{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XD7UAYH7DFAW3HVNAECDVBXP3K","short_pith_number":"pith:XD7UAYH7","canonical_record":{"source":{"id":"2410.03751","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T21:48:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"635db2684ef37c9a5d0bff65bf49a80b140b6fa5c73ad4bca220a95c74fa74d3","abstract_canon_sha256":"ebe475e50865e45a7f19f4be1a014a1b93090876272170fc558a452e01a2b5c3"},"schema_version":"1.0"},"canonical_sha256":"b8ff4060ff19416d9ead01043a86efdab4774bc3ba8dd49ce690e3397e4d6a34","source":{"kind":"arxiv","id":"2410.03751","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03751","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03751v4","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03751","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"XD7UAYH7DFAW","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"XD7UAYH7DFAW3HVN","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"XD7UAYH7","created_at":"2026-07-05T11:49:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XD7UAYH7DFAW3HVNAECDVBXP3K","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03751","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T21:48:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"635db2684ef37c9a5d0bff65bf49a80b140b6fa5c73ad4bca220a95c74fa74d3","abstract_canon_sha256":"ebe475e50865e45a7f19f4be1a014a1b93090876272170fc558a452e01a2b5c3"},"schema_version":"1.0"},"canonical_sha256":"b8ff4060ff19416d9ead01043a86efdab4774bc3ba8dd49ce690e3397e4d6a34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:47.086223Z","signature_b64":"FqwhKHRfvyMUB3GnwMW3bcAPQiHVwiUJNsvu9EPxN5Gf4hOQTMPdQpUn+pY81L6gdxfDXjgi5dCpMwYLAF+XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ff4060ff19416d9ead01043a86efdab4774bc3ba8dd49ce690e3397e4d6a34","last_reissued_at":"2026-07-05T11:49:47.085718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:47.085718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03751","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":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rkK4NCLgJL7MZrX8IdvwrLuxN9ZH8yX4ZYQUQZ7257Zl9o3lB7QWl3ebkN+zTROlMhxmDJU3B7mdgB7hb21hAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:08:52.732677Z"},"content_sha256":"e5faa67a3c9b80fa6afadbb5bf1531ceecbcc1e75d0996a5fc6b57ee6b7701ed","schema_version":"1.0","event_id":"sha256:e5faa67a3c9b80fa6afadbb5bf1531ceecbcc1e75d0996a5fc6b57ee6b7701ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XD7UAYH7DFAW3HVNAECDVBXP3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recent Advances in Speech Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dianzhi Yu, Guangyan Zhang, Irwin King, Qichao Wang, Wenqian Cui, Xiaoqi Jiao, Yiwen Guo, Ziqiao Meng","submitted_at":"2024-10-01T21:48:12Z","abstract_excerpt":"Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightforward approach to achieve this involves a pipeline of ``Automatic Speech Recognition (ASR) + LLM + Text-to-Speech (TTS)\", where input speech is transcribed to text, processed by an LLM, and then converted back to speech. Despite being straightforward, this method suffers from inherent limitations, such as information loss during modality con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03751","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/2410.03751/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":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qyf7MSx4zXP7S1u6EP/ZSMqvFVk2CgPPe4n5mvga+b3k6AnA1SGfhnpnmly5U7Bpzlq9T1QORX84r50/WPMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:08:52.733738Z"},"content_sha256":"254828d17794ad1f0778ba9b1a873b8b1a07cfeabee3fc4c18d9495412ec1f1a","schema_version":"1.0","event_id":"sha256:254828d17794ad1f0778ba9b1a873b8b1a07cfeabee3fc4c18d9495412ec1f1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/bundle.json","state_url":"https://pith.science/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/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":"2026-08-04T15:08:52Z","links":{"resolver":"https://pith.science/pith/XD7UAYH7DFAW3HVNAECDVBXP3K","bundle":"https://pith.science/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/bundle.json","state":"https://pith.science/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XD7UAYH7DFAW3HVNAECDVBXP3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XD7UAYH7DFAW3HVNAECDVBXP3K","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":"ebe475e50865e45a7f19f4be1a014a1b93090876272170fc558a452e01a2b5c3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T21:48:12Z","title_canon_sha256":"635db2684ef37c9a5d0bff65bf49a80b140b6fa5c73ad4bca220a95c74fa74d3"},"schema_version":"1.0","source":{"id":"2410.03751","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03751","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03751v4","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03751","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"XD7UAYH7DFAW","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"XD7UAYH7DFAW3HVN","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"XD7UAYH7","created_at":"2026-07-05T11:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:254828d17794ad1f0778ba9b1a873b8b1a07cfeabee3fc4c18d9495412ec1f1a","target":"graph","created_at":"2026-07-05T11:49:47Z","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/2410.03751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightforward approach to achieve this involves a pipeline of ``Automatic Speech Recognition (ASR) + LLM + Text-to-Speech (TTS)\", where input speech is transcribed to text, processed by an LLM, and then converted back to speech. Despite being straightforward, this method suffers from inherent limitations, such as information loss during modality con","authors_text":"Dianzhi Yu, Guangyan Zhang, Irwin King, Qichao Wang, Wenqian Cui, Xiaoqi Jiao, Yiwen Guo, Ziqiao Meng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T21:48:12Z","title":"Recent Advances in Speech Language Models: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03751","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:e5faa67a3c9b80fa6afadbb5bf1531ceecbcc1e75d0996a5fc6b57ee6b7701ed","target":"record","created_at":"2026-07-05T11:49:47Z","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":"ebe475e50865e45a7f19f4be1a014a1b93090876272170fc558a452e01a2b5c3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T21:48:12Z","title_canon_sha256":"635db2684ef37c9a5d0bff65bf49a80b140b6fa5c73ad4bca220a95c74fa74d3"},"schema_version":"1.0","source":{"id":"2410.03751","kind":"arxiv","version":4}},"canonical_sha256":"b8ff4060ff19416d9ead01043a86efdab4774bc3ba8dd49ce690e3397e4d6a34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8ff4060ff19416d9ead01043a86efdab4774bc3ba8dd49ce690e3397e4d6a34","first_computed_at":"2026-07-05T11:49:47.085718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:47.085718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqwhKHRfvyMUB3GnwMW3bcAPQiHVwiUJNsvu9EPxN5Gf4hOQTMPdQpUn+pY81L6gdxfDXjgi5dCpMwYLAF+XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:47.086223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03751","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5faa67a3c9b80fa6afadbb5bf1531ceecbcc1e75d0996a5fc6b57ee6b7701ed","sha256:254828d17794ad1f0778ba9b1a873b8b1a07cfeabee3fc4c18d9495412ec1f1a"],"state_sha256":"2923ce4fbb47a6b6e8924e7a97efcdcf1cdf1ad093a4007beefe1cdfd4e67afb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUCok+p7GtGWLRZj2DvnFKD+6rm6BaJJPi/TNp4WDg8Itu/idTje2TL+mGzM1IrBgj4xG+6aJTiwNGpqhbHHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:08:52.752271Z","bundle_sha256":"e329c50abdc655eac8bc42593483539b4e2fd33f233f2d3adf37461a3a2118df"}}