{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3BIFBR7IWQFI6IPC4XZUQRBP7Y","short_pith_number":"pith:3BIFBR7I","canonical_record":{"source":{"id":"2501.00805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T11:11:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"cd64dd95e42ad12be12b70809ad52f097b32ad21d2bd4f648b2defa7bed9364f","abstract_canon_sha256":"086185e0ae84701857517fb8f86c305803938c757c54e951c9f738e4ca770e73"},"schema_version":"1.0"},"canonical_sha256":"d85050c7e8b40a8f21e2e5f348442ffe3099a5d57936aa47a68570fdd3601b18","source":{"kind":"arxiv","id":"2501.00805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00805","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00805v1","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00805","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"3BIFBR7IWQFI","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_16","alias_value":"3BIFBR7IWQFI6IPC","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_8","alias_value":"3BIFBR7I","created_at":"2026-07-05T09:56:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3BIFBR7IWQFI6IPC4XZUQRBP7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T11:11:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"cd64dd95e42ad12be12b70809ad52f097b32ad21d2bd4f648b2defa7bed9364f","abstract_canon_sha256":"086185e0ae84701857517fb8f86c305803938c757c54e951c9f738e4ca770e73"},"schema_version":"1.0"},"canonical_sha256":"d85050c7e8b40a8f21e2e5f348442ffe3099a5d57936aa47a68570fdd3601b18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:10.558032Z","signature_b64":"8adIevIvlapxovQv30JTCOilDRHZ/oPlFxf8zoVrtdn9rAxsWUvUiWhKkKXS2cm5YVLmCzyuB7em7IcKYHIGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d85050c7e8b40a8f21e2e5f348442ffe3099a5d57936aa47a68570fdd3601b18","last_reissued_at":"2026-07-05T09:56:10.557575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:10.557575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00805","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":"2026-07-05T09:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVG2iJTFTyk5rzdC2MDUEYCtEczV+HHrsRaNh9KHJbKUgrSfCe8PR6S90CeE89xu7C5ASApVYoE2IWJrM1XDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:21:29.996029Z"},"content_sha256":"98f986e87cdc2ffe7a41d1184005b649dd88a33dafb9c0b3d1c4975aa7a2dabf","schema_version":"1.0","event_id":"sha256:98f986e87cdc2ffe7a41d1184005b649dd88a33dafb9c0b3d1c4975aa7a2dabf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3BIFBR7IWQFI6IPC4XZUQRBP7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gaofeng Cheng, Haitian Lu, Leying Zhang, Liuping Luo, Pengyuan Zhang, Yanmin Qian","submitted_at":"2025-01-01T11:11:07Z","abstract_excerpt":"Recently, ``textless\" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In this paper, we propose SLM and LLM Integration for spontaneous spoken Dialogue gEneration (SLIDE). Specifically, we first utilize an LLM to generate the textual content of spoken dialogue. Next, we convert the textual dialogues into phoneme sequences and use a two-tower transformer-based duration predictor to predict the duration of each phoneme. Finally, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00805","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/2501.00805/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":"2026-07-05T09:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZFhinRGz0sqZA96yCy4XQN9DClJOKA5HooG9au/B/Z8cXLStsPW7cbbb+7pRBEZcAFCKVjq6TF2PTY/z9/XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:21:29.996519Z"},"content_sha256":"ed3c8ab28107c14fd1afa874a4a69da9dc2a3a1bb1ad4774d76bd9c82b7e100b","schema_version":"1.0","event_id":"sha256:ed3c8ab28107c14fd1afa874a4a69da9dc2a3a1bb1ad4774d76bd9c82b7e100b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/bundle.json","state_url":"https://pith.science/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/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":"2026-08-04T04:21:29Z","links":{"resolver":"https://pith.science/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y","bundle":"https://pith.science/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/bundle.json","state":"https://pith.science/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BIFBR7IWQFI6IPC4XZUQRBP7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3BIFBR7IWQFI6IPC4XZUQRBP7Y","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":"086185e0ae84701857517fb8f86c305803938c757c54e951c9f738e4ca770e73","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T11:11:07Z","title_canon_sha256":"cd64dd95e42ad12be12b70809ad52f097b32ad21d2bd4f648b2defa7bed9364f"},"schema_version":"1.0","source":{"id":"2501.00805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00805","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00805v1","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00805","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"3BIFBR7IWQFI","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_16","alias_value":"3BIFBR7IWQFI6IPC","created_at":"2026-07-05T09:56:10Z"},{"alias_kind":"pith_short_8","alias_value":"3BIFBR7I","created_at":"2026-07-05T09:56:10Z"}],"graph_snapshots":[{"event_id":"sha256:ed3c8ab28107c14fd1afa874a4a69da9dc2a3a1bb1ad4774d76bd9c82b7e100b","target":"graph","created_at":"2026-07-05T09:56:10Z","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/2501.00805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, ``textless\" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In this paper, we propose SLM and LLM Integration for spontaneous spoken Dialogue gEneration (SLIDE). Specifically, we first utilize an LLM to generate the textual content of spoken dialogue. Next, we convert the textual dialogues into phoneme sequences and use a two-tower transformer-based duration predictor to predict the duration of each phoneme. Finally, a","authors_text":"Gaofeng Cheng, Haitian Lu, Leying Zhang, Liuping Luo, Pengyuan Zhang, Yanmin Qian","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T11:11:07Z","title":"SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00805","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":"sha256:98f986e87cdc2ffe7a41d1184005b649dd88a33dafb9c0b3d1c4975aa7a2dabf","target":"record","created_at":"2026-07-05T09:56:10Z","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":"086185e0ae84701857517fb8f86c305803938c757c54e951c9f738e4ca770e73","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-01T11:11:07Z","title_canon_sha256":"cd64dd95e42ad12be12b70809ad52f097b32ad21d2bd4f648b2defa7bed9364f"},"schema_version":"1.0","source":{"id":"2501.00805","kind":"arxiv","version":1}},"canonical_sha256":"d85050c7e8b40a8f21e2e5f348442ffe3099a5d57936aa47a68570fdd3601b18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d85050c7e8b40a8f21e2e5f348442ffe3099a5d57936aa47a68570fdd3601b18","first_computed_at":"2026-07-05T09:56:10.557575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:10.557575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8adIevIvlapxovQv30JTCOilDRHZ/oPlFxf8zoVrtdn9rAxsWUvUiWhKkKXS2cm5YVLmCzyuB7em7IcKYHIGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:10.558032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98f986e87cdc2ffe7a41d1184005b649dd88a33dafb9c0b3d1c4975aa7a2dabf","sha256:ed3c8ab28107c14fd1afa874a4a69da9dc2a3a1bb1ad4774d76bd9c82b7e100b"],"state_sha256":"cebed38543980517393d000c9186857076d2e8af0d798b9a97f3c00df4e392ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sNWYUXbSnRhZpcxfwIbeVZbiS57MmXD0oJc9P7cf4115IS5DZWWPDH/PtCpP8P7XRjGmmPAcyeXQ+k6frsSuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:21:30.001754Z","bundle_sha256":"fb70f2e9731dc4a7db517ed3607867f423de35c2ed5defe40fe1f514c29ab13a"}}