{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DKVJK264NNB7FKZA3B6ZQUC2O3","short_pith_number":"pith:DKVJK264","canonical_record":{"source":{"id":"2202.00842","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-02T01:27:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3b1163da2f2ff11a6c36f53be4280c51a38fbf0ae055bc0ba3733f2522861b44","abstract_canon_sha256":"eb71e3713ca4f595b6074a0c5e47bc2bcb16b5a297fb28bf06a39bdf22cc663a"},"schema_version":"1.0"},"canonical_sha256":"1aaa956bdc6b43f2ab20d87d98505a76dfe5ddc0b1740a0703d4e75bddca5d42","source":{"kind":"arxiv","id":"2202.00842","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00842","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00842v5","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00842","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"DKVJK264NNB7","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_16","alias_value":"DKVJK264NNB7FKZA","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_8","alias_value":"DKVJK264","created_at":"2026-07-05T04:40:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DKVJK264NNB7FKZA3B6ZQUC2O3","target":"record","payload":{"canonical_record":{"source":{"id":"2202.00842","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-02T01:27:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3b1163da2f2ff11a6c36f53be4280c51a38fbf0ae055bc0ba3733f2522861b44","abstract_canon_sha256":"eb71e3713ca4f595b6074a0c5e47bc2bcb16b5a297fb28bf06a39bdf22cc663a"},"schema_version":"1.0"},"canonical_sha256":"1aaa956bdc6b43f2ab20d87d98505a76dfe5ddc0b1740a0703d4e75bddca5d42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:25.599713Z","signature_b64":"DPKzQV0ZcbrBtPBM3izcl8wFP0Gmz8Dl4BrO0JwyQpAh52sLlWxbTIbuXGCAEYu2xiI1PMBEvCoFIPPZC+o/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aaa956bdc6b43f2ab20d87d98505a76dfe5ddc0b1740a0703d4e75bddca5d42","last_reissued_at":"2026-07-05T04:40:25.599178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:25.599178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.00842","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3I+DxZbeRALCc/1FyAl5fCO8aojBdTH+JYyMzWLRCx9CunX8kf8a3N96WuPAQzbfDlps6Ci3HFTle/zrqTrRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:46:39.219916Z"},"content_sha256":"e27dbbb520cbf2f6096962f79ca40a8aafdb6c2a9e5c75a676892563d2b6baf0","schema_version":"1.0","event_id":"sha256:e27dbbb520cbf2f6096962f79ca40a8aafdb6c2a9e5c75a676892563d2b6baf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DKVJK264NNB7FKZA3B6ZQUC2O3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streaming Multi-Talker ASR with Token-Level Serialized Output Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Yu Wu, Zhong Meng, Zhuo Chen","submitted_at":"2022-02-02T01:27:21Z","abstract_excerpt":"This paper proposes a token-level serialized output training (t-SOT), a novel framework for streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi-talker ASR models using multiple output branches, the t-SOT model has only a single output branch that generates recognition tokens (e.g., words, subwords) of multiple speakers in chronological order based on their emission times. A special token that indicates the change of ``virtual'' output channels is introduced to keep track of the overlapping utterances. Compared to the prior streaming multi-talker ASR model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00842","kind":"arxiv","version":5},"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/2202.00842/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":"2026-07-05T04:40:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11/RPi0BDrsMh1QG+5K7xqpP95V1DsBc2K6eNmRfhbg1IITbl/jD7sCY/eUM62EXXj+EPikh+fG1BxURz/HiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:46:39.220423Z"},"content_sha256":"41f82cfae6d858409e4e300a2ecd06a589a9b9d4851a49250d3f66f1eaee1f1f","schema_version":"1.0","event_id":"sha256:41f82cfae6d858409e4e300a2ecd06a589a9b9d4851a49250d3f66f1eaee1f1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/bundle.json","state_url":"https://pith.science/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/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":"2026-08-19T02:46:39Z","links":{"resolver":"https://pith.science/pith/DKVJK264NNB7FKZA3B6ZQUC2O3","bundle":"https://pith.science/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/bundle.json","state":"https://pith.science/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKVJK264NNB7FKZA3B6ZQUC2O3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DKVJK264NNB7FKZA3B6ZQUC2O3","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":"eb71e3713ca4f595b6074a0c5e47bc2bcb16b5a297fb28bf06a39bdf22cc663a","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-02T01:27:21Z","title_canon_sha256":"3b1163da2f2ff11a6c36f53be4280c51a38fbf0ae055bc0ba3733f2522861b44"},"schema_version":"1.0","source":{"id":"2202.00842","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00842","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00842v5","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00842","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_12","alias_value":"DKVJK264NNB7","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_16","alias_value":"DKVJK264NNB7FKZA","created_at":"2026-07-05T04:40:25Z"},{"alias_kind":"pith_short_8","alias_value":"DKVJK264","created_at":"2026-07-05T04:40:25Z"}],"graph_snapshots":[{"event_id":"sha256:41f82cfae6d858409e4e300a2ecd06a589a9b9d4851a49250d3f66f1eaee1f1f","target":"graph","created_at":"2026-07-05T04:40:25Z","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/2202.00842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a token-level serialized output training (t-SOT), a novel framework for streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi-talker ASR models using multiple output branches, the t-SOT model has only a single output branch that generates recognition tokens (e.g., words, subwords) of multiple speakers in chronological order based on their emission times. A special token that indicates the change of ``virtual'' output channels is introduced to keep track of the overlapping utterances. Compared to the prior streaming multi-talker ASR model","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Yu Wu, Zhong Meng, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-02T01:27:21Z","title":"Streaming Multi-Talker ASR with Token-Level Serialized Output Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00842","kind":"arxiv","version":5},"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:e27dbbb520cbf2f6096962f79ca40a8aafdb6c2a9e5c75a676892563d2b6baf0","target":"record","created_at":"2026-07-05T04:40:25Z","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":"eb71e3713ca4f595b6074a0c5e47bc2bcb16b5a297fb28bf06a39bdf22cc663a","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-02T01:27:21Z","title_canon_sha256":"3b1163da2f2ff11a6c36f53be4280c51a38fbf0ae055bc0ba3733f2522861b44"},"schema_version":"1.0","source":{"id":"2202.00842","kind":"arxiv","version":5}},"canonical_sha256":"1aaa956bdc6b43f2ab20d87d98505a76dfe5ddc0b1740a0703d4e75bddca5d42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aaa956bdc6b43f2ab20d87d98505a76dfe5ddc0b1740a0703d4e75bddca5d42","first_computed_at":"2026-07-05T04:40:25.599178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:25.599178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DPKzQV0ZcbrBtPBM3izcl8wFP0Gmz8Dl4BrO0JwyQpAh52sLlWxbTIbuXGCAEYu2xiI1PMBEvCoFIPPZC+o/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:25.599713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00842","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e27dbbb520cbf2f6096962f79ca40a8aafdb6c2a9e5c75a676892563d2b6baf0","sha256:41f82cfae6d858409e4e300a2ecd06a589a9b9d4851a49250d3f66f1eaee1f1f"],"state_sha256":"77061ceab03d7575ac194f747b93f7b8d9b131e08f09ec182563f51fea299159"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7EMeOr7wZp8r3u2N8mmjOWSgebRC+VtDmIAopK51UvJBkEKwhjUxXU2lTnwKZi3a1Lh9M0tVymu8RsCWa91UDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:46:39.225439Z","bundle_sha256":"c593216221940064f4a3a690cd7119d079aa2466831a54a18e950e02b30f9ba0"}}