{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G7H4UVCL5LAEO6CSDH2BF5QRCZ","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":"b23ae9eac08a3ed7114141c489a353cfbd9624ca7c570cd5ee518991c9b81e8f","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T23:25:04Z","title_canon_sha256":"2616b9ecfdc3de8cd7b6a0595d2d2fea2021dacf16f1deced7723081a30ea7b5"},"schema_version":"1.0","source":{"id":"2402.08846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08846","created_at":"2026-07-05T07:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08846v1","created_at":"2026-07-05T07:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08846","created_at":"2026-07-05T07:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"G7H4UVCL5LAE","created_at":"2026-07-05T07:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"G7H4UVCL5LAEO6CS","created_at":"2026-07-05T07:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"G7H4UVCL","created_at":"2026-07-05T07:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:dc4c92fc011713f8c2beb603a19e95251cef919e080e257be22e4034e366a463","target":"graph","created_at":"2026-07-05T07:45:03Z","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/2402.08846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focus on solving one of the most important tasks in the field of speech processing, i.e., automatic speech recognition (ASR), with speech foundation encoders and large language models (LLM). Recent works have complex designs such as compressing the output temporally for the speech encoder, tackling modal alignment for the projector, and utilizing parameter-efficient fine-tuning for the LLM. We found that delicate designs are not necessary, while an embarrassingly simple composition of off-the-shelf speech encoder, LLM, and the only trainable linear projector is competent for ","authors_text":"Fan Yu, Guanrou Yang, Jiaming Wang, Qian Chen, Shiliang Zhang, Siqi Zheng, Xie Chen, Yifan Yang, Zhifu Gao, Zhihao Du, Ziyang Ma","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T23:25:04Z","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08846","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":"sha256:88970de97acd7179c3496eb609384df3bb11d9f8044b60f67909629ca60453be","target":"record","created_at":"2026-07-05T07:45:03Z","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":"b23ae9eac08a3ed7114141c489a353cfbd9624ca7c570cd5ee518991c9b81e8f","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-13T23:25:04Z","title_canon_sha256":"2616b9ecfdc3de8cd7b6a0595d2d2fea2021dacf16f1deced7723081a30ea7b5"},"schema_version":"1.0","source":{"id":"2402.08846","kind":"arxiv","version":1}},"canonical_sha256":"37cfca544beac047785219f412f6111664c2295d1f7b7e8559bcc90b436e6ae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37cfca544beac047785219f412f6111664c2295d1f7b7e8559bcc90b436e6ae2","first_computed_at":"2026-07-05T07:45:03.586198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:03.586198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4cq0gowQ2Yx2ICkANlfJFiAGL6CPaDzacpg4/wI5sZ0SaaEDWdg977+vpn+Xgky0//quJ8ilAQ9LpnJFPIqyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:03.586697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88970de97acd7179c3496eb609384df3bb11d9f8044b60f67909629ca60453be","sha256:dc4c92fc011713f8c2beb603a19e95251cef919e080e257be22e4034e366a463"],"state_sha256":"6b25934f4e4a7800e85f74812bf7c28e0363d004edd5c38251a040fe33dd83d1"}