{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYAH3ZAGKXJJWSYLGOVZBRI6BE","short_pith_number":"pith:MYAH3ZAG","schema_version":"1.0","canonical_sha256":"66007de40655d29b4b0b33ab90c51e0919d325e5f98341efa774178b8c33188c","source":{"kind":"arxiv","id":"2411.13766","version":4},"attestation_state":"computed","paper":{"title":"Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenhui Xu, Dancheng Liu, Gelei Xu, Jinjun Xiong, Ruiyang Qin, Shaocong Wang, X. Sharon Hu, Yiyu Shi, Yuting Hu, Zheyu Yan","submitted_at":"2024-11-21T00:29:58Z","abstract_excerpt":"The combination of Large Language Models (LLM) and Automatic Speech Recognition (ASR), when deployed on edge devices (called edge ASR-LLM), can serve as a powerful personalized assistant to enable audio-based interaction for users. Compared to text-based interaction, edge ASR-LLM allows accessible and natural audio interactions. Unfortunately, existing ASR-LLM models are mainly trained in high-performance computing environments and produce substantial model weights, making them difficult to deploy on edge devices. More importantly, to better serve users' personalized needs, the ASR-LLM must be"},"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":"2411.13766","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-21T00:29:58Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9a1a9ec27fb0cfb3664c9d0fe88aa061f50579cbd7d18e15902081750d2c80c4","abstract_canon_sha256":"16f64961636ca4e18b59fe7f4921ee26808cfc9e57b9c1e9d7d8d77340d98727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:52.237687Z","signature_b64":"QknZ4az1QkelR9GZK6obgYQVAqSc8RRQ5RrmgOp45tjpyECcwY75VJ5NrCXeSBAWetWlTTfCrMh2HXGfasF+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66007de40655d29b4b0b33ab90c51e0919d325e5f98341efa774178b8c33188c","last_reissued_at":"2026-07-05T11:35:52.237108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:52.237108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenhui Xu, Dancheng Liu, Gelei Xu, Jinjun Xiong, Ruiyang Qin, Shaocong Wang, X. Sharon Hu, Yiyu Shi, Yuting Hu, Zheyu Yan","submitted_at":"2024-11-21T00:29:58Z","abstract_excerpt":"The combination of Large Language Models (LLM) and Automatic Speech Recognition (ASR), when deployed on edge devices (called edge ASR-LLM), can serve as a powerful personalized assistant to enable audio-based interaction for users. Compared to text-based interaction, edge ASR-LLM allows accessible and natural audio interactions. Unfortunately, existing ASR-LLM models are mainly trained in high-performance computing environments and produce substantial model weights, making them difficult to deploy on edge devices. More importantly, to better serve users' personalized needs, the ASR-LLM must be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13766","kind":"arxiv","version":4},"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/2411.13766/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":"2411.13766","created_at":"2026-07-05T11:35:52.237178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13766v4","created_at":"2026-07-05T11:35:52.237178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13766","created_at":"2026-07-05T11:35:52.237178+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYAH3ZAGKXJJ","created_at":"2026-07-05T11:35:52.237178+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYAH3ZAGKXJJWSYL","created_at":"2026-07-05T11:35:52.237178+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYAH3ZAG","created_at":"2026-07-05T11:35:52.237178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE","json":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE.json","graph_json":"https://pith.science/api/pith-number/MYAH3ZAGKXJJWSYLGOVZBRI6BE/graph.json","events_json":"https://pith.science/api/pith-number/MYAH3ZAGKXJJWSYLGOVZBRI6BE/events.json","paper":"https://pith.science/paper/MYAH3ZAG"},"agent_actions":{"view_html":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE","download_json":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE.json","view_paper":"https://pith.science/paper/MYAH3ZAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13766&json=true","fetch_graph":"https://pith.science/api/pith-number/MYAH3ZAGKXJJWSYLGOVZBRI6BE/graph.json","fetch_events":"https://pith.science/api/pith-number/MYAH3ZAGKXJJWSYLGOVZBRI6BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE/action/storage_attestation","attest_author":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE/action/author_attestation","sign_citation":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE/action/citation_signature","submit_replication":"https://pith.science/pith/MYAH3ZAGKXJJWSYLGOVZBRI6BE/action/replication_record"}},"created_at":"2026-07-05T11:35:52.237178+00:00","updated_at":"2026-07-05T11:35:52.237178+00:00"}