{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QCQ4DKS6ZGO5KTR6LMJ5E55ORQ","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":"6a975dfef87a4e9a492ca85ffa0bd4408493500cf98673b62953bf82d98493d9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T04:16:30Z","title_canon_sha256":"8829098d0d6393a9736092e08bac062df25df7e0d80e5a8fdabfb8be51ed234b"},"schema_version":"1.0","source":{"id":"2406.00976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00976","created_at":"2026-07-05T09:29:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00976v2","created_at":"2026-07-05T09:29:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00976","created_at":"2026-07-05T09:29:29Z"},{"alias_kind":"pith_short_12","alias_value":"QCQ4DKS6ZGO5","created_at":"2026-07-05T09:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"QCQ4DKS6ZGO5KTR6","created_at":"2026-07-05T09:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"QCQ4DKS6","created_at":"2026-07-05T09:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:e196a983e8675ed0f95582b32f837ffec85dd8b970443b65a79bed292ed7c7d8","target":"graph","created_at":"2026-07-05T09:29:29Z","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/2406.00976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce \\textbf{G}enerative \\textbf{P}re-trained \\textbf{S}peech \\textbf{T}ransformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi","authors_text":"Dan Su, Dong Yu, Linli Xu, Liqiang He, Yongxin Zhu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T04:16:30Z","title":"Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00976","kind":"arxiv","version":2},"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":"sha256:6ef023554344f8f8a459106b586c39a9e9c40e78721575b0a55e786efaa66737","target":"record","created_at":"2026-07-05T09:29:29Z","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":"6a975dfef87a4e9a492ca85ffa0bd4408493500cf98673b62953bf82d98493d9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T04:16:30Z","title_canon_sha256":"8829098d0d6393a9736092e08bac062df25df7e0d80e5a8fdabfb8be51ed234b"},"schema_version":"1.0","source":{"id":"2406.00976","kind":"arxiv","version":2}},"canonical_sha256":"80a1c1aa5ec99dd54e3e5b13d277ae8c102b2457431640355a041afaaf0eb64b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80a1c1aa5ec99dd54e3e5b13d277ae8c102b2457431640355a041afaaf0eb64b","first_computed_at":"2026-07-05T09:29:29.768669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:29.768669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z1itDp5lmaII4sWXn49oysxoOVaFxQXGPfOLidvtsiMAj7MdfWU2DMH5eoy0PK+GHNbH3WCGKxb/mXPPH+UUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:29.769160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ef023554344f8f8a459106b586c39a9e9c40e78721575b0a55e786efaa66737","sha256:e196a983e8675ed0f95582b32f837ffec85dd8b970443b65a79bed292ed7c7d8"],"state_sha256":"0acf9c54c982e8e9f11e21d5223176131f5ffc4398b030e5d10e1feae696a1e2"}