{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SHLGX3FTFKVSJEXXS6MNUCIYAA","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":"e4801a1c9e65c99407f91a8aa8e8feb26f053f162d628e8b06feddfc0d9f0e9a","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T14:36:02Z","title_canon_sha256":"bb122c57ffa4af34defa9ffb07c86393b759996de27359250ba428aa970c257e"},"schema_version":"1.0","source":{"id":"2407.03966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03966","created_at":"2026-07-05T08:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03966v1","created_at":"2026-07-05T08:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03966","created_at":"2026-07-05T08:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"SHLGX3FTFKVS","created_at":"2026-07-05T08:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"SHLGX3FTFKVSJEXX","created_at":"2026-07-05T08:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"SHLGX3FT","created_at":"2026-07-05T08:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:d68de5355f600cbb4bd84ecd18247598828c8508e2c5dd5fef9bbcab18bec128","target":"graph","created_at":"2026-07-05T08:40:26Z","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/2407.03966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods have relied on either the Permutation Invariant Training (PIT) or the time-based First-In-First-Out (FIFO) rule. This study presents a model-based serialization strategy that incorporates an auxiliary module into the Attention Encoder-Decoder architecture, autonomously identifying the crucial factors to order the output sequence of the speech components in mult","authors_text":"Dong Wang, Jiqing Han, Lantian Li, Shi Yin, Ying Shi","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T14:36:02Z","title":"Serialized Output Training by Learned Dominance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03966","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":"sha256:5de6eea95e8f3e8d5b6ad2fe529bb53d0021b2fcf0496fe43a947b44b1e1704a","target":"record","created_at":"2026-07-05T08:40:26Z","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":"e4801a1c9e65c99407f91a8aa8e8feb26f053f162d628e8b06feddfc0d9f0e9a","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T14:36:02Z","title_canon_sha256":"bb122c57ffa4af34defa9ffb07c86393b759996de27359250ba428aa970c257e"},"schema_version":"1.0","source":{"id":"2407.03966","kind":"arxiv","version":1}},"canonical_sha256":"91d66becb32aab2492f79798da0918000413fd96fd046fe887a1fe43a434ae67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91d66becb32aab2492f79798da0918000413fd96fd046fe887a1fe43a434ae67","first_computed_at":"2026-07-05T08:40:26.917831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:26.917831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n6SKIvPfbX5gh/A9LEo/AUlf7270TQem1qD3aFGBmVBuxI1J06omod3XWgoZYd0RUt3dlVo2c7GIdYIj0gDQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:26.918293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5de6eea95e8f3e8d5b6ad2fe529bb53d0021b2fcf0496fe43a947b44b1e1704a","sha256:d68de5355f600cbb4bd84ecd18247598828c8508e2c5dd5fef9bbcab18bec128"],"state_sha256":"27640f02ccb586c9f18c84d74aadc358563279d0651be68b89e2dcbf6e36cc11"}