{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IEHH33UU4SPVC757CTA665O4DB","short_pith_number":"pith:IEHH33UU","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"},"canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","source":{"kind":"arxiv","id":"2305.11834","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IEHH33UU4SPVC757CTA665O4DB","target":"record","payload":{"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"},"canonical_sha256":"410e7dee94e49f517fbf14c1ef75dc184c962ad51456da8f1ca262aeefddab8b","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"},"source_kind":"arxiv","source_id":"2305.11834","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdX2g8t3l/u1EHK+rp4VUb1+uyrQ8xpApOG2Oe+gffur+gg9i88U315b+r2TVqk22xTBTq2ZuA6kJkgHP0t6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:01:13.169393Z"},"content_sha256":"522e94d86e09080db9e972497cf7d8b4b6850f0ae44bf7074ce2fc478dc18483","schema_version":"1.0","event_id":"sha256:522e94d86e09080db9e972497cf7d8b4b6850f0ae44bf7074ce2fc478dc18483"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IEHH33UU4SPVC757CTA665O4DB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:35:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wOVKppR4Kolu6WES77Bl5ZcjW+MJXblZU9YHIN3xx/vPRRqrtHidqXeB80B0NZ/2MW4JY7ZCURyUFMyo0uYOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:01:13.169901Z"},"content_sha256":"1b7d4194a63a8f2b77762fed56246bc0fa55ddae64bdf4190ddf84a328f0ce95","schema_version":"1.0","event_id":"sha256:1b7d4194a63a8f2b77762fed56246bc0fa55ddae64bdf4190ddf84a328f0ce95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/bundle.json","state_url":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEHH33UU4SPVC757CTA665O4DB/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":"2026-07-07T13:01:13Z","links":{"resolver":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB","bundle":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/bundle.json","state":"https://pith.science/pith/IEHH33UU4SPVC757CTA665O4DB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEHH33UU4SPVC757CTA665O4DB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbOFTvL6wjXjwRaM/8jMe1sMDymZ3+yNJBlhp9J60hzjewrYhX2T49LGPVWTUjZ7auoDs96rIAQ1+qH0BspPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:01:13.172956Z","bundle_sha256":"87d0ccbaa04fee20afc13fbdf1c0c628ed392a6acb39db66703617d5754b8266"}}