{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FY43KKPKEIHXIS5MOVDBB27XR4","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":"e8f08a92a6bf084c93fac54cc0a0e2f227905972cd58607088de381881a911e4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:32:19Z","title_canon_sha256":"e50fb401c2b473af989ad9f203afb90e63899a0b069e2e75c73767faa2bca70c"},"schema_version":"1.0","source":{"id":"2305.12459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12459","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12459v1","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12459","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_12","alias_value":"FY43KKPKEIHX","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_16","alias_value":"FY43KKPKEIHXIS5M","created_at":"2026-07-05T06:12:10Z"},{"alias_kind":"pith_short_8","alias_value":"FY43KKPK","created_at":"2026-07-05T06:12:10Z"}],"graph_snapshots":[{"event_id":"sha256:9b67159ba08733dc09981dd33a8b8cb6bc6726be14f488c0e3d69f7398c583c1","target":"graph","created_at":"2026-07-05T06:12:10Z","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/2305.12459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is empl","authors_text":"Fan Yu, Jie Zhang, Li-Rong Dai, Mohan Shi, Qian Chen, Shiliang Zhang, Yangze Li, Zhihao Du","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:32:19Z","title":"CASA-ASR: Context-Aware Speaker-Attributed ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12459","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":"sha256:5e10651f71167b8e9c14630deb2e6b5ff482772fb5889557b0a02f44f9faf4df","target":"record","created_at":"2026-07-05T06:12:10Z","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":"e8f08a92a6bf084c93fac54cc0a0e2f227905972cd58607088de381881a911e4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-21T13:32:19Z","title_canon_sha256":"e50fb401c2b473af989ad9f203afb90e63899a0b069e2e75c73767faa2bca70c"},"schema_version":"1.0","source":{"id":"2305.12459","kind":"arxiv","version":1}},"canonical_sha256":"2e39b529ea220f744bac754610ebf78f260814b33e5603cb738d90232d9af364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e39b529ea220f744bac754610ebf78f260814b33e5603cb738d90232d9af364","first_computed_at":"2026-07-05T06:12:10.895326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:10.895326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Np9YCQMkWFPrG36wlJRpdlCOLGjaEhhadGjsfnpC5Io+QZmB7ndcRBLkAMUZBY1LvWolLDjyLFBVNUI8EXfTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:10.895781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e10651f71167b8e9c14630deb2e6b5ff482772fb5889557b0a02f44f9faf4df","sha256:9b67159ba08733dc09981dd33a8b8cb6bc6726be14f488c0e3d69f7398c583c1"],"state_sha256":"34030a31ce245686aa1b2e9f3525daba2c63b939ed48e7a365c956585993e637"}