{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H6KP3FJ6PQZ6A2TBSSQGQRRBPR","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":"a86521001a4c463deb93eeffc693215d30322f325aa3a4b7414ad247717252cd","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-02T23:03:30Z","title_canon_sha256":"4ae5013c3c5b417b533f39fb5d399f76bb9c98d2ec4bc5b8bacdbde4c6201c0d"},"schema_version":"1.0","source":{"id":"2310.01688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01688","created_at":"2026-07-05T06:56:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01688v1","created_at":"2026-07-05T06:56:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01688","created_at":"2026-07-05T06:56:44Z"},{"alias_kind":"pith_short_12","alias_value":"H6KP3FJ6PQZ6","created_at":"2026-07-05T06:56:44Z"},{"alias_kind":"pith_short_16","alias_value":"H6KP3FJ6PQZ6A2TB","created_at":"2026-07-05T06:56:44Z"},{"alias_kind":"pith_short_8","alias_value":"H6KP3FJ6","created_at":"2026-07-05T06:56:44Z"}],"graph_snapshots":[{"event_id":"sha256:9091ab552f925bd68fe0c1043a6e19910bb72c1b156944618c4dd07faaffa795","target":"graph","created_at":"2026-07-05T06:56:44Z","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/2310.01688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel framework for joint speaker diarization (SD) and automatic speech recognition (ASR), named SLIDAR (sliding-window diarization-augmented recognition). SLIDAR can process arbitrary length inputs and can handle any number of speakers, effectively solving ``who spoke what, when'' concurrently. SLIDAR leverages a sliding window approach and consists of an end-to-end diarization-augmented speech transcription (E2E DAST) model which provides, locally, for each window: transcripts, diarization and speaker embeddings. The E2E DAST model is based on an encoder-decoder archite","authors_text":"Jee-weon Jung, Samuele Cornell, Shinji Watanabe, Stefano Squartini","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-02T23:03:30Z","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01688","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:a3a259277cb97be9d558ab616e0db880815d2c69ba5daee6c3281bf792f00e2e","target":"record","created_at":"2026-07-05T06:56:44Z","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":"a86521001a4c463deb93eeffc693215d30322f325aa3a4b7414ad247717252cd","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-10-02T23:03:30Z","title_canon_sha256":"4ae5013c3c5b417b533f39fb5d399f76bb9c98d2ec4bc5b8bacdbde4c6201c0d"},"schema_version":"1.0","source":{"id":"2310.01688","kind":"arxiv","version":1}},"canonical_sha256":"3f94fd953e7c33e06a6194a06846217c5187b92411d390a8a9c3436706a05b63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f94fd953e7c33e06a6194a06846217c5187b92411d390a8a9c3436706a05b63","first_computed_at":"2026-07-05T06:56:44.849363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:44.849363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p8sulc/P0HpP0picmUs0eyzx5KVPmsKdDo2IGllrbXZlLDcNmfrHc61Cdo3ONUYxHobVMkGi600EUmqnlDKNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:44.849823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3a259277cb97be9d558ab616e0db880815d2c69ba5daee6c3281bf792f00e2e","sha256:9091ab552f925bd68fe0c1043a6e19910bb72c1b156944618c4dd07faaffa795"],"state_sha256":"e94e0b837c7c8fcb6abe53c64ee38517841e733c76e54ea397d182840f4f45db"}