{"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"}