{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:A6LOHBD32VF3JCDDCKOZ6STMGV","short_pith_number":"pith:A6LOHBD3","canonical_record":{"source":{"id":"2101.01853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-06T03:36:09Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"a68507f4edb0e93ce7fd492b6d91419413ad5e242d7792bab15eb80d4d4a0e05","abstract_canon_sha256":"f6548ec96b0686ff56e9462543a8874b6ebbb042f5f2551468f041feea0f8e8a"},"schema_version":"1.0"},"canonical_sha256":"0796e3847bd54bb48863129d9f4a6c355b082f84b870ca71a63662218ddddf7a","source":{"kind":"arxiv","id":"2101.01853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01853","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01853v1","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01853","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"A6LOHBD32VF3","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"A6LOHBD32VF3JCDD","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"A6LOHBD3","created_at":"2026-07-05T02:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:A6LOHBD32VF3JCDDCKOZ6STMGV","target":"record","payload":{"canonical_record":{"source":{"id":"2101.01853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-06T03:36:09Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"a68507f4edb0e93ce7fd492b6d91419413ad5e242d7792bab15eb80d4d4a0e05","abstract_canon_sha256":"f6548ec96b0686ff56e9462543a8874b6ebbb042f5f2551468f041feea0f8e8a"},"schema_version":"1.0"},"canonical_sha256":"0796e3847bd54bb48863129d9f4a6c355b082f84b870ca71a63662218ddddf7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:00.834167Z","signature_b64":"2hGrX8QXOnmATdN/uAHHUmloLGdutOo96AkIcAbrusdyRHOpNL5cLPWCpe9j9iYAmZfVtcYTo1mOIAzuvephBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0796e3847bd54bb48863129d9f4a6c355b082f84b870ca71a63662218ddddf7a","last_reissued_at":"2026-07-05T02:05:00.833817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:00.833817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.01853","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":"2026-07-05T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDXa3EnoPirF2csT7hIPeqTx9NvW3DwM03l7ns+vG/BXZyTx3/WGZUcu+Rfn07940p//6rh6d0KMTeRCvbYRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:02:47.572348Z"},"content_sha256":"32498695f454b498373d8dff1c93e1f8f80b60be7aabe543c6e146a54b9013c9","schema_version":"1.0","event_id":"sha256:32498695f454b498373d8dff1c93e1f8f80b60be7aabe543c6e146a54b9013c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:A6LOHBD32VF3JCDDCKOZ6STMGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xuankai Chang, Yashesh Gaur, Zhong Meng","submitted_at":"2021-01-06T03:36:09Z","abstract_excerpt":"An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed recently to jointly perform speaker counting, speech recognition and speaker identification. The model achieved a low speaker-attributed word error rate (SA-WER) for monaural overlapped speech comprising an unknown number of speakers. However, the E2E modeling approach is susceptible to the mismatch between the training and testing conditions. It has yet to be investigated whether the E2E SA-ASR model works well for recordings that are much longer than samples seen during training. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01853","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/2101.01853/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":"2026-07-05T02:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mffz5MQGtBs/KeE8m9LyLd2SyUpqUibCkP0WlOofbdsTlYbcqEGoc30yhmZtjYhOoUuuq5sW/3U32qP2cRRiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:02:47.572898Z"},"content_sha256":"9275438847f9543b1c996177f121e7cfb5217f68593fd9fba37504de27f52d3f","schema_version":"1.0","event_id":"sha256:9275438847f9543b1c996177f121e7cfb5217f68593fd9fba37504de27f52d3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/bundle.json","state_url":"https://pith.science/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/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":"2026-08-04T08:02:47Z","links":{"resolver":"https://pith.science/pith/A6LOHBD32VF3JCDDCKOZ6STMGV","bundle":"https://pith.science/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/bundle.json","state":"https://pith.science/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6LOHBD32VF3JCDDCKOZ6STMGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:A6LOHBD32VF3JCDDCKOZ6STMGV","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":"f6548ec96b0686ff56e9462543a8874b6ebbb042f5f2551468f041feea0f8e8a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-06T03:36:09Z","title_canon_sha256":"a68507f4edb0e93ce7fd492b6d91419413ad5e242d7792bab15eb80d4d4a0e05"},"schema_version":"1.0","source":{"id":"2101.01853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01853","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01853v1","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01853","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"A6LOHBD32VF3","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"A6LOHBD32VF3JCDD","created_at":"2026-07-05T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"A6LOHBD3","created_at":"2026-07-05T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:9275438847f9543b1c996177f121e7cfb5217f68593fd9fba37504de27f52d3f","target":"graph","created_at":"2026-07-05T02:05:00Z","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/2101.01853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed recently to jointly perform speaker counting, speech recognition and speaker identification. The model achieved a low speaker-attributed word error rate (SA-WER) for monaural overlapped speech comprising an unknown number of speakers. However, the E2E modeling approach is susceptible to the mismatch between the training and testing conditions. It has yet to be investigated whether the E2E SA-ASR model works well for recordings that are much longer than samples seen during training. In this work, we ","authors_text":"Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xuankai Chang, Yashesh Gaur, Zhong Meng","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-06T03:36:09Z","title":"Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01853","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":"sha256:32498695f454b498373d8dff1c93e1f8f80b60be7aabe543c6e146a54b9013c9","target":"record","created_at":"2026-07-05T02:05:00Z","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":"f6548ec96b0686ff56e9462543a8874b6ebbb042f5f2551468f041feea0f8e8a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-06T03:36:09Z","title_canon_sha256":"a68507f4edb0e93ce7fd492b6d91419413ad5e242d7792bab15eb80d4d4a0e05"},"schema_version":"1.0","source":{"id":"2101.01853","kind":"arxiv","version":1}},"canonical_sha256":"0796e3847bd54bb48863129d9f4a6c355b082f84b870ca71a63662218ddddf7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0796e3847bd54bb48863129d9f4a6c355b082f84b870ca71a63662218ddddf7a","first_computed_at":"2026-07-05T02:05:00.833817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:05:00.833817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hGrX8QXOnmATdN/uAHHUmloLGdutOo96AkIcAbrusdyRHOpNL5cLPWCpe9j9iYAmZfVtcYTo1mOIAzuvephBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:05:00.834167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.01853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32498695f454b498373d8dff1c93e1f8f80b60be7aabe543c6e146a54b9013c9","sha256:9275438847f9543b1c996177f121e7cfb5217f68593fd9fba37504de27f52d3f"],"state_sha256":"70fae89b6bf01e6540c74d2817c94264a2ae5944f76f31945b377fbc09c6b5db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GlIWz6ZEXynOll6WVHZHoILrO2mJO17JwKEpY+irEL+lGbrQ5KqEBBeGxQXTwY4ivYuMqV02jdG53OQ4ZKSuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:02:47.577637Z","bundle_sha256":"7ed2d08cd92aa91447bc15483f27ef0ea8a3cc841ca5780df2a429f6fe537b52"}}