{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EMZQQNABLABTEPQZFHZEONJIHC","short_pith_number":"pith:EMZQQNAB","schema_version":"1.0","canonical_sha256":"23330834015803323e1929f2473528388e07769e7c1543ee2f21992c5f0f4e26","source":{"kind":"arxiv","id":"2405.19041","version":1},"attestation_state":"computed","paper":{"title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Wang, Jiajun Zhang, Minpeng Liao, Zhongqiang Huang","submitted_at":"2024-05-29T12:32:08Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.19041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T12:32:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2d22d2b199f1c68c7a9de543a050fdaa003dc0d13fe46488361ccee956d1fbe5","abstract_canon_sha256":"5bb76870f5163e4d7cf66f52fec6e0aedd9af8deb8a7ca2516010a39d55a3300"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:47.078862Z","signature_b64":"ruTwYRnHtIS1d0Uv1n//aObNeQ8mCrBVHo8BP31WkcuqCkzXPP5ygYA+pj+/6LbUfpdNv4HXXbjv2NV8RXvSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23330834015803323e1929f2473528388e07769e7c1543ee2f21992c5f0f4e26","last_reissued_at":"2026-07-05T08:24:47.078368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:47.078368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Wang, Jiajun Zhang, Minpeng Liao, Zhongqiang Huang","submitted_at":"2024-05-29T12:32:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19041","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.19041/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.19041","created_at":"2026-07-05T08:24:47.078430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19041v1","created_at":"2026-07-05T08:24:47.078430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19041","created_at":"2026-07-05T08:24:47.078430+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMZQQNABLABT","created_at":"2026-07-05T08:24:47.078430+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMZQQNABLABTEPQZ","created_at":"2026-07-05T08:24:47.078430+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMZQQNAB","created_at":"2026-07-05T08:24:47.078430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11033","citing_title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC","json":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC.json","graph_json":"https://pith.science/api/pith-number/EMZQQNABLABTEPQZFHZEONJIHC/graph.json","events_json":"https://pith.science/api/pith-number/EMZQQNABLABTEPQZFHZEONJIHC/events.json","paper":"https://pith.science/paper/EMZQQNAB"},"agent_actions":{"view_html":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC","download_json":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC.json","view_paper":"https://pith.science/paper/EMZQQNAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19041&json=true","fetch_graph":"https://pith.science/api/pith-number/EMZQQNABLABTEPQZFHZEONJIHC/graph.json","fetch_events":"https://pith.science/api/pith-number/EMZQQNABLABTEPQZFHZEONJIHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC/action/storage_attestation","attest_author":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC/action/author_attestation","sign_citation":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC/action/citation_signature","submit_replication":"https://pith.science/pith/EMZQQNABLABTEPQZFHZEONJIHC/action/replication_record"}},"created_at":"2026-07-05T08:24:47.078430+00:00","updated_at":"2026-07-05T08:24:47.078430+00:00"}