{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NVMYMIZKJH7DFGD53PE2K4BXXD","short_pith_number":"pith:NVMYMIZK","canonical_record":{"source":{"id":"2412.04917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-06T10:16:04Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"9cf42dbadc09a9b261cb84c06a80d745c8fa75a3fb02d5d8c8959707f53bae35","abstract_canon_sha256":"9d27b8710a12021bf3f16832cdd9ffdc2db3eb68222961071a5b5f95bd155501"},"schema_version":"1.0"},"canonical_sha256":"6d5986232a49fe32987ddbc9a57037b8c9b864ffcef43a17d0fe0561d2498261","source":{"kind":"arxiv","id":"2412.04917","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04917","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04917v1","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04917","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"NVMYMIZKJH7D","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"NVMYMIZKJH7DFGD5","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"NVMYMIZK","created_at":"2026-07-05T09:45:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NVMYMIZKJH7DFGD53PE2K4BXXD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-06T10:16:04Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"9cf42dbadc09a9b261cb84c06a80d745c8fa75a3fb02d5d8c8959707f53bae35","abstract_canon_sha256":"9d27b8710a12021bf3f16832cdd9ffdc2db3eb68222961071a5b5f95bd155501"},"schema_version":"1.0"},"canonical_sha256":"6d5986232a49fe32987ddbc9a57037b8c9b864ffcef43a17d0fe0561d2498261","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:26.034090Z","signature_b64":"DMjH22W4vzAeu0d6u1YmEjMHQDyg/4sb9cmI6kYZ0jc8lCMWC8EMMYZjl6UBMGw/IymDX7hj2q+I6DvglwFJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d5986232a49fe32987ddbc9a57037b8c9b864ffcef43a17d0fe0561d2498261","last_reissued_at":"2026-07-05T09:45:26.033666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:26.033666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04917","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i/4T+7DZox6LHHj4FN5Rw3rUM/1OEaaKBR8Yfh2TiFtM3g4PO7xuN2WL5vEYHNDOIqIuk3VKa2+lGjgkncZoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:20:51.419524Z"},"content_sha256":"5bea8c6b3cb4eb180ddb44fc6a9171ee2c5cd9ea07aa74a43b0e3aa456345872","schema_version":"1.0","event_id":"sha256:5bea8c6b3cb4eb180ddb44fc6a9171ee2c5cd9ea07aa74a43b0e3aa456345872"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NVMYMIZKJH7DFGD53PE2K4BXXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Sheng Zhao, Shujie Liu, Yanqing Liu, Ze Yuan","submitted_at":"2024-12-06T10:16:04Z","abstract_excerpt":"Recent advances in GPT-4o like multi-modality models have demonstrated remarkable progress for direct speech-to-speech conversation, with real-time speech interaction experience and strong speech understanding ability. However, current research focuses on discrete speech tokens to align with discrete text tokens for language modelling, which depends on an audio codec with residual connections or independent group tokens, such a codec usually leverages large scale and diverse datasets training to ensure that the discrete speech codes have good representation for varied domain, noise, style data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04917","kind":"arxiv","version":1},"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/2412.04917/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":"2026-07-05T09:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6TpFsi1jCOBeaQ5VsSZjbGWs8t8k1at53GrbFlZ1mJn9Ypd6fp43jFGaWVpbo6dqYpoeWlb3QFylv+kOtQGdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:20:51.420168Z"},"content_sha256":"203b4b06bd321bd470edc7c453f56ae0807415640f0303cad04bc5dfe7c38d12","schema_version":"1.0","event_id":"sha256:203b4b06bd321bd470edc7c453f56ae0807415640f0303cad04bc5dfe7c38d12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/bundle.json","state_url":"https://pith.science/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/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":"2026-08-03T18:20:51Z","links":{"resolver":"https://pith.science/pith/NVMYMIZKJH7DFGD53PE2K4BXXD","bundle":"https://pith.science/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/bundle.json","state":"https://pith.science/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVMYMIZKJH7DFGD53PE2K4BXXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NVMYMIZKJH7DFGD53PE2K4BXXD","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":"9d27b8710a12021bf3f16832cdd9ffdc2db3eb68222961071a5b5f95bd155501","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-06T10:16:04Z","title_canon_sha256":"9cf42dbadc09a9b261cb84c06a80d745c8fa75a3fb02d5d8c8959707f53bae35"},"schema_version":"1.0","source":{"id":"2412.04917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04917","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04917v1","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04917","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"NVMYMIZKJH7D","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"NVMYMIZKJH7DFGD5","created_at":"2026-07-05T09:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"NVMYMIZK","created_at":"2026-07-05T09:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:203b4b06bd321bd470edc7c453f56ae0807415640f0303cad04bc5dfe7c38d12","target":"graph","created_at":"2026-07-05T09:45:26Z","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/2412.04917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in GPT-4o like multi-modality models have demonstrated remarkable progress for direct speech-to-speech conversation, with real-time speech interaction experience and strong speech understanding ability. However, current research focuses on discrete speech tokens to align with discrete text tokens for language modelling, which depends on an audio codec with residual connections or independent group tokens, such a codec usually leverages large scale and diverse datasets training to ensure that the discrete speech codes have good representation for varied domain, noise, style data","authors_text":"Sheng Zhao, Shujie Liu, Yanqing Liu, Ze Yuan","cross_cats":["eess.AS","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-06T10:16:04Z","title":"Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04917","kind":"arxiv","version":1},"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":"sha256:5bea8c6b3cb4eb180ddb44fc6a9171ee2c5cd9ea07aa74a43b0e3aa456345872","target":"record","created_at":"2026-07-05T09:45:26Z","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":"9d27b8710a12021bf3f16832cdd9ffdc2db3eb68222961071a5b5f95bd155501","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-06T10:16:04Z","title_canon_sha256":"9cf42dbadc09a9b261cb84c06a80d745c8fa75a3fb02d5d8c8959707f53bae35"},"schema_version":"1.0","source":{"id":"2412.04917","kind":"arxiv","version":1}},"canonical_sha256":"6d5986232a49fe32987ddbc9a57037b8c9b864ffcef43a17d0fe0561d2498261","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d5986232a49fe32987ddbc9a57037b8c9b864ffcef43a17d0fe0561d2498261","first_computed_at":"2026-07-05T09:45:26.033666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:26.033666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DMjH22W4vzAeu0d6u1YmEjMHQDyg/4sb9cmI6kYZ0jc8lCMWC8EMMYZjl6UBMGw/IymDX7hj2q+I6DvglwFJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:26.034090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bea8c6b3cb4eb180ddb44fc6a9171ee2c5cd9ea07aa74a43b0e3aa456345872","sha256:203b4b06bd321bd470edc7c453f56ae0807415640f0303cad04bc5dfe7c38d12"],"state_sha256":"22a87dce7838e741aab6aaf8c663ef6a9c70004886d24641e9f5a358fc275237"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fFthpWAxbA6Ge4GEphF2Qir+m2O91THGOZuK0SaMNPxZEeE+jJiBJ/+z6XlO7jke4M8sWGRL9iNxiBm4nn6tAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:20:51.425721Z","bundle_sha256":"37c2c79a070db15a1f38354e03c4c13e499b60e4d163165b33907d8343c4258e"}}