{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BU6RVUNLHKM7WWLMVVULLRLWRJ","short_pith_number":"pith:BU6RVUNL","schema_version":"1.0","canonical_sha256":"0d3d1ad1ab3a99fb596cad68b5c5768a690a134ef1465124edd2e6bab3e62907","source":{"kind":"arxiv","id":"2603.10468","version":2},"attestation_state":"computed","paper":{"title":"G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dezhu Xu, Duo Ma, Haoyu Li, Jing Peng, Kai Yu, Mengtian Li, Shuai Wang, Yucheng Wang, Yunfan Du, Ziyi Chen","submitted_at":"2026-03-11T06:40:01Z","abstract_excerpt":"We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM tr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.10468","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T06:40:01Z","cross_cats_sorted":["cs.AI","cs.HC","cs.MM","cs.SD"],"title_canon_sha256":"4a53e70c27a1b0e023b22b6a7ebef8f9508fe24fb7b720e474f6965660070756","abstract_canon_sha256":"1f816163994e45a3c3ce8edf0cbf542a83abc95d6d8793c1ccd49f0b913eafd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:37.118501Z","signature_b64":"6G5DHatrpdxhtoizc1dxHgEAJfzouVi9VpUg5/Iu2SX3Hn2WG7bhMg7XSktCgnN5q2JKy/IrGzaulJ9bEzXeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d3d1ad1ab3a99fb596cad68b5c5768a690a134ef1465124edd2e6bab3e62907","last_reissued_at":"2026-06-01T02:03:37.117375Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:37.117375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G-STAR: End-to-End Global Speaker-Tracking Attributed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dezhu Xu, Duo Ma, Haoyu Li, Jing Peng, Kai Yu, Mengtian Li, Shuai Wang, Yucheng Wang, Yunfan Du, Ziyi Chen","submitted_at":"2026-03-11T06:40:01Z","abstract_excerpt":"We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.10468","kind":"arxiv","version":2},"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/2603.10468/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.10468","created_at":"2026-06-01T02:03:37.117515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.10468v2","created_at":"2026-06-01T02:03:37.117515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.10468","created_at":"2026-06-01T02:03:37.117515+00:00"},{"alias_kind":"pith_short_12","alias_value":"BU6RVUNLHKM7","created_at":"2026-06-01T02:03:37.117515+00:00"},{"alias_kind":"pith_short_16","alias_value":"BU6RVUNLHKM7WWLM","created_at":"2026-06-01T02:03:37.117515+00:00"},{"alias_kind":"pith_short_8","alias_value":"BU6RVUNL","created_at":"2026-06-01T02:03:37.117515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ","json":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ.json","graph_json":"https://pith.science/api/pith-number/BU6RVUNLHKM7WWLMVVULLRLWRJ/graph.json","events_json":"https://pith.science/api/pith-number/BU6RVUNLHKM7WWLMVVULLRLWRJ/events.json","paper":"https://pith.science/paper/BU6RVUNL"},"agent_actions":{"view_html":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ","download_json":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ.json","view_paper":"https://pith.science/paper/BU6RVUNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.10468&json=true","fetch_graph":"https://pith.science/api/pith-number/BU6RVUNLHKM7WWLMVVULLRLWRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BU6RVUNLHKM7WWLMVVULLRLWRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ/action/storage_attestation","attest_author":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ/action/author_attestation","sign_citation":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ/action/citation_signature","submit_replication":"https://pith.science/pith/BU6RVUNLHKM7WWLMVVULLRLWRJ/action/replication_record"}},"created_at":"2026-06-01T02:03:37.117515+00:00","updated_at":"2026-06-01T02:03:37.117515+00:00"}