks, such as Audio Captioning or Audio Question & Answering. We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks. It t","authors_text":"Benjamin Elizalde, Huaming Wang, Rita Singh, Soham Deshmukh","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T17:20:56Z","title":"Pengi: An Audio Language Model for Audio Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11834","kind":"arxiv","version":2},"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":"sha256:522e94d86e09080db9e972497cf7d8b4b6850f0ae44bf7074ce2fc478dc18483","target":"record","created_at":"2026-07-05T07:35:18Z","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":"9f878704f65c864f30c3f74414d16baaa65166af894a6b1764e8541ae647fe03","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T17:20:56Z","title_canon_sha256":"57832b3160b858c06e8a69fc570f7484872d85fab493c29098c6563b3a046e76"},"schema_version":"1.0","source":{"id":"2305.11834","kind":"arxiv","version":2}},"canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","first_computed_at":"2026-07-05T07:35:18.992522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:18.992522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tA1MhFV/VWwPzldQK5cGfs80k8IJCKD7GI4m58hxOMyMHUPXk8LPInNszwlXv1okcRQKFkXd81lWCtzLuFg6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:18.992950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:522e94d86e09080db9e972497cf7d8b4b6850f0ae44bf7074ce2fc478dc18483","sha256:1b7d4194a63a8f2b77762fed56246bc0fa55ddae64bdf4190ddf84a328f0ce95"],"state_sha256":"925cf26dae6a04adb60ed3c0ca61bc16ae95ecfa5fd6bcfeae74c0e4fb5617a3"}