{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ASCXW2C75OXPS2LPXEBIROHJG3","short_pith_number":"pith:ASCXW2C7","canonical_record":{"source":{"id":"2409.17010","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T15:15:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7fbef9b40d0c34dc47e5a6cc391263006c462df1a24027bebb8247a58428105f","abstract_canon_sha256":"f73b26ca5a30f83a6218c7abad860f5b7bfa8af1d97b17bcd2769fb5e52f8a2d"},"schema_version":"1.0"},"canonical_sha256":"04857b685febaef9696fb90288b8e936ddc7530a04b45048d511aaecfa890bce","source":{"kind":"arxiv","id":"2409.17010","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17010","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17010v4","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17010","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"ASCXW2C75OXP","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"ASCXW2C75OXPS2LP","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"ASCXW2C7","created_at":"2026-07-05T10:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ASCXW2C75OXPS2LPXEBIROHJG3","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17010","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T15:15:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7fbef9b40d0c34dc47e5a6cc391263006c462df1a24027bebb8247a58428105f","abstract_canon_sha256":"f73b26ca5a30f83a6218c7abad860f5b7bfa8af1d97b17bcd2769fb5e52f8a2d"},"schema_version":"1.0"},"canonical_sha256":"04857b685febaef9696fb90288b8e936ddc7530a04b45048d511aaecfa890bce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:11.597906Z","signature_b64":"REWtUBozNpFvqykIsgpl7455km/dKH3tvTdFc8Akwk99jEq671BZ6dw1tX58KyQAaImdzgF0Ljh+Bxm94Km6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04857b685febaef9696fb90288b8e936ddc7530a04b45048d511aaecfa890bce","last_reissued_at":"2026-07-05T10:17:11.597447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:11.597447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17010","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCpFKpBbx8n+vjvd20kqm+In9F8iAyx2u6TNi92Ir6qLjlD1CYmXFoYN1RCjhcSJbPLbHs2PO/1EFSjSDqMBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:07:09.104709Z"},"content_sha256":"d1fbd2eb04cb4cc3c8a7a0bf9195f954c224ea096e6e1ad39d7cc289243a347d","schema_version":"1.0","event_id":"sha256:d1fbd2eb04cb4cc3c8a7a0bf9195f954c224ea096e6e1ad39d7cc289243a347d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ASCXW2C75OXPS2LPXEBIROHJG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chao Zhang, Phil Woodland, Qiujia Li, Xiaoyu Yang","submitted_at":"2024-09-25T15:15:42Z","abstract_excerpt":"With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high performance on multiple tasks, since different speech and audio processing tasks usually require different training data, input features, or model architectures to achieve optimal performance. In this work, MT2KD, a novel two-stage multi-task learning framework is proposed to build a general-purpose speech and audio encoder that jointly performs three fundamental task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17010","kind":"arxiv","version":4},"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/2409.17010/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":"2026-07-05T10:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RrfrKTZTXYfdJ/BN8nx000uCFySU4ae8FviF7Vl3P4oKBk/5Qefwt8gy0WSVCqO4F54AQ9XhiCUTOxB6Lz7ZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T03:07:09.105373Z"},"content_sha256":"79833f274d68a5257600515215192c9e6e33351b6af4cd86396da8fd544f77c5","schema_version":"1.0","event_id":"sha256:79833f274d68a5257600515215192c9e6e33351b6af4cd86396da8fd544f77c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASCXW2C75OXPS2LPXEBIROHJG3/bundle.json","state_url":"https://pith.science/pith/ASCXW2C75OXPS2LPXEBIROHJG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASCXW2C75OXPS2LPXEBIROHJG3/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":"2026-08-21T03:07:09Z","links":{"resolver":"https://pith.science/pith/ASCXW2C75OXPS2LPXEBIROHJG3","bundle":"https://pith.science/pith/ASCXW2C75OXPS2LPXEBIROHJG3/bundle.json","state":"https://pith.science/pith/ASCXW2C75OXPS2LPXEBIROHJG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASCXW2C75OXPS2LPXEBIROHJG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ASCXW2C75OXPS2LPXEBIROHJG3","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":"f73b26ca5a30f83a6218c7abad860f5b7bfa8af1d97b17bcd2769fb5e52f8a2d","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T15:15:42Z","title_canon_sha256":"7fbef9b40d0c34dc47e5a6cc391263006c462df1a24027bebb8247a58428105f"},"schema_version":"1.0","source":{"id":"2409.17010","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17010","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17010v4","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17010","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"ASCXW2C75OXP","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"ASCXW2C75OXPS2LP","created_at":"2026-07-05T10:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"ASCXW2C7","created_at":"2026-07-05T10:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:79833f274d68a5257600515215192c9e6e33351b6af4cd86396da8fd544f77c5","target":"graph","created_at":"2026-07-05T10:17:11Z","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/2409.17010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high performance on multiple tasks, since different speech and audio processing tasks usually require different training data, input features, or model architectures to achieve optimal performance. In this work, MT2KD, a novel two-stage multi-task learning framework is proposed to build a general-purpose speech and audio encoder that jointly performs three fundamental task","authors_text":"Chao Zhang, Phil Woodland, Qiujia Li, Xiaoyu Yang","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T15:15:42Z","title":"MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17010","kind":"arxiv","version":4},"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:d1fbd2eb04cb4cc3c8a7a0bf9195f954c224ea096e6e1ad39d7cc289243a347d","target":"record","created_at":"2026-07-05T10:17:11Z","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":"f73b26ca5a30f83a6218c7abad860f5b7bfa8af1d97b17bcd2769fb5e52f8a2d","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T15:15:42Z","title_canon_sha256":"7fbef9b40d0c34dc47e5a6cc391263006c462df1a24027bebb8247a58428105f"},"schema_version":"1.0","source":{"id":"2409.17010","kind":"arxiv","version":4}},"canonical_sha256":"04857b685febaef9696fb90288b8e936ddc7530a04b45048d511aaecfa890bce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04857b685febaef9696fb90288b8e936ddc7530a04b45048d511aaecfa890bce","first_computed_at":"2026-07-05T10:17:11.597447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:11.597447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"REWtUBozNpFvqykIsgpl7455km/dKH3tvTdFc8Akwk99jEq671BZ6dw1tX58KyQAaImdzgF0Ljh+Bxm94Km6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:11.597906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17010","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1fbd2eb04cb4cc3c8a7a0bf9195f954c224ea096e6e1ad39d7cc289243a347d","sha256:79833f274d68a5257600515215192c9e6e33351b6af4cd86396da8fd544f77c5"],"state_sha256":"2bbad8ceee47ee0714f3ae22ca837a26e6377fe8523c2fc0f8f45c804804b166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBb8PWgidT7O1uzwJbjhWOcELrSvPQhViKeod28D8zMb9Ao47hI2rFS5fVz4C+K1PG/QGG7D8E1xB9MYabeBCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T03:07:09.109286Z","bundle_sha256":"c193cbbeed8765c6725b58bb4b7ac1e464ca6c1f71d44aa13261bc3d65651fa7"}}