{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MP4OLXHVBWSILTGTFOONHYLDUQ","short_pith_number":"pith:MP4OLXHV","canonical_record":{"source":{"id":"2409.11835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T09:36:55Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"401aeff19d3d8b3b2f19b3f3d547fb43ec957cd0091eaf6ed4aebaa868c4e30e","abstract_canon_sha256":"28102fa54ece733658ccb396066a382304fd2fe5c41bc61f40c0558390edda71"},"schema_version":"1.0"},"canonical_sha256":"63f8e5dcf50da485ccd32b9cd3e163a405209706f4af1b070ab6735f3b040571","source":{"kind":"arxiv","id":"2409.11835","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11835","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11835v1","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11835","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_12","alias_value":"MP4OLXHVBWSI","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_16","alias_value":"MP4OLXHVBWSILTGT","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_8","alias_value":"MP4OLXHV","created_at":"2026-07-05T09:08:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MP4OLXHVBWSILTGTFOONHYLDUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T09:36:55Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"401aeff19d3d8b3b2f19b3f3d547fb43ec957cd0091eaf6ed4aebaa868c4e30e","abstract_canon_sha256":"28102fa54ece733658ccb396066a382304fd2fe5c41bc61f40c0558390edda71"},"schema_version":"1.0"},"canonical_sha256":"63f8e5dcf50da485ccd32b9cd3e163a405209706f4af1b070ab6735f3b040571","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:38.611499Z","signature_b64":"S73WWgFEmVx6M+O4SmElXEtZBZ+naRC1E5nTWxBAKWCKWTyXvmnRBBHkhRw+tHNeWnILXxHztS6t1FKZ8yZ9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f8e5dcf50da485ccd32b9cd3e163a405209706f4af1b070ab6735f3b040571","last_reissued_at":"2026-07-05T09:08:38.610977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:38.610977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11835","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":"2026-07-05T09:08:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0s/PwMhu8ErAa0SPHLoYnXyPM2Lot3n/0eXzYJEYCKj2ErF4C5e8CcXxUHfXJ5DmCAg3ejfnNqhyXGm5JUnaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:19:22.192325Z"},"content_sha256":"79cd47e09e32cb977468df0097cd26cf01a913ece5f329cf4e038e6165daf232","schema_version":"1.0","event_id":"sha256:79cd47e09e32cb977468df0097cd26cf01a913ece5f329cf4e038e6165daf232"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MP4OLXHVBWSILTGTFOONHYLDUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Chunyu Qiang, Guanjun Li, Jianhua Tao, Ruibo Fu, Shuchen Shi, Tao Wang, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yuankun Xie, Yukun Liu, Zhengqi Wen, Zhiyong Wang","submitted_at":"2024-09-18T09:36:55Z","abstract_excerpt":"In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the specific acoustic properties of speech. To address these limitations, we propose a method called Directional Patch Interaction for Text-to-Speech (DPI-TTS), which builds on DiT and achieves fast training without compromising accuracy. Notably, DPI-TTS employs a low-to-high frequency, frame-by-frame "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11835","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/2409.11835/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":"2026-07-05T09:08:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yjIBWHs9QzNAamRLbdgtmrxtty6GB8V1YAS8FsvvNjg3g+rRQfGjdNspf+IVL6G08fCAwON+Z0XyOS2EZ1PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T12:19:22.192746Z"},"content_sha256":"1685850e6a3d64b3ee93b3b016315ebe1a0606f96b0cc5b16119a2ae149ad282","schema_version":"1.0","event_id":"sha256:1685850e6a3d64b3ee93b3b016315ebe1a0606f96b0cc5b16119a2ae149ad282"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/bundle.json","state_url":"https://pith.science/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/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":"2026-07-08T12:19:22Z","links":{"resolver":"https://pith.science/pith/MP4OLXHVBWSILTGTFOONHYLDUQ","bundle":"https://pith.science/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/bundle.json","state":"https://pith.science/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MP4OLXHVBWSILTGTFOONHYLDUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MP4OLXHVBWSILTGTFOONHYLDUQ","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":"28102fa54ece733658ccb396066a382304fd2fe5c41bc61f40c0558390edda71","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T09:36:55Z","title_canon_sha256":"401aeff19d3d8b3b2f19b3f3d547fb43ec957cd0091eaf6ed4aebaa868c4e30e"},"schema_version":"1.0","source":{"id":"2409.11835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11835","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11835v1","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11835","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_12","alias_value":"MP4OLXHVBWSI","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_16","alias_value":"MP4OLXHVBWSILTGT","created_at":"2026-07-05T09:08:38Z"},{"alias_kind":"pith_short_8","alias_value":"MP4OLXHV","created_at":"2026-07-05T09:08:38Z"}],"graph_snapshots":[{"event_id":"sha256:1685850e6a3d64b3ee93b3b016315ebe1a0606f96b0cc5b16119a2ae149ad282","target":"graph","created_at":"2026-07-05T09:08:38Z","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/2409.11835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the specific acoustic properties of speech. To address these limitations, we propose a method called Directional Patch Interaction for Text-to-Speech (DPI-TTS), which builds on DiT and achieves fast training without compromising accuracy. Notably, DPI-TTS employs a low-to-high frequency, frame-by-frame ","authors_text":"Chenxing Li, Chunyu Qiang, Guanjun Li, Jianhua Tao, Ruibo Fu, Shuchen Shi, Tao Wang, Xiaopeng Wang, Xin Qi, Xuefei Liu, Yi Lu, Yuankun Xie, Yukun Liu, Zhengqi Wen, Zhiyong Wang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T09:36:55Z","title":"DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11835","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":"sha256:79cd47e09e32cb977468df0097cd26cf01a913ece5f329cf4e038e6165daf232","target":"record","created_at":"2026-07-05T09:08:38Z","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":"28102fa54ece733658ccb396066a382304fd2fe5c41bc61f40c0558390edda71","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T09:36:55Z","title_canon_sha256":"401aeff19d3d8b3b2f19b3f3d547fb43ec957cd0091eaf6ed4aebaa868c4e30e"},"schema_version":"1.0","source":{"id":"2409.11835","kind":"arxiv","version":1}},"canonical_sha256":"63f8e5dcf50da485ccd32b9cd3e163a405209706f4af1b070ab6735f3b040571","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63f8e5dcf50da485ccd32b9cd3e163a405209706f4af1b070ab6735f3b040571","first_computed_at":"2026-07-05T09:08:38.610977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:38.610977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S73WWgFEmVx6M+O4SmElXEtZBZ+naRC1E5nTWxBAKWCKWTyXvmnRBBHkhRw+tHNeWnILXxHztS6t1FKZ8yZ9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:38.611499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79cd47e09e32cb977468df0097cd26cf01a913ece5f329cf4e038e6165daf232","sha256:1685850e6a3d64b3ee93b3b016315ebe1a0606f96b0cc5b16119a2ae149ad282"],"state_sha256":"7cf40a1c86103d8db234dd6b2394fb9ada3b70d829e3d79b530d35846db211a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dJTJE7QsT871Z+sR8WYrp843rHEWaf7p+XiGVtGnUcvwnN5soYyeHakKsRejibe4JMiEgDsQlwn5EoyWRhNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T12:19:22.195288Z","bundle_sha256":"33a43332169a3cba674bb965a4bf95985aec5c1d049414fe0b98d8b89c59921f"}}