{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRNK7DI25DTYBDP4ZWTF4VLPVW","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":"582fa608d32df89c2854819382c073d6a52dc07bf43e539182f241aa1574c127","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T12:18:18Z","title_canon_sha256":"826f1b7a3ce04c8a985b147e774e1a63df302752483214401ac8e8e36a141c66"},"schema_version":"1.0","source":{"id":"2406.07198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07198","created_at":"2026-07-05T08:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07198v1","created_at":"2026-07-05T08:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07198","created_at":"2026-07-05T08:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"RRNK7DI25DTY","created_at":"2026-07-05T08:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"RRNK7DI25DTYBDP4","created_at":"2026-07-05T08:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"RRNK7DI2","created_at":"2026-07-05T08:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:243a39bce87801a877e79076ffb632ffe843a4f874d031ff0fa8bea59a1571a0","target":"graph","created_at":"2026-07-05T08:30:19Z","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/2406.07198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional speaker diarization seeks to detect ``who spoke when'' according to speaker characteristics. Extending to target speech diarization, we detect ``when target event occurs'' according to the semantic characteristics of speech. We propose a novel Multimodal Target Speech Diarization (MM-TSD) framework, which accommodates diverse and multi-modal prompts to specify target events in a flexible and user-friendly manner, including semantic language description, pre-enrolled speech, pre-registered face image, and audio-language logical prompts. We further propose a voice-face aligner module","authors_text":"Haizhou Li, Ruijie Tao, Yanmin Qian, Yidi Jiang, Zhengyang Chen","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T12:18:18Z","title":"Target Speech Diarization with Multimodal Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07198","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:b8dca7c797337d3e94c0a535824d937178ed3d6667df7fe3453267f3a408a661","target":"record","created_at":"2026-07-05T08:30:19Z","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":"582fa608d32df89c2854819382c073d6a52dc07bf43e539182f241aa1574c127","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T12:18:18Z","title_canon_sha256":"826f1b7a3ce04c8a985b147e774e1a63df302752483214401ac8e8e36a141c66"},"schema_version":"1.0","source":{"id":"2406.07198","kind":"arxiv","version":1}},"canonical_sha256":"8c5aaf8d1ae8e7808dfccda65e556fad941f4da3a57232b953d64dce98f36cc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c5aaf8d1ae8e7808dfccda65e556fad941f4da3a57232b953d64dce98f36cc2","first_computed_at":"2026-07-05T08:30:19.793976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:19.793976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"83/AHebuw3nDGPJDSbPLxy8a8QFbzTo4ov48Gy13i3MOEL79dvylMHKyu1tWw6By0pKKos1aL24EvJUymUakBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:19.794482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8dca7c797337d3e94c0a535824d937178ed3d6667df7fe3453267f3a408a661","sha256:243a39bce87801a877e79076ffb632ffe843a4f874d031ff0fa8bea59a1571a0"],"state_sha256":"de94397e380a5bdeba514a367293be8598748d2a7d9158e3ca0f2133c16a5455"}