{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TMZOORUZ33LLIPMNOYSK4UJLG5","short_pith_number":"pith:TMZOORUZ","schema_version":"1.0","canonical_sha256":"9b32e74699ded6b43d8d7624ae512b376171b9ba5cc603f42c9d1cd7649b0f0b","source":{"kind":"arxiv","id":"2605.21147","version":1},"attestation_state":"computed","paper":{"title":"SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daling Wang, Feiliang Ren, Hinrich Sch\\\"utze, Mengjie Zhao, Qian Li, Shanru Zhang, Shi Feng, Xing Li, Yongkang Liu, Zijing Wang","submitted_at":"2026-05-20T13:19:28Z","abstract_excerpt":"As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning, which is widely used to reduce resource requirements. However, decreasing the rank encounters challenges with limited representational capacity. Theory suggests that LoRA fine-tuning with rank r converges toward the top r singular values of the pre-trained weight matrix. As the rank increases, more principal singular directions are preserve"},"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":"2605.21147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T13:19:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"285fb80d0bcd1b9336dbad8e5edfcf8e72595ccad1adb535eb224b68f8a57ed9","abstract_canon_sha256":"8ec043997fed07ed3f617b1a915e1f2a7aa2c53738f77fc232c3d4587189808b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:39.962373Z","signature_b64":"6WZ0aSsfKpuyeO13jvpS23BUXdb+WzEaDq2I6a8rXBJnjFtyTP5TRwVDostTsJTxf/3tGM8vWP0ZnmEyToBcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b32e74699ded6b43d8d7624ae512b376171b9ba5cc603f42c9d1cd7649b0f0b","last_reissued_at":"2026-05-21T01:05:39.961533Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:39.961533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daling Wang, Feiliang Ren, Hinrich Sch\\\"utze, Mengjie Zhao, Qian Li, Shanru Zhang, Shi Feng, Xing Li, Yongkang Liu, Zijing Wang","submitted_at":"2026-05-20T13:19:28Z","abstract_excerpt":"As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning, which is widely used to reduce resource requirements. However, decreasing the rank encounters challenges with limited representational capacity. Theory suggests that LoRA fine-tuning with rank r converges toward the top r singular values of the pre-trained weight matrix. As the rank increases, more principal singular directions are preserve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21147","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/2605.21147/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":"2605.21147","created_at":"2026-05-21T01:05:39.961673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21147v1","created_at":"2026-05-21T01:05:39.961673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21147","created_at":"2026-05-21T01:05:39.961673+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMZOORUZ33LL","created_at":"2026-05-21T01:05:39.961673+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMZOORUZ33LLIPMN","created_at":"2026-05-21T01:05:39.961673+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMZOORUZ","created_at":"2026-05-21T01:05:39.961673+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/TMZOORUZ33LLIPMNOYSK4UJLG5","json":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5.json","graph_json":"https://pith.science/api/pith-number/TMZOORUZ33LLIPMNOYSK4UJLG5/graph.json","events_json":"https://pith.science/api/pith-number/TMZOORUZ33LLIPMNOYSK4UJLG5/events.json","paper":"https://pith.science/paper/TMZOORUZ"},"agent_actions":{"view_html":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5","download_json":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5.json","view_paper":"https://pith.science/paper/TMZOORUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21147&json=true","fetch_graph":"https://pith.science/api/pith-number/TMZOORUZ33LLIPMNOYSK4UJLG5/graph.json","fetch_events":"https://pith.science/api/pith-number/TMZOORUZ33LLIPMNOYSK4UJLG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5/action/storage_attestation","attest_author":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5/action/author_attestation","sign_citation":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5/action/citation_signature","submit_replication":"https://pith.science/pith/TMZOORUZ33LLIPMNOYSK4UJLG5/action/replication_record"}},"created_at":"2026-05-21T01:05:39.961673+00:00","updated_at":"2026-05-21T01:05:39.961673+00:00"}