{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AB6CQBQV72CH6Z5SZWYCWRZIGJ","short_pith_number":"pith:AB6CQBQV","schema_version":"1.0","canonical_sha256":"007c280615fe847f67b2cdb02b4728325bc03ec71156362601dc596857149a80","source":{"kind":"arxiv","id":"2503.00493","version":4},"attestation_state":"computed","paper":{"title":"LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Boyi Kang, Chao Weng, Guobin Ma, Jun Chen, Lei Xie, Longshuai Xiao, Mingshuai Liu, Wei Xue, Xinfa Zhu, Yike Zhu, Zhen Ye, Zihan Zhang, Ziqian Wang","submitted_at":"2025-03-01T13:44:50Z","abstract_excerpt":"Recent advancements in language models (LMs) have demonstrated strong capabilities in semantic understanding and contextual modeling, which have flourished in generative speech enhancement (SE). However, many LM-based SE approaches primarily focus on semantic information, often neglecting the critical role of acoustic information, which leads to acoustic inconsistency after enhancement and limited generalization across diverse SE tasks. In this paper, we introduce LLaSE-G1, a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement. LLaSE-G1 offers the fo"},"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":"2503.00493","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-01T13:44:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"9568abcec5efe4cb393ae795a27b4fa9f4f1b7f9b573abbc3957b5885e1252ce","abstract_canon_sha256":"37d0d1be095529d42a294fe8c6c729ae94781fda9de4210f23600d5c68556625"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:41.799901Z","signature_b64":"VccNNOlwOelpzUIQks+QhBCOmEkjJq8LaUF5uuJoYuwJ/7QwC8HLh/wU/+jCNaK4ihCL61ise1u2Lf8f/V0HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"007c280615fe847f67b2cdb02b4728325bc03ec71156362601dc596857149a80","last_reissued_at":"2026-07-05T11:18:41.799443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:41.799443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Boyi Kang, Chao Weng, Guobin Ma, Jun Chen, Lei Xie, Longshuai Xiao, Mingshuai Liu, Wei Xue, Xinfa Zhu, Yike Zhu, Zhen Ye, Zihan Zhang, Ziqian Wang","submitted_at":"2025-03-01T13:44:50Z","abstract_excerpt":"Recent advancements in language models (LMs) have demonstrated strong capabilities in semantic understanding and contextual modeling, which have flourished in generative speech enhancement (SE). However, many LM-based SE approaches primarily focus on semantic information, often neglecting the critical role of acoustic information, which leads to acoustic inconsistency after enhancement and limited generalization across diverse SE tasks. In this paper, we introduce LLaSE-G1, a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement. LLaSE-G1 offers the fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00493","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/2503.00493/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":"2503.00493","created_at":"2026-07-05T11:18:41.799503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00493v4","created_at":"2026-07-05T11:18:41.799503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00493","created_at":"2026-07-05T11:18:41.799503+00:00"},{"alias_kind":"pith_short_12","alias_value":"AB6CQBQV72CH","created_at":"2026-07-05T11:18:41.799503+00:00"},{"alias_kind":"pith_short_16","alias_value":"AB6CQBQV72CH6Z5S","created_at":"2026-07-05T11:18:41.799503+00:00"},{"alias_kind":"pith_short_8","alias_value":"AB6CQBQV","created_at":"2026-07-05T11:18:41.799503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17806","citing_title":"PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06006","citing_title":"Discriminative-Generative Target Speaker Extraction with Decoder-Only Language Models","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ","json":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ.json","graph_json":"https://pith.science/api/pith-number/AB6CQBQV72CH6Z5SZWYCWRZIGJ/graph.json","events_json":"https://pith.science/api/pith-number/AB6CQBQV72CH6Z5SZWYCWRZIGJ/events.json","paper":"https://pith.science/paper/AB6CQBQV"},"agent_actions":{"view_html":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ","download_json":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ.json","view_paper":"https://pith.science/paper/AB6CQBQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00493&json=true","fetch_graph":"https://pith.science/api/pith-number/AB6CQBQV72CH6Z5SZWYCWRZIGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AB6CQBQV72CH6Z5SZWYCWRZIGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ/action/storage_attestation","attest_author":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ/action/author_attestation","sign_citation":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ/action/citation_signature","submit_replication":"https://pith.science/pith/AB6CQBQV72CH6Z5SZWYCWRZIGJ/action/replication_record"}},"created_at":"2026-07-05T11:18:41.799503+00:00","updated_at":"2026-07-05T11:18:41.799503+00:00"}