{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZILPTVETXM26JWBW67CQEXKFCR","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":"8200ddc5876126e0d9e5fe1dc3342bde8be18a7671ef3c6e453d4e53373a67ed","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-04T15:01:10Z","title_canon_sha256":"019a3059d60c39bc4b4bd1d4ddd737a3bdf8119da0600d2438738270419bf964"},"schema_version":"1.0","source":{"id":"2601.01554","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.01554","created_at":"2026-07-09T01:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"2601.01554v6","created_at":"2026-07-09T01:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.01554","created_at":"2026-07-09T01:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZILPTVETXM26","created_at":"2026-07-09T01:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZILPTVETXM26JWBW","created_at":"2026-07-09T01:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZILPTVET","created_at":"2026-07-09T01:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:b951564ac783f7a9831dc494c6433e54ac61bc387bb3469924aad71047aec397","target":"graph","created_at":"2026-07-09T01:19:50Z","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/2601.01554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained ","authors_text":"Chen Yang, Hanfu Chen, Jie Zhu, Jingqi Chen, Ke Chen, Liwei Fan, MOSI.AI: Donghua Yu, Muchen Li, Qinyuan Cheng, Shimin Li, Songlin Wang, Wenbo Zhang, Wenxuan Wang, Xipeng Qiu, Yang Wang, Yi Jiang, Yitian Gong, Yiyang Zhang, Yuqian Zhang, Zhaoye Fei, Zhengyuan Lin, Zhe Xu, Zhiyu Wu","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-04T15:01:10Z","title":"MOSS Transcribe Diarize Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.01554","kind":"arxiv","version":6},"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":"sha256:16b24a46d4c2fba0613c2224673f355933685aa43bfe0d238c5f128b97e6d419","target":"record","created_at":"2026-07-09T01:19:50Z","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":"8200ddc5876126e0d9e5fe1dc3342bde8be18a7671ef3c6e453d4e53373a67ed","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-01-04T15:01:10Z","title_canon_sha256":"019a3059d60c39bc4b4bd1d4ddd737a3bdf8119da0600d2438738270419bf964"},"schema_version":"1.0","source":{"id":"2601.01554","kind":"arxiv","version":6}},"canonical_sha256":"ca16f9d493bb35e4d836f7c5025d4514668087d45f9e9dc62778e7c791163698","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca16f9d493bb35e4d836f7c5025d4514668087d45f9e9dc62778e7c791163698","first_computed_at":"2026-07-09T01:19:50.317755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:19:50.317755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgn5hDcpA8okAUy5qjsdrWQytd6qUbm1+9mk2SxkjG3r62W/PA8KCqvqxNFc9F2btUZ/07wTpTgiKcOBWiGvAA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:19:50.318271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.01554","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16b24a46d4c2fba0613c2224673f355933685aa43bfe0d238c5f128b97e6d419","sha256:b951564ac783f7a9831dc494c6433e54ac61bc387bb3469924aad71047aec397"],"state_sha256":"b879d2c9d62ebe7cfcee02d5a37e83cada2f02a8687d6052f7dc117a76c9df4b"}