{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EMZQQNABLABTEPQZFHZEONJIHC","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":"5bb76870f5163e4d7cf66f52fec6e0aedd9af8deb8a7ca2516010a39d55a3300","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T12:32:08Z","title_canon_sha256":"2d22d2b199f1c68c7a9de543a050fdaa003dc0d13fe46488361ccee956d1fbe5"},"schema_version":"1.0","source":{"id":"2405.19041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19041","created_at":"2026-07-05T08:24:47Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19041v1","created_at":"2026-07-05T08:24:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19041","created_at":"2026-07-05T08:24:47Z"},{"alias_kind":"pith_short_12","alias_value":"EMZQQNABLABT","created_at":"2026-07-05T08:24:47Z"},{"alias_kind":"pith_short_16","alias_value":"EMZQQNABLABTEPQZ","created_at":"2026-07-05T08:24:47Z"},{"alias_kind":"pith_short_8","alias_value":"EMZQQNAB","created_at":"2026-07-05T08:24:47Z"}],"graph_snapshots":[{"event_id":"sha256:f562bb523e6c8b5905897928b8f9b6abd9a58a38444e08a7ce998a34e0241ea0","target":"graph","created_at":"2026-07-05T08:24:47Z","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/2405.19041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent end-to-end approaches have shown promise in extending large language models (LLMs) to speech inputs, but face limitations in directly assessing and optimizing alignment quality and fail to achieve fine-grained alignment due to speech-text length mismatch. We introduce BLSP-KD, a novel approach for Bootstrapping Language-Speech Pretraining via Knowledge Distillation, which addresses these limitations through two key techniques. First, it optimizes speech-text alignment by minimizing the divergence between the LLM's next-token prediction distributions for speech and text inputs using know","authors_text":"Chen Wang, Jiajun Zhang, Minpeng Liao, Zhongqiang Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T12:32:08Z","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19041","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":"sha256:7894b304fef5bc7cb019f56fdc2288e999a3c57cdfb733f7cc82a5416005f6b4","target":"record","created_at":"2026-07-05T08:24:47Z","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":"5bb76870f5163e4d7cf66f52fec6e0aedd9af8deb8a7ca2516010a39d55a3300","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T12:32:08Z","title_canon_sha256":"2d22d2b199f1c68c7a9de543a050fdaa003dc0d13fe46488361ccee956d1fbe5"},"schema_version":"1.0","source":{"id":"2405.19041","kind":"arxiv","version":1}},"canonical_sha256":"23330834015803323e1929f2473528388e07769e7c1543ee2f21992c5f0f4e26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23330834015803323e1929f2473528388e07769e7c1543ee2f21992c5f0f4e26","first_computed_at":"2026-07-05T08:24:47.078368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:47.078368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ruTwYRnHtIS1d0Uv1n//aObNeQ8mCrBVHo8BP31WkcuqCkzXPP5ygYA+pj+/6LbUfpdNv4HXXbjv2NV8RXvSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:47.078862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7894b304fef5bc7cb019f56fdc2288e999a3c57cdfb733f7cc82a5416005f6b4","sha256:f562bb523e6c8b5905897928b8f9b6abd9a58a38444e08a7ce998a34e0241ea0"],"state_sha256":"5741538bd2f3edb0d3a434a083090a112bd311756e59cef1a08acb09de1ea266"}