{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MZT7IWN2IIIGFH35B22JMJY75W","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":"077f332ddf10d462311afe7366cf7b17e6a09338244b5a879a33e9680db81b51","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-10T17:20:11Z","title_canon_sha256":"9b475f10bc232536baf43771956d078041568cb8b12d05bbc786238d2ef8f873"},"schema_version":"1.0","source":{"id":"2409.06656","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06656","created_at":"2026-07-05T11:39:43Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06656v3","created_at":"2026-07-05T11:39:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06656","created_at":"2026-07-05T11:39:43Z"},{"alias_kind":"pith_short_12","alias_value":"MZT7IWN2IIIG","created_at":"2026-07-05T11:39:43Z"},{"alias_kind":"pith_short_16","alias_value":"MZT7IWN2IIIGFH35","created_at":"2026-07-05T11:39:43Z"},{"alias_kind":"pith_short_8","alias_value":"MZT7IWN2","created_at":"2026-07-05T11:39:43Z"}],"graph_snapshots":[{"event_id":"sha256:102d8d17518cf6994569993543fcddf62cc6ad702d55de69c2083734bea2d98e","target":"graph","created_at":"2026-07-05T11:39:43Z","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/2409.06656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss (PIL), Sortformer introduces Sort Loss to resolve the permutation problem, either independently or in tandem with PIL. In addition, we propose a streamlined multi-speaker speech-to-text architecture that leverages Sortformer for speaker supervision, embedding speaker labels into the encoder using sinusoidal kernel functions. This design addresses the speaker permutation problem through sorted objectives, effectively ","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Nithin Rao Koluguri, Taejin Park, Weiqing Wang","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-10T17:20:11Z","title":"Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06656","kind":"arxiv","version":3},"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":"sha256:23cc0c4ef4e494d6eec8d2d04b1a834aaac00cbdda2e5318be8089a189615a38","target":"record","created_at":"2026-07-05T11:39:43Z","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":"077f332ddf10d462311afe7366cf7b17e6a09338244b5a879a33e9680db81b51","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-10T17:20:11Z","title_canon_sha256":"9b475f10bc232536baf43771956d078041568cb8b12d05bbc786238d2ef8f873"},"schema_version":"1.0","source":{"id":"2409.06656","kind":"arxiv","version":3}},"canonical_sha256":"6667f459ba4210629f7d0eb496271fedbee3d82175b47dc1b78dc76a9a44ce17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6667f459ba4210629f7d0eb496271fedbee3d82175b47dc1b78dc76a9a44ce17","first_computed_at":"2026-07-05T11:39:43.244141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:43.244141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H+WQi3FTkrBVbG8JBlndR4tYAaCZq6IkrTApz1ICWrZBrKShPwf+Ta8hRKcQPHU4HLF53Nath+0rYmK/ym/vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:43.244863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06656","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23cc0c4ef4e494d6eec8d2d04b1a834aaac00cbdda2e5318be8089a189615a38","sha256:102d8d17518cf6994569993543fcddf62cc6ad702d55de69c2083734bea2d98e"],"state_sha256":"137e5991005eaf0de20e89dc2809a120730516c6e986010fd8d0174a50fcdf8f"}