{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WH7U2LCA7KPPY7A5HGTZO4T7IQ","short_pith_number":"pith:WH7U2LCA","canonical_record":{"source":{"id":"2101.08473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"11334201cfb3aa6cc2e80b3d37eb13a5dfa604a4e1afd1bd748c0e0e35e1d246","abstract_canon_sha256":"f66d7f59196173e3a4bd58e4c29f94a3603e0162fbe05f98133375f501eecf5e"},"schema_version":"1.0"},"canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","source":{"kind":"arxiv","id":"2101.08473","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08473","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08473v2","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08473","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"WH7U2LCA7KPP","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"WH7U2LCA7KPPY7A5","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"WH7U2LCA","created_at":"2026-07-05T02:29:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WH7U2LCA7KPPY7A5HGTZO4T7IQ","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"11334201cfb3aa6cc2e80b3d37eb13a5dfa604a4e1afd1bd748c0e0e35e1d246","abstract_canon_sha256":"f66d7f59196173e3a4bd58e4c29f94a3603e0162fbe05f98133375f501eecf5e"},"schema_version":"1.0"},"canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:57.078881Z","signature_b64":"jAEgHN10HLttGSd7GPVswAlRZnTb7V7m5zGvvxMRz87WMWepYkS8NmtsD/nlpzVKAPTbYUxBuXa28TAgqMDXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","last_reissued_at":"2026-07-05T02:29:57.078434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:57.078434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08473","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":"2026-07-05T02:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+dBUiNlPUp9OBFsoDZdqJip26x9mAJisnGGBfECrqatOUFHE6n3TzbIiegrIBBD6B0dqAwqeaz2svkrVtSFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:20.600929Z"},"content_sha256":"9e5ba76178bd7563cdb01963f57587526e98f949e960d1491358f6ccf0fe00d0","schema_version":"1.0","event_id":"sha256:9e5ba76178bd7563cdb01963f57587526e98f949e960d1491358f6ccf0fe00d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WH7U2LCA7KPPY7A5HGTZO4T7IQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kenji Nagamatsu, Paola Garcia, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yuki Takashima, Yusuke Fujita","submitted_at":"2021-01-21T07:24:21Z","abstract_excerpt":"We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08473","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/2101.08473/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":"2026-07-05T02:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIhw2fraCjGgT3hS8iE1pX+j0Ls2Ma8j1WMlmJGLS8HnOT2uwr8I80nhut/iZdzaAg4FoHUeWHj/D3wST3QxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:29:20.601848Z"},"content_sha256":"aad75d66772c56d2444f2122dc8045b84572a284f210ed3c7ba9207f814ac433","schema_version":"1.0","event_id":"sha256:aad75d66772c56d2444f2122dc8045b84572a284f210ed3c7ba9207f814ac433"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/bundle.json","state_url":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/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":"2026-08-04T19:29:20Z","links":{"resolver":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ","bundle":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/bundle.json","state":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WH7U2LCA7KPPY7A5HGTZO4T7IQ","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":"f66d7f59196173e3a4bd58e4c29f94a3603e0162fbe05f98133375f501eecf5e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","title_canon_sha256":"11334201cfb3aa6cc2e80b3d37eb13a5dfa604a4e1afd1bd748c0e0e35e1d246"},"schema_version":"1.0","source":{"id":"2101.08473","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08473","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08473v2","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08473","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"WH7U2LCA7KPP","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"WH7U2LCA7KPPY7A5","created_at":"2026-07-05T02:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"WH7U2LCA","created_at":"2026-07-05T02:29:57Z"}],"graph_snapshots":[{"event_id":"sha256:aad75d66772c56d2444f2122dc8045b84572a284f210ed3c7ba9207f814ac433","target":"graph","created_at":"2026-07-05T02:29:57Z","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/2101.08473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed ","authors_text":"Kenji Nagamatsu, Paola Garcia, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yuki Takashima, Yusuke Fujita","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","title":"Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08473","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":"sha256:9e5ba76178bd7563cdb01963f57587526e98f949e960d1491358f6ccf0fe00d0","target":"record","created_at":"2026-07-05T02:29:57Z","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":"f66d7f59196173e3a4bd58e4c29f94a3603e0162fbe05f98133375f501eecf5e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","title_canon_sha256":"11334201cfb3aa6cc2e80b3d37eb13a5dfa604a4e1afd1bd748c0e0e35e1d246"},"schema_version":"1.0","source":{"id":"2101.08473","kind":"arxiv","version":2}},"canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","first_computed_at":"2026-07-05T02:29:57.078434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:57.078434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jAEgHN10HLttGSd7GPVswAlRZnTb7V7m5zGvvxMRz87WMWepYkS8NmtsD/nlpzVKAPTbYUxBuXa28TAgqMDXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:57.078881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08473","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e5ba76178bd7563cdb01963f57587526e98f949e960d1491358f6ccf0fe00d0","sha256:aad75d66772c56d2444f2122dc8045b84572a284f210ed3c7ba9207f814ac433"],"state_sha256":"bc4bae4926801d9aaa46d38ffe6e986674c8ce6c646ce4b2600c10740ee02eac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sb5c62fBXPWBHSuiRK5hpZirLUos8vliophm+m5Ecw3KbHFK8nm4Qyup9ook7w5xwuE6zLmVF29UiKRE9yRKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:29:20.608796Z","bundle_sha256":"d730b45b743435ccae9850f0f5e757833685e67df62e8176751a7d97b26c4ed3"}}