{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IEHH33UU4SPVC757CTA665O4DB","short_pith_number":"pith:IEHH33UU","schema_version":"1.0","canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","source":{"kind":"arxiv","id":"2305.11834","version":2},"attestation_state":"computed","paper":{"title":"Pengi: An Audio Language Model for Audio Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Elizalde, Huaming Wang, Rita Singh, Soham Deshmukh","submitted_at":"2023-05-19T17:20:56Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.11834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T17:20:56Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"57832b3160b858c06e8a69fc570f7484872d85fab493c29098c6563b3a046e76","abstract_canon_sha256":"9f878704f65c864f30c3f74414d16baaa65166af894a6b1764e8541ae647fe03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:18.992950Z","signature_b64":"tA1MhFV/VWwPzldQK5cGfs80k8IJCKD7GI4m58hxOMyMHUPXk8LPInNszwlXv1okcRQKFkXd81lWCtzLuFg6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","last_reissued_at":"2026-07-05T07:35:18.992522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:18.992522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pengi: An Audio Language Model for Audio Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin Elizalde, Huaming Wang, Rita Singh, Soham Deshmukh","submitted_at":"2023-05-19T17:20:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11834","kind":"arxiv","version":2},"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/2305.11834/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.11834","created_at":"2026-07-05T07:35:18.992578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11834v2","created_at":"2026-07-05T07:35:18.992578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11834","created_at":"2026-07-05T07:35:18.992578+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEHH33UU4SPV","created_at":"2026-07-05T07:35:18.992578+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEHH33UU4SPVC757","created_at":"2026-07-05T07:35:18.992578+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEHH33UU","created_at":"2026-07-05T07:35:18.992578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00247","citing_title":"Adaptive Perturbation Selection for Contrastive Audio Decoding","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB","json":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB.json","graph_json":"https://pith.science/api/pith-number/IEHH33UU4SPVC757CTA665O4DB/graph.json","events_json":"https://pith.science/api/pith-number/IEHH33UU4SPVC757CTA665O4DB/events.json","paper":"https://pith.science/paper/IEHH33UU"},"agent_actions":{"view_html":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB","download_json":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB.json","view_paper":"https://pith.science/paper/IEHH33UU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11834&json=true","fetch_graph":"https://pith.science/api/pith-number/IEHH33UU4SPVC757CTA665O4DB/graph.json","fetch_events":"https://pith.science/api/pith-number/IEHH33UU4SPVC757CTA665O4DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/action/storage_attestation","attest_author":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/action/author_attestation","sign_citation":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/action/citation_signature","submit_replication":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/action/replication_record"}},"created_at":"2026-07-05T07:35:18.992578+00:00","updated_at":"2026-07-05T07:35:18.992578+00:00"}