{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27UNDFL35K54OKRAWQFLM62RCS","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":"0bfb85baffb69941b38118eb88506b84d196f34b9a468a590109ec0874b99c52","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T17:19:09Z","title_canon_sha256":"4252cc0f0f2fe568e6fddf88038e729d9e0e2501a4583802c8b1a744fc02b809"},"schema_version":"1.0","source":{"id":"2411.17607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17607","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17607v2","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17607","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"27UNDFL35K54","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"27UNDFL35K54OKRA","created_at":"2026-07-05T09:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"27UNDFL3","created_at":"2026-07-05T09:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:316b0470c50d25bef1753489d2f23d021eee1a911d385606a979996669c7e796","target":"graph","created_at":"2026-07-05T09:43:12Z","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/2411.17607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are constrained by the limited availability of unsupervised speech data and parallel speech-text data, which are significantly less abundant than text pre-training data, thereby limiting their scalability as LLMs. We propose a novel approach to scaling speech-text pre-training by leveraging large-scale synthetic interleaved data derived from text corpora, elimin","authors_text":"Aohan Zeng, Jie Tang, Lei Zhang, Mingdao Liu, Shengmin Jiang, Yuxiao Dong, Zhengxiao Du","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T17:19:09Z","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17607","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":"sha256:257a8a8b448f57a04720641b03e46e70bc2a29caa099627d0787cc731f8c429d","target":"record","created_at":"2026-07-05T09:43:12Z","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":"0bfb85baffb69941b38118eb88506b84d196f34b9a468a590109ec0874b99c52","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-26T17:19:09Z","title_canon_sha256":"4252cc0f0f2fe568e6fddf88038e729d9e0e2501a4583802c8b1a744fc02b809"},"schema_version":"1.0","source":{"id":"2411.17607","kind":"arxiv","version":2}},"canonical_sha256":"d7e8d1957beabbc72a20b40ab67b5114be02422f1979f0939fb457876a1a1246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7e8d1957beabbc72a20b40ab67b5114be02422f1979f0939fb457876a1a1246","first_computed_at":"2026-07-05T09:43:12.019749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:12.019749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E8GtW6Qw6c044lUfH8zFRpys4I4yWoSSo8w/eHIuZC5pQhRw7PR+J+qXsPoxdGp7TnCuZUtu3lvuvx9O5A2ICg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:12.020295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257a8a8b448f57a04720641b03e46e70bc2a29caa099627d0787cc731f8c429d","sha256:316b0470c50d25bef1753489d2f23d021eee1a911d385606a979996669c7e796"],"state_sha256":"5ad08be012e8645348b63c0ea841bffbb213f82b1c62867ac290f1d819425fec"}