{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQBL4MZTGZFAXELRJ7ZUGQKJRN","short_pith_number":"pith:PQBL4MZT","canonical_record":{"source":{"id":"2409.00815","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T19:07:34Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"72d9d7e2a75509708d6ea71478648ec7089cbe32d03d8c5c8555b70a72921175","abstract_canon_sha256":"25557ef0a22576c24beaed98302a8ebacb62a793aa0340db68f34c8ee10ba67e"},"schema_version":"1.0"},"canonical_sha256":"7c02be3333364a0b91714ff34341498b708a336b6127d8304919b0e58f859a6f","source":{"kind":"arxiv","id":"2409.00815","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00815","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00815v3","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00815","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"PQBL4MZTGZFA","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"PQBL4MZTGZFAXELR","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"PQBL4MZT","created_at":"2026-07-05T09:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQBL4MZTGZFAXELRJ7ZUGQKJRN","target":"record","payload":{"canonical_record":{"source":{"id":"2409.00815","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T19:07:34Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"72d9d7e2a75509708d6ea71478648ec7089cbe32d03d8c5c8555b70a72921175","abstract_canon_sha256":"25557ef0a22576c24beaed98302a8ebacb62a793aa0340db68f34c8ee10ba67e"},"schema_version":"1.0"},"canonical_sha256":"7c02be3333364a0b91714ff34341498b708a336b6127d8304919b0e58f859a6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:38.833648Z","signature_b64":"rINlfVat0pxznK/wYtMWwfNsc8hHBCVSeU6CqDLhjL+uyKgVS+Yy3j32DHLXmjZ4ZJ/7AE2sf2Vu5OArpjmyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c02be3333364a0b91714ff34341498b708a336b6127d8304919b0e58f859a6f","last_reissued_at":"2026-07-05T09:05:38.833105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:38.833105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.00815","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DUea3N4W0zvm78YcDl01v5b3NqfVji4Y7/DVGqrJpjERu6c6+czEx0vBbcA4E/RqOdiwfZJogdxo0MCheSlmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:35:24.723741Z"},"content_sha256":"5471ee420b6b7c2faac12001699419a37c1263c7f75ada2d96c154119383bab7","schema_version":"1.0","event_id":"sha256:5471ee420b6b7c2faac12001699419a37c1263c7f75ada2d96c154119383bab7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQBL4MZTGZFAXELRJ7ZUGQKJRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao Shi, Tatsuya Kawahara, Yuan Gao, Zhaoheng Ni","submitted_at":"2024-09-01T19:07:34Z","abstract_excerpt":"Serialized output training (SOT) attracts increasing attention due to its convenience and flexibility for multi-speaker automatic speech recognition (ASR). However, it is not easy to train with attention loss only. In this paper, we propose the overlapped encoding separation (EncSep) to fully utilize the benefits of the connectionist temporal classification (CTC) and attention hybrid loss. This additional separator is inserted after the encoder to extract the multi-speaker information with CTC losses. Furthermore, we propose the serialized speech information guidance SOT (GEncSep) to further u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00815","kind":"arxiv","version":3},"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/2409.00815/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":"2026-07-05T09:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PlvHLNlPLAKwrLvX3v/0DiOEtfkmplnubCInJw4HP5xlhuK7qEahdU8pwrb6eStVDj6ggBAk+bTwnSNA1h63Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:35:24.724234Z"},"content_sha256":"40718375598bf78dc919e71ae537495083192eaddf7d46057afddbf6840a0c76","schema_version":"1.0","event_id":"sha256:40718375598bf78dc919e71ae537495083192eaddf7d46057afddbf6840a0c76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/bundle.json","state_url":"https://pith.science/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/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":"2026-08-15T22:35:24Z","links":{"resolver":"https://pith.science/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN","bundle":"https://pith.science/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/bundle.json","state":"https://pith.science/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQBL4MZTGZFAXELRJ7ZUGQKJRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQBL4MZTGZFAXELRJ7ZUGQKJRN","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":"25557ef0a22576c24beaed98302a8ebacb62a793aa0340db68f34c8ee10ba67e","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T19:07:34Z","title_canon_sha256":"72d9d7e2a75509708d6ea71478648ec7089cbe32d03d8c5c8555b70a72921175"},"schema_version":"1.0","source":{"id":"2409.00815","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00815","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00815v3","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00815","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"PQBL4MZTGZFA","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"PQBL4MZTGZFAXELR","created_at":"2026-07-05T09:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"PQBL4MZT","created_at":"2026-07-05T09:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:40718375598bf78dc919e71ae537495083192eaddf7d46057afddbf6840a0c76","target":"graph","created_at":"2026-07-05T09:05:38Z","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/2409.00815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Serialized output training (SOT) attracts increasing attention due to its convenience and flexibility for multi-speaker automatic speech recognition (ASR). However, it is not easy to train with attention loss only. In this paper, we propose the overlapped encoding separation (EncSep) to fully utilize the benefits of the connectionist temporal classification (CTC) and attention hybrid loss. This additional separator is inserted after the encoder to extract the multi-speaker information with CTC losses. Furthermore, we propose the serialized speech information guidance SOT (GEncSep) to further u","authors_text":"Hao Shi, Tatsuya Kawahara, Yuan Gao, Zhaoheng Ni","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T19:07:34Z","title":"Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00815","kind":"arxiv","version":3},"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":"sha256:5471ee420b6b7c2faac12001699419a37c1263c7f75ada2d96c154119383bab7","target":"record","created_at":"2026-07-05T09:05:38Z","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":"25557ef0a22576c24beaed98302a8ebacb62a793aa0340db68f34c8ee10ba67e","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-01T19:07:34Z","title_canon_sha256":"72d9d7e2a75509708d6ea71478648ec7089cbe32d03d8c5c8555b70a72921175"},"schema_version":"1.0","source":{"id":"2409.00815","kind":"arxiv","version":3}},"canonical_sha256":"7c02be3333364a0b91714ff34341498b708a336b6127d8304919b0e58f859a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c02be3333364a0b91714ff34341498b708a336b6127d8304919b0e58f859a6f","first_computed_at":"2026-07-05T09:05:38.833105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:38.833105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rINlfVat0pxznK/wYtMWwfNsc8hHBCVSeU6CqDLhjL+uyKgVS+Yy3j32DHLXmjZ4ZJ/7AE2sf2Vu5OArpjmyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:38.833648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00815","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5471ee420b6b7c2faac12001699419a37c1263c7f75ada2d96c154119383bab7","sha256:40718375598bf78dc919e71ae537495083192eaddf7d46057afddbf6840a0c76"],"state_sha256":"62657489e71560d856aa52f07bafa59189a4eba07aae057864fabdbfc8fa065b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WB9vwKW333cs6VkAzHIgp2rAIV+gOeJKYCBnscChl6jJ6j1sRxLZKoFLecwhtWBKXvuqwIksBHwKK2LzCNGkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:35:24.727733Z","bundle_sha256":"2dd7b2e929445fa9c59a382b688005a6edf8a202b7c02698b10a4208572e6846"}}