{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IX7VAFWQOQXFFDZ55M6NSUDZC5","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":"8518df9b0f36d2195ba33c340dcd502616ed277b85834aa8d2bb18864f79371d","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:06:29Z","title_canon_sha256":"4f0cae829d7fdbbb7100ab55a8690c1ff11ae277229df2f4cbc7d606314774a7"},"schema_version":"1.0","source":{"id":"2401.18045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.18045","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.18045v1","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18045","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"IX7VAFWQOQXF","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"IX7VAFWQOQXFFDZ5","created_at":"2026-07-05T07:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"IX7VAFWQ","created_at":"2026-07-05T07:39:46Z"}],"graph_snapshots":[{"event_id":"sha256:ca906860bde6850a72f3ee103dc60964e0fd51bc288518fb260d8ae7027b830c","target":"graph","created_at":"2026-07-05T07:39:46Z","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/2401.18045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in language models have significantly enhanced performance in multiple speech-related tasks. Existing speech language models typically utilize task-dependent prompt tokens to unify various speech tasks in a single model. However, this design omits the intrinsic connections between different speech tasks, which can potentially boost the performance of each task. In this work, we propose a novel decoder-only speech language model, SpeechComposer, that can unify common speech tasks by composing a fixed set of prompt tokens. Built upon four primary tasks -- speech synthesis, sp","authors_text":"Chenda Li, Ruihua Song, Shinji Watanabe, Soumi Maiti, Wangyou Zhang, Xihua Wang, Yifan Peng, Yihan Wu, Yuyue Wang","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:06:29Z","title":"SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.18045","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":"sha256:5b71945b6aca094a2949c20c4014f0349d0b2d4f3bd0dc6d00ffbf06765c5dc5","target":"record","created_at":"2026-07-05T07:39:46Z","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":"8518df9b0f36d2195ba33c340dcd502616ed277b85834aa8d2bb18864f79371d","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:06:29Z","title_canon_sha256":"4f0cae829d7fdbbb7100ab55a8690c1ff11ae277229df2f4cbc7d606314774a7"},"schema_version":"1.0","source":{"id":"2401.18045","kind":"arxiv","version":1}},"canonical_sha256":"45ff5016d0742e528f3deb3cd950791776f2b91ccae5031c0f4a7bc1d155bc7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45ff5016d0742e528f3deb3cd950791776f2b91ccae5031c0f4a7bc1d155bc7c","first_computed_at":"2026-07-05T07:39:46.170082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:46.170082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pf1W9D9tAXBOD6PYob992FvH8Mty7cv4rEFpa/EDn4zPf/lZm/8EamliU7WGGt03dajXqDu7M5HWufVqkHUqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:46.170484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.18045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b71945b6aca094a2949c20c4014f0349d0b2d4f3bd0dc6d00ffbf06765c5dc5","sha256:ca906860bde6850a72f3ee103dc60964e0fd51bc288518fb260d8ae7027b830c"],"state_sha256":"2496d01ac47e76011cc10f249b0e673b2c209a53a547728fdbfcf0da3567456d"}