{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SJFBAEMTIL3AYJAJJNTKM6XW5V","short_pith_number":"pith:SJFBAEMT","canonical_record":{"source":{"id":"2405.08295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T03:33:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c7a6bdfaff489bfe75d81cef90d5d76f70eca5d7cf7bf4ccfdc5199c93c28883","abstract_canon_sha256":"8a58263f408964ff1d3a4e36265b72d9b6c0af03a966b0f8cf26537514839bdf"},"schema_version":"1.0"},"canonical_sha256":"924a10119342f60c24094b66a67af6ed7eab14756de090958d8c9fd332da7ebf","source":{"kind":"arxiv","id":"2405.08295","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08295","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08295v3","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08295","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"SJFBAEMTIL3A","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"SJFBAEMTIL3AYJAJ","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"SJFBAEMT","created_at":"2026-07-05T10:38:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SJFBAEMTIL3AYJAJJNTKM6XW5V","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T03:33:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c7a6bdfaff489bfe75d81cef90d5d76f70eca5d7cf7bf4ccfdc5199c93c28883","abstract_canon_sha256":"8a58263f408964ff1d3a4e36265b72d9b6c0af03a966b0f8cf26537514839bdf"},"schema_version":"1.0"},"canonical_sha256":"924a10119342f60c24094b66a67af6ed7eab14756de090958d8c9fd332da7ebf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:33.225521Z","signature_b64":"rv7c2wppW/8ua3MO84l7lPsVDm4mzXX9V8gvQhNPxhZcnSdnHuSLhuptuqh9ZG6u+cB7tCjwSzkFCrP5LgkZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"924a10119342f60c24094b66a67af6ed7eab14756de090958d8c9fd332da7ebf","last_reissued_at":"2026-07-05T10:38:33.225056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:33.225056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08295","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYA20s0gMbrrZ7jsXa4MaRUMK7x2OL/3e21eNPAsIOzsvKlw+5Fh7nqgb4zJWabSB87O2Oq7gv+5qzWI1pJRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:18:37.882169Z"},"content_sha256":"d8669c52f9dc2132c15ac717c8345e60384420cb960de35729687e95bc85c796","schema_version":"1.0","event_id":"sha256:d8669c52f9dc2132c15ac717c8345e60384420cb960de35729687e95bc85c796"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SJFBAEMTIL3AYJAJJNTKM6XW5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dhanush Bekal, Jie Yuan, Karel Mundnich, Katrin Kirchhoff, Kyu J Han, Monica Sunkara, Nilaksh Das, Prashant Mathur, Rohit Paturi, Sai Muralidhar Jayanthi, Saket Dingliwal, Sravan Bodapati, Srikanth Ronanki, Sundararajan Srinivasan, Xilai Li, Xing Niu, Zhaocheng Huang","submitted_at":"2024-05-14T03:33:31Z","abstract_excerpt":"Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio and text inputs, but their capabilities are often limited to specific fine-tuned tasks such as automatic speech recognition and translation. We therefore develop SpeechVerse, a robust multi-task training and curriculum learning framework that combines pre-trained speech and text foundation models via a small set of learnable parameters, while keeping the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08295","kind":"arxiv","version":3},"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/2405.08295/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":"2026-07-05T10:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KiQPo7ZAJC30GIRUxHiwb727nTk/4ODhAJ8uQRvOCBL6aT2Xnhk2D5TDX8ltKZAJZF7rUATKUQT3yKN+Zqj4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:18:37.882888Z"},"content_sha256":"ba8482fc819ce57962ea2c3a6471bed5dd5e50f0af121af8f8ad3ca08e516b77","schema_version":"1.0","event_id":"sha256:ba8482fc819ce57962ea2c3a6471bed5dd5e50f0af121af8f8ad3ca08e516b77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/bundle.json","state_url":"https://pith.science/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/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":"2026-08-06T14:18:37Z","links":{"resolver":"https://pith.science/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V","bundle":"https://pith.science/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/bundle.json","state":"https://pith.science/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJFBAEMTIL3AYJAJJNTKM6XW5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJFBAEMTIL3AYJAJJNTKM6XW5V","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":"8a58263f408964ff1d3a4e36265b72d9b6c0af03a966b0f8cf26537514839bdf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T03:33:31Z","title_canon_sha256":"c7a6bdfaff489bfe75d81cef90d5d76f70eca5d7cf7bf4ccfdc5199c93c28883"},"schema_version":"1.0","source":{"id":"2405.08295","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08295","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08295v3","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08295","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"SJFBAEMTIL3A","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"SJFBAEMTIL3AYJAJ","created_at":"2026-07-05T10:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"SJFBAEMT","created_at":"2026-07-05T10:38:33Z"}],"graph_snapshots":[{"event_id":"sha256:ba8482fc819ce57962ea2c3a6471bed5dd5e50f0af121af8f8ad3ca08e516b77","target":"graph","created_at":"2026-07-05T10:38:33Z","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/2405.08295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown incredible proficiency in performing tasks that require semantic understanding of natural language instructions. Recently, many works have further expanded this capability to perceive multimodal audio and text inputs, but their capabilities are often limited to specific fine-tuned tasks such as automatic speech recognition and translation. We therefore develop SpeechVerse, a robust multi-task training and curriculum learning framework that combines pre-trained speech and text foundation models via a small set of learnable parameters, while keeping the pr","authors_text":"Dhanush Bekal, Jie Yuan, Karel Mundnich, Katrin Kirchhoff, Kyu J Han, Monica Sunkara, Nilaksh Das, Prashant Mathur, Rohit Paturi, Sai Muralidhar Jayanthi, Saket Dingliwal, Sravan Bodapati, Srikanth Ronanki, Sundararajan Srinivasan, Xilai Li, Xing Niu, Zhaocheng Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T03:33:31Z","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08295","kind":"arxiv","version":3},"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:d8669c52f9dc2132c15ac717c8345e60384420cb960de35729687e95bc85c796","target":"record","created_at":"2026-07-05T10:38:33Z","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":"8a58263f408964ff1d3a4e36265b72d9b6c0af03a966b0f8cf26537514839bdf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T03:33:31Z","title_canon_sha256":"c7a6bdfaff489bfe75d81cef90d5d76f70eca5d7cf7bf4ccfdc5199c93c28883"},"schema_version":"1.0","source":{"id":"2405.08295","kind":"arxiv","version":3}},"canonical_sha256":"924a10119342f60c24094b66a67af6ed7eab14756de090958d8c9fd332da7ebf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"924a10119342f60c24094b66a67af6ed7eab14756de090958d8c9fd332da7ebf","first_computed_at":"2026-07-05T10:38:33.225056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:33.225056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rv7c2wppW/8ua3MO84l7lPsVDm4mzXX9V8gvQhNPxhZcnSdnHuSLhuptuqh9ZG6u+cB7tCjwSzkFCrP5LgkZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:33.225521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08295","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8669c52f9dc2132c15ac717c8345e60384420cb960de35729687e95bc85c796","sha256:ba8482fc819ce57962ea2c3a6471bed5dd5e50f0af121af8f8ad3ca08e516b77"],"state_sha256":"9706f3e5aa58b5801080049f749d8a2fa339f00724b6c43c13f8670c71cfb491"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlAdbQY4tt1BHa0FQImX1K0NZaJFMeXSMUrrjd8VhhrIFY4kphq58OCif0PBKy1oPvWgaH7Tf6T4SJsbketyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:18:37.890158Z","bundle_sha256":"1ef4e5ca66ab7ac53b23f9c74b41bcba7a3c97fe494b7456d76a5ba668f02455"}}