{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LMDLX7JBSP3SIRNQNO3BFAQ6I5","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":"1f1840a9515157c0e42f43bad1aafbdbc32bc4a46ef0251786506c4848f82590","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-07T16:07:42Z","title_canon_sha256":"142897aa1fb43df72f9717a3bbbd7e7d510b9104c740da6f7c656e60cfa6c04e"},"schema_version":"1.0","source":{"id":"2310.04863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04863","created_at":"2026-07-05T06:58:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04863v1","created_at":"2026-07-05T06:58:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04863","created_at":"2026-07-05T06:58:23Z"},{"alias_kind":"pith_short_12","alias_value":"LMDLX7JBSP3S","created_at":"2026-07-05T06:58:23Z"},{"alias_kind":"pith_short_16","alias_value":"LMDLX7JBSP3SIRNQ","created_at":"2026-07-05T06:58:23Z"},{"alias_kind":"pith_short_8","alias_value":"LMDLX7JB","created_at":"2026-07-05T06:58:23Z"}],"graph_snapshots":[{"event_id":"sha256:1f646dd5d4de9d4609c6d24c1077c007bdffed96e7ff35498fdf99d882f61f7e","target":"graph","created_at":"2026-07-05T06:58:23Z","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/2310.04863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR).Although being able to obtain state-of-the-art (SOTA) performance, most of the studies are based on an autoregressive (AR) decoder which generates tokens one-by-one and results in a large real-time factor (RTF). To speed up inference, we introduce a recently proposed non-autoregressive model Paraformer as an acoustic model in the SA-ASR model.Paraformer uses a single-step decoder to enable parallel generation, obtaining comparable performa","authors_text":"Fan Yu, Lei Xie, Mohan Shi, Pengcheng Guo, Shiliang Zhang, Yangze Li, Yuhao Liang, Zhihao Du","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-07T16:07:42Z","title":"SA-Paraformer: Non-autoregressive End-to-End Speaker-Attributed ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04863","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":"sha256:1d187b8b32bab013914bbecbec9d3203a121eb17e3c81c7ba9e9fc2ea38c950b","target":"record","created_at":"2026-07-05T06:58:23Z","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":"1f1840a9515157c0e42f43bad1aafbdbc32bc4a46ef0251786506c4848f82590","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-07T16:07:42Z","title_canon_sha256":"142897aa1fb43df72f9717a3bbbd7e7d510b9104c740da6f7c656e60cfa6c04e"},"schema_version":"1.0","source":{"id":"2310.04863","kind":"arxiv","version":1}},"canonical_sha256":"5b06bbfd2193f72445b06bb612821e4764aecd7afbf7022b89e0bffc8f57e91d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b06bbfd2193f72445b06bb612821e4764aecd7afbf7022b89e0bffc8f57e91d","first_computed_at":"2026-07-05T06:58:23.890209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:23.890209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oVLDmbbXvJFeEPhk+d3Eib7HZkDRZSV506h/Ue54cCHj2jOshoTi7ohihQpl3AeWPkSgMSe4HnNxAryRkr57Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:23.890569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d187b8b32bab013914bbecbec9d3203a121eb17e3c81c7ba9e9fc2ea38c950b","sha256:1f646dd5d4de9d4609c6d24c1077c007bdffed96e7ff35498fdf99d882f61f7e"],"state_sha256":"3e3c5009f4aa70fa203a5c27d203a98006a9e40467a28952b5790abece844988"}