{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OEY3PRVRFQXAXJBGCUNKRGNDJ5","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":"0dfdb3e5089fb9608941b608a33833a6154f6102d86f1414fbb9fb26161f1a3d","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:36:39Z","title_canon_sha256":"dcc3f4430494729916d04a64419bd4ed9055983b73e12386f2c74e3b96db22e0"},"schema_version":"1.0","source":{"id":"2502.12900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12900","created_at":"2026-07-05T10:16:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12900v1","created_at":"2026-07-05T10:16:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12900","created_at":"2026-07-05T10:16:26Z"},{"alias_kind":"pith_short_12","alias_value":"OEY3PRVRFQXA","created_at":"2026-07-05T10:16:26Z"},{"alias_kind":"pith_short_16","alias_value":"OEY3PRVRFQXAXJBG","created_at":"2026-07-05T10:16:26Z"},{"alias_kind":"pith_short_8","alias_value":"OEY3PRVR","created_at":"2026-07-05T10:16:26Z"}],"graph_snapshots":[{"event_id":"sha256:a8c59973050716756b401523eb7f4a376b64672584ca39c68d1ec325db7ab8b5","target":"graph","created_at":"2026-07-05T10:16:26Z","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/2502.12900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing end-to-end speech large language models (LLMs) usually rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth. We focus on two fundamental problems between speech and text: the representation space gap and sequence length inconsistency. We propose Soundwave, which utilizes an efficient training strategy and a novel architecture to address these issues. Results show that Soundwave outperforms the advanced Qwen2-Audio in speech translation and AIR-Bench speech tasks, using only one-fiftieth of the training data. Further analysis sh","authors_text":"Benyou Wang, Fan Bu, Haizhou Li, Ruiyu Zhang, Yuhao Zhang, Zhiheng Liu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:36:39Z","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12900","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":"sha256:4b6f3a915a322c8bcf0b5b5f23ea9bc03f9e2b0a0806afdf5a93935194c2e81d","target":"record","created_at":"2026-07-05T10:16:26Z","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":"0dfdb3e5089fb9608941b608a33833a6154f6102d86f1414fbb9fb26161f1a3d","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T14:36:39Z","title_canon_sha256":"dcc3f4430494729916d04a64419bd4ed9055983b73e12386f2c74e3b96db22e0"},"schema_version":"1.0","source":{"id":"2502.12900","kind":"arxiv","version":1}},"canonical_sha256":"7131b7c6b12c2e0ba426151aa899a34f45223d7d4bed9c1ea6f2ea9f154f4c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7131b7c6b12c2e0ba426151aa899a34f45223d7d4bed9c1ea6f2ea9f154f4c2d","first_computed_at":"2026-07-05T10:16:26.084842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:26.084842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ACSSFLuAIGEdt8u91PvFTvrFxR2zOhg3WTAWT9Ax2huL/BZo7T/UqRoG15TDZlV/Qyd++n7ddcEdGjRH7eBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:26.085411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b6f3a915a322c8bcf0b5b5f23ea9bc03f9e2b0a0806afdf5a93935194c2e81d","sha256:a8c59973050716756b401523eb7f4a376b64672584ca39c68d1ec325db7ab8b5"],"state_sha256":"07712486295784a884987846486efa7530b0d79d03f05e413c33245f1eb6b70f"}