{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JX4FXY5DCBTRLEN4EZJBMH3SJI","short_pith_number":"pith:JX4FXY5D","canonical_record":{"source":{"id":"2606.20650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3d0918d3431ed95fe31d5005a6703ebc6edf4e281d88f43ce6b672c5eab19908","abstract_canon_sha256":"fc5f8481c1e9265738f8f69c58cca9c1ddbef8916ffcee6e48c691fe801c06cc"},"schema_version":"1.0"},"canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","source":{"kind":"arxiv","id":"2606.20650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20650","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20650v1","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20650","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"JX4FXY5DCBTR","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"JX4FXY5DCBTRLEN4","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"JX4FXY5D","created_at":"2026-06-23T00:11:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JX4FXY5DCBTRLEN4EZJBMH3SJI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"3d0918d3431ed95fe31d5005a6703ebc6edf4e281d88f43ce6b672c5eab19908","abstract_canon_sha256":"fc5f8481c1e9265738f8f69c58cca9c1ddbef8916ffcee6e48c691fe801c06cc"},"schema_version":"1.0"},"canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:52.579369Z","signature_b64":"uXvOp5NISiQKOFsepPZFT3X981lIz4GqXf50kJV/XISIKEsicc3Gi+4GPX9O6TLq0+Ss8XFtkC2mxdrHSrC3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","last_reissued_at":"2026-06-23T00:11:52.578987Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:52.578987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20650","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":"2026-06-23T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TSmDsmKAXtwCjP+IzTDEKWVOpP+2E316hEiqv5v3OcRMVTD3nULBDTdH/ZvnnzOj1k7Bl3s2/CDwfrtV3jpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T07:22:06.660995Z"},"content_sha256":"14cb6a4583167166317dec44d4b0c5642d6f5bca784e6052228e3b9c069bfc50","schema_version":"1.0","event_id":"sha256:14cb6a4583167166317dec44d4b0c5642d6f5bca784e6052228e3b9c069bfc50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JX4FXY5DCBTRLEN4EZJBMH3SJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bingao Xu, Ganjun Liu, Hongchuan Wu, Jiasheng Chen, Jun Du, Minghui Wu, Ting Meng, Yonglong Cai, Zikun Fang","submitted_at":"2026-06-08T06:54:55Z","abstract_excerpt":"Instruction-based controllable speech synthesis enables users to specify emotions through natural language. However, existing approaches often rely on coarse emotion labels and lack explicit modeling of fine-grained intensity. We propose EmoInstruct-TTS, a dual-path instruction-guided framework for emotional speech synthesis. We introduce Emotion2embed, a supervised semantic-acoustic emotion embedding covering 48 emotional states, including fine-grained categories and intensity levels. To infer embeddings from free-form instructions, we design an Instruction-Conditioned Emotion Flow Model (ICE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20650","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/2606.20650/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":"2026-06-23T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOfgPpOFmOkpouK1S1VCpH8aI48+PwLjlUvYXMyexeYUFq9du0LKQRDa+nHKbpaqfugxCp0+AaxcoULRuPaDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T07:22:06.661394Z"},"content_sha256":"f802e2562d81e4f9966c1b089332f2340361027a4709f42feb9e6b55362e6ed9","schema_version":"1.0","event_id":"sha256:f802e2562d81e4f9966c1b089332f2340361027a4709f42feb9e6b55362e6ed9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/bundle.json","state_url":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/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":"2026-06-24T07:22:06Z","links":{"resolver":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI","bundle":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/bundle.json","state":"https://pith.science/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JX4FXY5DCBTRLEN4EZJBMH3SJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JX4FXY5DCBTRLEN4EZJBMH3SJI","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":"fc5f8481c1e9265738f8f69c58cca9c1ddbef8916ffcee6e48c691fe801c06cc","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","title_canon_sha256":"3d0918d3431ed95fe31d5005a6703ebc6edf4e281d88f43ce6b672c5eab19908"},"schema_version":"1.0","source":{"id":"2606.20650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20650","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20650v1","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20650","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"JX4FXY5DCBTR","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"JX4FXY5DCBTRLEN4","created_at":"2026-06-23T00:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"JX4FXY5D","created_at":"2026-06-23T00:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:f802e2562d81e4f9966c1b089332f2340361027a4709f42feb9e6b55362e6ed9","target":"graph","created_at":"2026-06-23T00:11:52Z","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/2606.20650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-based controllable speech synthesis enables users to specify emotions through natural language. However, existing approaches often rely on coarse emotion labels and lack explicit modeling of fine-grained intensity. We propose EmoInstruct-TTS, a dual-path instruction-guided framework for emotional speech synthesis. We introduce Emotion2embed, a supervised semantic-acoustic emotion embedding covering 48 emotional states, including fine-grained categories and intensity levels. To infer embeddings from free-form instructions, we design an Instruction-Conditioned Emotion Flow Model (ICE","authors_text":"Bingao Xu, Ganjun Liu, Hongchuan Wu, Jiasheng Chen, Jun Du, Minghui Wu, Ting Meng, Yonglong Cai, Zikun Fang","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20650","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":"sha256:14cb6a4583167166317dec44d4b0c5642d6f5bca784e6052228e3b9c069bfc50","target":"record","created_at":"2026-06-23T00:11:52Z","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":"fc5f8481c1e9265738f8f69c58cca9c1ddbef8916ffcee6e48c691fe801c06cc","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T06:54:55Z","title_canon_sha256":"3d0918d3431ed95fe31d5005a6703ebc6edf4e281d88f43ce6b672c5eab19908"},"schema_version":"1.0","source":{"id":"2606.20650","kind":"arxiv","version":1}},"canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4df85be3a310671591bc2652161f724a20d4705a28d7f546fd77ba040fb18c2d","first_computed_at":"2026-06-23T00:11:52.578987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:52.578987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXvOp5NISiQKOFsepPZFT3X981lIz4GqXf50kJV/XISIKEsicc3Gi+4GPX9O6TLq0+Ss8XFtkC2mxdrHSrC3Dg==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:52.579369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14cb6a4583167166317dec44d4b0c5642d6f5bca784e6052228e3b9c069bfc50","sha256:f802e2562d81e4f9966c1b089332f2340361027a4709f42feb9e6b55362e6ed9"],"state_sha256":"927379292b25a323774a00d017f0b2baa141c03059577d506b6cec1bdc50e522"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lvilELv0xgnsJ8fWUJ/FE3ABV1dkTsfosnz4EqcMedRqpM5sL6inFzV4soQIzxDzGapjigFyorKBq60z/qF7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T07:22:06.663679Z","bundle_sha256":"9529a2ad7d4c22b5b6c6298258435dec52f43cc4b972889a192de87e51f6c5b2"}}