{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J2NYAANXB7QF7Y6KUL7B6NBG6G","short_pith_number":"pith:J2NYAANX","canonical_record":{"source":{"id":"2309.08489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T15:48:45Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"4ec20cd9153efe3538112727b780f1e7a66023eee3a6a00273afa5c1e26b09b4","abstract_canon_sha256":"c5eae6b2d556a0f2f788b5319f462a65f1b601e78559fcbf729d7991a962e23c"},"schema_version":"1.0"},"canonical_sha256":"4e9b8001b70fe05fe3caa2fe1f3426f1b3adde47fbadd3cc53c902b17e02eb4f","source":{"kind":"arxiv","id":"2309.08489","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08489","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08489v1","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08489","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"J2NYAANXB7QF","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"J2NYAANXB7QF7Y6K","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"J2NYAANX","created_at":"2026-07-05T06:51:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J2NYAANXB7QF7Y6KUL7B6NBG6G","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T15:48:45Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"4ec20cd9153efe3538112727b780f1e7a66023eee3a6a00273afa5c1e26b09b4","abstract_canon_sha256":"c5eae6b2d556a0f2f788b5319f462a65f1b601e78559fcbf729d7991a962e23c"},"schema_version":"1.0"},"canonical_sha256":"4e9b8001b70fe05fe3caa2fe1f3426f1b3adde47fbadd3cc53c902b17e02eb4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:07.155958Z","signature_b64":"UHaYDaE7jvzHenrg4uQmjCre6k4up1wF7MIdBBuNCh0cqCkftbuyW0uWAsOLC43QwkFbJ7T94WFS3LSnX5O3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e9b8001b70fe05fe3caa2fe1f3426f1b3adde47fbadd3cc53c902b17e02eb4f","last_reissued_at":"2026-07-05T06:51:07.155561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:07.155561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08489","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":"2026-07-05T06:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LB4b/em70YL45ZBzLNrUUiHJjF9OMOPP0l2H8NjA4QwLBhVJeQIEwSWIgjswxGZJ83DZdOjuV7Gpe6JeoqI8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:46:38.933436Z"},"content_sha256":"378727654e920f128ab2e2a437cc24bddcc65adaa018118eba97856006b95ab0","schema_version":"1.0","event_id":"sha256:378727654e920f128ab2e2a437cc24bddcc65adaa018118eba97856006b95ab0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J2NYAANXB7QF7Y6KUL7B6NBG6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Guanlong Zhao, Hank Liao, Quan Wang, Weiran Wang, Wei Xia, Yiling Huang","submitted_at":"2023-09-15T15:48:45Z","abstract_excerpt":"While standard speaker diarization attempts to answer the question \"who spoken when\", most of relevant applications in reality are more interested in determining \"who spoken what\". Whether it is the conventional modularized approach or the more recent end-to-end neural diarization (EEND), an additional automatic speech recognition (ASR) model and an orchestration algorithm are required to associate the speaker labels with recognized words. In this paper, we propose Word-level End-to-End Neural Diarization (WEEND) with auxiliary network, a multi-task learning algorithm that performs end-to-end "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08489","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/2309.08489/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":"2026-07-05T06:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U2TFbb78N1V5/Lj5Ji+fsXcaQIz0Ql2vrGbYODTuQX24NHwV6NgXTKKeAuRdnuKwANC02AgOds22Uxkfp171Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:46:38.933963Z"},"content_sha256":"a6da29115cc3221038a4b49b75ae820d2d8e6c150930cd913e91c75abb7bacdd","schema_version":"1.0","event_id":"sha256:a6da29115cc3221038a4b49b75ae820d2d8e6c150930cd913e91c75abb7bacdd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/bundle.json","state_url":"https://pith.science/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/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":"2026-08-21T05:46:38Z","links":{"resolver":"https://pith.science/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G","bundle":"https://pith.science/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/bundle.json","state":"https://pith.science/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2NYAANXB7QF7Y6KUL7B6NBG6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J2NYAANXB7QF7Y6KUL7B6NBG6G","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":"c5eae6b2d556a0f2f788b5319f462a65f1b601e78559fcbf729d7991a962e23c","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T15:48:45Z","title_canon_sha256":"4ec20cd9153efe3538112727b780f1e7a66023eee3a6a00273afa5c1e26b09b4"},"schema_version":"1.0","source":{"id":"2309.08489","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08489","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08489v1","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08489","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"J2NYAANXB7QF","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"J2NYAANXB7QF7Y6K","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"J2NYAANX","created_at":"2026-07-05T06:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:a6da29115cc3221038a4b49b75ae820d2d8e6c150930cd913e91c75abb7bacdd","target":"graph","created_at":"2026-07-05T06:51:07Z","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/2309.08489/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While standard speaker diarization attempts to answer the question \"who spoken when\", most of relevant applications in reality are more interested in determining \"who spoken what\". Whether it is the conventional modularized approach or the more recent end-to-end neural diarization (EEND), an additional automatic speech recognition (ASR) model and an orchestration algorithm are required to associate the speaker labels with recognized words. In this paper, we propose Word-level End-to-End Neural Diarization (WEEND) with auxiliary network, a multi-task learning algorithm that performs end-to-end ","authors_text":"Guanlong Zhao, Hank Liao, Quan Wang, Weiran Wang, Wei Xia, Yiling Huang","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T15:48:45Z","title":"Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08489","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":"sha256:378727654e920f128ab2e2a437cc24bddcc65adaa018118eba97856006b95ab0","target":"record","created_at":"2026-07-05T06:51:07Z","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":"c5eae6b2d556a0f2f788b5319f462a65f1b601e78559fcbf729d7991a962e23c","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T15:48:45Z","title_canon_sha256":"4ec20cd9153efe3538112727b780f1e7a66023eee3a6a00273afa5c1e26b09b4"},"schema_version":"1.0","source":{"id":"2309.08489","kind":"arxiv","version":1}},"canonical_sha256":"4e9b8001b70fe05fe3caa2fe1f3426f1b3adde47fbadd3cc53c902b17e02eb4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e9b8001b70fe05fe3caa2fe1f3426f1b3adde47fbadd3cc53c902b17e02eb4f","first_computed_at":"2026-07-05T06:51:07.155561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:07.155561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHaYDaE7jvzHenrg4uQmjCre6k4up1wF7MIdBBuNCh0cqCkftbuyW0uWAsOLC43QwkFbJ7T94WFS3LSnX5O3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:07.155958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08489","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:378727654e920f128ab2e2a437cc24bddcc65adaa018118eba97856006b95ab0","sha256:a6da29115cc3221038a4b49b75ae820d2d8e6c150930cd913e91c75abb7bacdd"],"state_sha256":"f5a25d6e5b8f99934511537ef9916680210057f9c47c99e7abbb15cfbda2ec41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hSshafZ1/f/JLWGTHYmtKc75D84Gh35YJRF0THtVPIndOUEbHNzgYGsI+1wUUzGzEfKvmyOujTE8DpOBBioqAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:46:38.938708Z","bundle_sha256":"f1c4c0aa63e7414cf797b13fd579b9625b3ceb6dbd6af8799c66fb9bf4fb9776"}}