{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2GBRR5ZQ67R5M6FFZIPB6LRBOL","short_pith_number":"pith:2GBRR5ZQ","canonical_record":{"source":{"id":"2111.13694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-11-28T12:51:04Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d821843913657ecf800e580b430808a5384e9c1e1f31117c630371ca2f7980ae","abstract_canon_sha256":"642519d9a149d4b8d12a851102b47f9c0fe3bcfc145675755978a6d54fabc1ad"},"schema_version":"1.0"},"canonical_sha256":"d18318f730f7e3d678a5ca1e1f2e2172d85f99e39e8d31bc65bb9c45b8f21f75","source":{"kind":"arxiv","id":"2111.13694","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13694","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13694v1","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13694","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"2GBRR5ZQ67R5","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"2GBRR5ZQ67R5M6FF","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"2GBRR5ZQ","created_at":"2026-07-05T03:35:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2GBRR5ZQ67R5M6FFZIPB6LRBOL","target":"record","payload":{"canonical_record":{"source":{"id":"2111.13694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-11-28T12:51:04Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d821843913657ecf800e580b430808a5384e9c1e1f31117c630371ca2f7980ae","abstract_canon_sha256":"642519d9a149d4b8d12a851102b47f9c0fe3bcfc145675755978a6d54fabc1ad"},"schema_version":"1.0"},"canonical_sha256":"d18318f730f7e3d678a5ca1e1f2e2172d85f99e39e8d31bc65bb9c45b8f21f75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:34.910634Z","signature_b64":"R62J5RxpgR1r6yhD++7ULrP/0jhzczcNYqnJyaeWvzWCgL8VBAyFQIpIuuhAMEmKEzHVYhokRf00Tj5HwSORCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d18318f730f7e3d678a5ca1e1f2e2172d85f99e39e8d31bc65bb9c45b8f21f75","last_reissued_at":"2026-07-05T03:35:34.910035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:34.910035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.13694","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":"2026-07-05T03:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOuBwbAJSeuMkJ/hwtdTackKAV2K1nFsC0n733dW0U9zWvDjTmzB2RGXKb0JXPKf0jPA2ZqiHmvDQS1s0SIJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:22.062120Z"},"content_sha256":"b7156584fe97b8101e72518e8a59bc542e0705300ff6c4f3f9abe2a03dfa7832","schema_version":"1.0","event_id":"sha256:b7156584fe97b8101e72518e8a59bc542e0705300ff6c4f3f9abe2a03dfa7832"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2GBRR5ZQ67R5M6FFZIPB6LRBOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ming Lei, Shiliang Zhang, Siqi Zheng, Weilong Huang, Zhihao Du","submitted_at":"2021-11-28T12:51:04Z","abstract_excerpt":"Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels according to the similarities between speech features and given speaker embeddings. Our method is further extended and integrated with downstream tasks by utilizing the textual information, which has not been well studied in previous literature. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13694","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/2111.13694/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":"2026-07-05T03:35:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjaOnax7/VNmEzkG38qraZAArbx+KoIMa+rshrKjEQu6q6ANyY+7BXg7T+TNi/3a9BHJEVDdx/UQx8JjvePZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:22.062649Z"},"content_sha256":"fc724bb5b2ffd1b434c63ba2bbe20e3b2e17ff4e799a48d8f8120c19475134d0","schema_version":"1.0","event_id":"sha256:fc724bb5b2ffd1b434c63ba2bbe20e3b2e17ff4e799a48d8f8120c19475134d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/bundle.json","state_url":"https://pith.science/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/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":"2026-08-05T01:48:22Z","links":{"resolver":"https://pith.science/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL","bundle":"https://pith.science/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/bundle.json","state":"https://pith.science/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GBRR5ZQ67R5M6FFZIPB6LRBOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2GBRR5ZQ67R5M6FFZIPB6LRBOL","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":"642519d9a149d4b8d12a851102b47f9c0fe3bcfc145675755978a6d54fabc1ad","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-11-28T12:51:04Z","title_canon_sha256":"d821843913657ecf800e580b430808a5384e9c1e1f31117c630371ca2f7980ae"},"schema_version":"1.0","source":{"id":"2111.13694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13694","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13694v1","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13694","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_12","alias_value":"2GBRR5ZQ67R5","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_16","alias_value":"2GBRR5ZQ67R5M6FF","created_at":"2026-07-05T03:35:34Z"},{"alias_kind":"pith_short_8","alias_value":"2GBRR5ZQ","created_at":"2026-07-05T03:35:34Z"}],"graph_snapshots":[{"event_id":"sha256:fc724bb5b2ffd1b434c63ba2bbe20e3b2e17ff4e799a48d8f8120c19475134d0","target":"graph","created_at":"2026-07-05T03:35:34Z","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/2111.13694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels according to the similarities between speech features and given speaker embeddings. Our method is further extended and integrated with downstream tasks by utilizing the textual information, which has not been well studied in previous literature. The","authors_text":"Ming Lei, Shiliang Zhang, Siqi Zheng, Weilong Huang, Zhihao Du","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-11-28T12:51:04Z","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13694","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:b7156584fe97b8101e72518e8a59bc542e0705300ff6c4f3f9abe2a03dfa7832","target":"record","created_at":"2026-07-05T03:35:34Z","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":"642519d9a149d4b8d12a851102b47f9c0fe3bcfc145675755978a6d54fabc1ad","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-11-28T12:51:04Z","title_canon_sha256":"d821843913657ecf800e580b430808a5384e9c1e1f31117c630371ca2f7980ae"},"schema_version":"1.0","source":{"id":"2111.13694","kind":"arxiv","version":1}},"canonical_sha256":"d18318f730f7e3d678a5ca1e1f2e2172d85f99e39e8d31bc65bb9c45b8f21f75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d18318f730f7e3d678a5ca1e1f2e2172d85f99e39e8d31bc65bb9c45b8f21f75","first_computed_at":"2026-07-05T03:35:34.910035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:34.910035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R62J5RxpgR1r6yhD++7ULrP/0jhzczcNYqnJyaeWvzWCgL8VBAyFQIpIuuhAMEmKEzHVYhokRf00Tj5HwSORCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:34.910634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.13694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7156584fe97b8101e72518e8a59bc542e0705300ff6c4f3f9abe2a03dfa7832","sha256:fc724bb5b2ffd1b434c63ba2bbe20e3b2e17ff4e799a48d8f8120c19475134d0"],"state_sha256":"cafbca63fa2d11385b57320162cdb784c7b5522aae5e6ea27ace92749daa6d0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1TKRudtXslY0qWsMM/I81S+aGzt13hIaJq/ZM3n6PT1kxpt3+AGxdivcJfS73v8+qoZeH8e+EEi5n7pW8qVgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:48:22.068494Z","bundle_sha256":"c7c3138bee25d73b706441ce4ebd6ed0ca05165c2b3262f18106475f049d439a"}}