{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EPUN7MMZ3QQ5VLN3ATEBZKVWT7","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":"d7001cbbabbb1f990f45a5cf5cefdf134feac67c16aab32965080d8312d62d2b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-24T15:36:08Z","title_canon_sha256":"ae1de13dafb47c1081d3e436b6f4e45bd66ea68d18953da18d235e2d3382f309"},"schema_version":"1.0","source":{"id":"2408.13608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13608","created_at":"2026-07-05T08:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13608v1","created_at":"2026-07-05T08:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13608","created_at":"2026-07-05T08:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"EPUN7MMZ3QQ5","created_at":"2026-07-05T08:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"EPUN7MMZ3QQ5VLN3","created_at":"2026-07-05T08:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"EPUN7MMZ","created_at":"2026-07-05T08:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:cbf2ae016b28c76c3511ea3fd923f050845297b2edfaa067b5a9767a96046862","target":"graph","created_at":"2026-07-05T08:59:53Z","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/2408.13608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expre","authors_text":"Jia Jia, Kehan Li, Qixin Wang, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, Zeyu Jin, Zhiyong Wu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-24T15:36:08Z","title":"SpeechCraft: A Fine-grained Expressive Speech Dataset with Natural Language Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13608","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":"sha256:6a72356d0edc9a33eb8aa8d71d3b1608790b9409b58c52547dde8899caa00a06","target":"record","created_at":"2026-07-05T08:59:53Z","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":"d7001cbbabbb1f990f45a5cf5cefdf134feac67c16aab32965080d8312d62d2b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-24T15:36:08Z","title_canon_sha256":"ae1de13dafb47c1081d3e436b6f4e45bd66ea68d18953da18d235e2d3382f309"},"schema_version":"1.0","source":{"id":"2408.13608","kind":"arxiv","version":1}},"canonical_sha256":"23e8dfb199dc21daadbb04c81caab69fc771406e24a90ad115e3ba099ccf814b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e8dfb199dc21daadbb04c81caab69fc771406e24a90ad115e3ba099ccf814b","first_computed_at":"2026-07-05T08:59:53.640736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:53.640736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4M36YDMIh838kpljc7vN6rR6GdmPBrgTJRrWiakc0TPr6FqvMUbv1xqp7dEz5pTqHKeWBhuTDPuUZDwjvmJlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:53.641194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a72356d0edc9a33eb8aa8d71d3b1608790b9409b58c52547dde8899caa00a06","sha256:cbf2ae016b28c76c3511ea3fd923f050845297b2edfaa067b5a9767a96046862"],"state_sha256":"334783cb4a4b0ebf75d8fe3b8c149fb155cb4916a2460ef783121334e81cfa02"}