{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","short_pith_number":"pith:EF5G2XVK","canonical_record":{"source":{"id":"2409.04859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159","abstract_canon_sha256":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2"},"schema_version":"1.0"},"canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","source":{"kind":"arxiv","id":"2409.04859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04859v2","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"EF5G2XVKUHRM","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"EF5G2XVKUHRMMBLU","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"EF5G2XVK","created_at":"2026-07-05T09:09:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159","abstract_canon_sha256":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2"},"schema_version":"1.0"},"canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:06.505440Z","signature_b64":"Ee1KFSm0Z1SsTLAQgTgap6su1R1BefN3rY6hCfmwrYkppBHW/3Fd2r4TLZx1Rda3jt89h2wJwI8IQiUB+V7xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","last_reissued_at":"2026-07-05T09:09:06.504959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:06.504959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04859","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9wJUmtw87b3e0U7aWjNEhlLhYQAur4hMc18ulzja+pD7h2CnMJpGBlAk2+cRuf0QunVejs8hIh0uotBowGrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:31:44.382176Z"},"content_sha256":"20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3","schema_version":"1.0","event_id":"sha256:20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Yidi Jiang, Zhengyang Chen","submitted_at":"2024-09-07T15:38:28Z","abstract_excerpt":"Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04859","kind":"arxiv","version":2},"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/2409.04859/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":"2026-07-05T09:09:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z+nrwQWEy3F/A8n44Lp9yCOUEpKuxuo4IzcEZ3w8BjUwwoz4lnIf2gdpsKZ56LHOfZdh8H+57N6tj2obfZEQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:31:44.382679Z"},"content_sha256":"e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7","schema_version":"1.0","event_id":"sha256:e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/bundle.json","state_url":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/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":"2026-07-31T21:31:44Z","links":{"resolver":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT","bundle":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/bundle.json","state":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","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":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159"},"schema_version":"1.0","source":{"id":"2409.04859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04859v2","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04859","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"EF5G2XVKUHRM","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"EF5G2XVKUHRMMBLU","created_at":"2026-07-05T09:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"EF5G2XVK","created_at":"2026-07-05T09:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7","target":"graph","created_at":"2026-07-05T09:09:06Z","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/2409.04859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, w","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Yidi Jiang, Zhengyang Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04859","kind":"arxiv","version":2},"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":"sha256:20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3","target":"record","created_at":"2026-07-05T09:09:06Z","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":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159"},"schema_version":"1.0","source":{"id":"2409.04859","kind":"arxiv","version":2}},"canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","first_computed_at":"2026-07-05T09:09:06.504959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:06.504959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ee1KFSm0Z1SsTLAQgTgap6su1R1BefN3rY6hCfmwrYkppBHW/3Fd2r4TLZx1Rda3jt89h2wJwI8IQiUB+V7xBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:06.505440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20120980d5b1821652e746ca4ddab038683aaa73883bd1b4b8f20e351a59bdc3","sha256:e24decf959d067fe6e603b956da38858afe8a058ad2f12aec982ea06de39afb7"],"state_sha256":"665cca593b09297a064538362b67473eee5afce5bea2efd06e248856ed0a7a34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"db6j8Y5lbGMT9uDiB+gtQJ7j5h3zuMwlknqEsdm0yNKJzXgSbK32C8BA4PgalihlRMVT4VnhogKwrvX9C/URAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T21:31:44.386832Z","bundle_sha256":"daaa59c2db70cb78f4956ff33a59d0a9619b69394f89247da21fadb1777ae848"}}