{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PN2SRYNUHTA2FTH64QA2LTQU4T","short_pith_number":"pith:PN2SRYNU","canonical_record":{"source":{"id":"2509.06074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:32:29Z","cross_cats_sorted":[],"title_canon_sha256":"38d62b42bfa14d17c3c50d5e57ffebf62ee98fbc0b41fc124bba78999e62bdc0","abstract_canon_sha256":"f7ecabc0f4f28397c86b816f7f987a7df4a9eb559db3c202275c198069c46853"},"schema_version":"1.0"},"canonical_sha256":"7b7528e1b43cc1a2ccfee401a5ce14e4f987f7619dd1b87b0212240811733c8f","source":{"kind":"arxiv","id":"2509.06074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06074","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06074v1","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06074","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"PN2SRYNUHTA2","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"PN2SRYNUHTA2FTH6","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"PN2SRYNU","created_at":"2026-07-05T12:06:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PN2SRYNUHTA2FTH64QA2LTQU4T","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:32:29Z","cross_cats_sorted":[],"title_canon_sha256":"38d62b42bfa14d17c3c50d5e57ffebf62ee98fbc0b41fc124bba78999e62bdc0","abstract_canon_sha256":"f7ecabc0f4f28397c86b816f7f987a7df4a9eb559db3c202275c198069c46853"},"schema_version":"1.0"},"canonical_sha256":"7b7528e1b43cc1a2ccfee401a5ce14e4f987f7619dd1b87b0212240811733c8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:29.555245Z","signature_b64":"6OvHEEP6leWqeYBNfOS/v6FxqfXeYcG6E3ifnNyOdhsfnEYTDEnq3XchUCQWihYQtDytqvAVtpF7vBHE4/biCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b7528e1b43cc1a2ccfee401a5ce14e4f987f7619dd1b87b0212240811733c8f","last_reissued_at":"2026-07-05T12:06:29.554748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:29.554748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06074","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":"2026-07-05T12:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Velr6xHo5B1za0fp+7W2VG5U+nVxxJfBcPCV8iULGCljeGFS9q5LPD1NhIxmYl+OpJ0hwNo9LHN137piDOuVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:01:01.745475Z"},"content_sha256":"498318d56c3a0f25a92dae93536e82efec1614b32d266d90a7d205c288f99302","schema_version":"1.0","event_id":"sha256:498318d56c3a0f25a92dae93536e82efec1614b32d266d90a7d205c288f99302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PN2SRYNUHTA2FTH64QA2LTQU4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berrak Sisman, Haizhou Li, Rui Liu, Zhenqi Jia","submitted_at":"2025-09-07T14:32:29Z","abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the utterance-level interaction characteristics of MDH and the target utterance. However, MDH contains fine-grained semantic and prosody knowledge at the word level. Existing methods overlook the fine-grained semantic and prosodic interaction modeling. To address this gap, we propose MFCIG-CSS, a novel Multimodal Fine-grained Context Interaction Graph-based CSS syst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06074","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/2509.06074/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":"2026-07-05T12:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsvFTS/OnPQJr8fsbtaDfTg8ffZUbwFzOn9yVHm9KgxuCNf00I4wAwsPn5dCqNpgmUlYvqD+AuCpam4h5YGmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:01:01.745964Z"},"content_sha256":"8d438d384735929f911d65c6bfbc95f07f0fe9c4cfa5048f391700898bf2f67a","schema_version":"1.0","event_id":"sha256:8d438d384735929f911d65c6bfbc95f07f0fe9c4cfa5048f391700898bf2f67a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/bundle.json","state_url":"https://pith.science/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/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":"2026-08-04T13:01:01Z","links":{"resolver":"https://pith.science/pith/PN2SRYNUHTA2FTH64QA2LTQU4T","bundle":"https://pith.science/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/bundle.json","state":"https://pith.science/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PN2SRYNUHTA2FTH64QA2LTQU4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PN2SRYNUHTA2FTH64QA2LTQU4T","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":"f7ecabc0f4f28397c86b816f7f987a7df4a9eb559db3c202275c198069c46853","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:32:29Z","title_canon_sha256":"38d62b42bfa14d17c3c50d5e57ffebf62ee98fbc0b41fc124bba78999e62bdc0"},"schema_version":"1.0","source":{"id":"2509.06074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06074","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06074v1","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06074","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"PN2SRYNUHTA2","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"PN2SRYNUHTA2FTH6","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"PN2SRYNU","created_at":"2026-07-05T12:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:8d438d384735929f911d65c6bfbc95f07f0fe9c4cfa5048f391700898bf2f67a","target":"graph","created_at":"2026-07-05T12:06:29Z","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/2509.06074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to generate speech with natural prosody by understanding the multimodal dialogue history (MDH). The latest work predicts the accurate prosody expression of the target utterance by modeling the utterance-level interaction characteristics of MDH and the target utterance. However, MDH contains fine-grained semantic and prosody knowledge at the word level. Existing methods overlook the fine-grained semantic and prosodic interaction modeling. To address this gap, we propose MFCIG-CSS, a novel Multimodal Fine-grained Context Interaction Graph-based CSS syst","authors_text":"Berrak Sisman, Haizhou Li, Rui Liu, Zhenqi Jia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:32:29Z","title":"Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06074","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":"sha256:498318d56c3a0f25a92dae93536e82efec1614b32d266d90a7d205c288f99302","target":"record","created_at":"2026-07-05T12:06:29Z","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":"f7ecabc0f4f28397c86b816f7f987a7df4a9eb559db3c202275c198069c46853","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:32:29Z","title_canon_sha256":"38d62b42bfa14d17c3c50d5e57ffebf62ee98fbc0b41fc124bba78999e62bdc0"},"schema_version":"1.0","source":{"id":"2509.06074","kind":"arxiv","version":1}},"canonical_sha256":"7b7528e1b43cc1a2ccfee401a5ce14e4f987f7619dd1b87b0212240811733c8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b7528e1b43cc1a2ccfee401a5ce14e4f987f7619dd1b87b0212240811733c8f","first_computed_at":"2026-07-05T12:06:29.554748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:29.554748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6OvHEEP6leWqeYBNfOS/v6FxqfXeYcG6E3ifnNyOdhsfnEYTDEnq3XchUCQWihYQtDytqvAVtpF7vBHE4/biCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:29.555245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:498318d56c3a0f25a92dae93536e82efec1614b32d266d90a7d205c288f99302","sha256:8d438d384735929f911d65c6bfbc95f07f0fe9c4cfa5048f391700898bf2f67a"],"state_sha256":"218bd75cec5e8fc41a1637d9381a871c9fd5bb9af9a38eeb72ce87faa86c2144"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9GDdBQw5bBsupYPY2aRb9wcgL7lGeYQ6BYaa91Pw7XmPVFFh8RT2JWmYO78jdBcKoLnr60xZ/rTDV2nyCM1sDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:01:01.750419Z","bundle_sha256":"078c658d7f2305db30b138e9a69b68d9417bc71f5585f02bb44458eeb45547ce"}}