{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7X3FEAJOPQFPC55C5TP6QHGUVI","short_pith_number":"pith:7X3FEAJO","canonical_record":{"source":{"id":"2309.06672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e6a0ce0080f4411bebd4fb74a25f1d84ca91a18ceb7edd9eb9ec289ebc72d6e5","abstract_canon_sha256":"005d06608acbb98d34d5551ee91660be2b10e839cafd844a0dd86059fd9b9351"},"schema_version":"1.0"},"canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","source":{"kind":"arxiv","id":"2309.06672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06672","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06672v1","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06672","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"7X3FEAJOPQFP","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"7X3FEAJOPQFPC55C","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"7X3FEAJO","created_at":"2026-07-05T06:50:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7X3FEAJOPQFPC55C5TP6QHGUVI","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e6a0ce0080f4411bebd4fb74a25f1d84ca91a18ceb7edd9eb9ec289ebc72d6e5","abstract_canon_sha256":"005d06608acbb98d34d5551ee91660be2b10e839cafd844a0dd86059fd9b9351"},"schema_version":"1.0"},"canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:21.123978Z","signature_b64":"OoF9ffFR+Y8JGI//sJfgO46mcQXJnbHMl+VDrrb0X0FNLNXMiqTiF0+mBMb0aVWbLcOtha1A6UpGsLdroavhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","last_reissued_at":"2026-07-05T06:50:21.123534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:21.123534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06672","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":"2026-07-05T06:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLdwVupNa59dmnNYKOdM7BaWiDVVTRQ0cy+AmfWtoDflrZG/Tn/uUc9z1ohsM3kVms+/seg4nRs15A73GrpHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T02:58:38.901171Z"},"content_sha256":"2ee81e7e8d9472d91f1a9dd884d39644b16c1bcdbdc90a1b625a5d7df54c85cb","schema_version":"1.0","event_id":"sha256:2ee81e7e8d9472d91f1a9dd884d39644b16c1bcdbdc90a1b625a5d7df54c85cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7X3FEAJOPQFPC55C5TP6QHGUVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer","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, Zhengyang Chen","submitted_at":"2023-09-13T02:17:13Z","abstract_excerpt":"Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06672","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/2309.06672/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":"2026-07-05T06:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q6ygUQWPo0nCEroH//Mb77bfRLizEkRpkeHGSgOzeiKbf7/swTmqN/LN8Vhg/pHO/h/hGQKhSKqfuIgoY4kgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T02:58:38.901557Z"},"content_sha256":"72a24d71ab7d53b51910f8c6aaa13a17222bbbb8b4ad9d813b716c81e9406e44","schema_version":"1.0","event_id":"sha256:72a24d71ab7d53b51910f8c6aaa13a17222bbbb8b4ad9d813b716c81e9406e44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/bundle.json","state_url":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/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":"2026-07-12T02:58:38Z","links":{"resolver":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI","bundle":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/bundle.json","state":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7X3FEAJOPQFPC55C5TP6QHGUVI","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":"005d06608acbb98d34d5551ee91660be2b10e839cafd844a0dd86059fd9b9351","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","title_canon_sha256":"e6a0ce0080f4411bebd4fb74a25f1d84ca91a18ceb7edd9eb9ec289ebc72d6e5"},"schema_version":"1.0","source":{"id":"2309.06672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06672","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06672v1","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06672","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"7X3FEAJOPQFP","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"7X3FEAJOPQFPC55C","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"7X3FEAJO","created_at":"2026-07-05T06:50:21Z"}],"graph_snapshots":[{"event_id":"sha256:72a24d71ab7d53b51910f8c6aaa13a17222bbbb8b4ad9d813b716c81e9406e44","target":"graph","created_at":"2026-07-05T06:50:21Z","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/2309.06672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For ","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Zhengyang Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","title":"Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06672","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":"sha256:2ee81e7e8d9472d91f1a9dd884d39644b16c1bcdbdc90a1b625a5d7df54c85cb","target":"record","created_at":"2026-07-05T06:50:21Z","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":"005d06608acbb98d34d5551ee91660be2b10e839cafd844a0dd86059fd9b9351","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","title_canon_sha256":"e6a0ce0080f4411bebd4fb74a25f1d84ca91a18ceb7edd9eb9ec289ebc72d6e5"},"schema_version":"1.0","source":{"id":"2309.06672","kind":"arxiv","version":1}},"canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","first_computed_at":"2026-07-05T06:50:21.123534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:21.123534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OoF9ffFR+Y8JGI//sJfgO46mcQXJnbHMl+VDrrb0X0FNLNXMiqTiF0+mBMb0aVWbLcOtha1A6UpGsLdroavhAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:21.123978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee81e7e8d9472d91f1a9dd884d39644b16c1bcdbdc90a1b625a5d7df54c85cb","sha256:72a24d71ab7d53b51910f8c6aaa13a17222bbbb8b4ad9d813b716c81e9406e44"],"state_sha256":"849fa20c62ff497012c9c11a8459bd6b54755c313aa0fb3bf1fce63c2c38f286"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+soETVn+pqQEykaAYBQWYGI7mkIHp/UWro+M1DvQSsG85GwvBiaQAAmSU+y8Tdpbvzt+S9CtjE/3nw2KWl51Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T02:58:38.903656Z","bundle_sha256":"6b0b33ceb66b37d7491517cd0d383083228566d73769d19af918d30d57da809e"}}