{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UI3VP7GG3JEDH6W3AQOTS2CBOR","short_pith_number":"pith:UI3VP7GG","schema_version":"1.0","canonical_sha256":"a23757fcc6da4833fadb041d39684174592f269905cb736a3a1e521f9d109a4a","source":{"kind":"arxiv","id":"2501.15040","version":1},"attestation_state":"computed","paper":{"title":"Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Dai, Kai Li, Maosheng Xiang, Xu Li, Yanmeng Guo, Zhongqi Wang","submitted_at":"2025-01-25T02:55:34Z","abstract_excerpt":"Vision language model (VLM) has been designed for large scale image-text alignment as a pretrained foundation model. For downstream few shot classification tasks, parameter efficient fine-tuning (PEFT) VLM has gained much popularity in the computer vision community. PEFT methods like prompt tuning and linear adapter have been studied for fine-tuning VLM while low rank adaptation (LoRA) algorithm has rarely been considered for few shot fine-tuning VLM. The main obstacle to use LoRA for few shot fine-tuning is the catastrophic forgetting problem. Because the visual language alignment knowledge i"},"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":"2501.15040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T02:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"9a0bd4ea236e5f79b9cbfe711b6119f461880d7a1cd4d49d03c2ffb2833e49ee","abstract_canon_sha256":"5f34af92ed05f419b3beb0d7d51f58a07f067b7dfacfe935ac7145682563b0a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:22.530784Z","signature_b64":"JBTnXGT+Wq2Oy02wvmO3Oxns1Mh0zf6gbBd4ulSwsswlO2Ehwo9xIAMp4PTgunZmW7mW18yPLVcCXgPx83VICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a23757fcc6da4833fadb041d39684174592f269905cb736a3a1e521f9d109a4a","last_reissued_at":"2026-07-05T10:05:22.530325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:22.530325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Dai, Kai Li, Maosheng Xiang, Xu Li, Yanmeng Guo, Zhongqi Wang","submitted_at":"2025-01-25T02:55:34Z","abstract_excerpt":"Vision language model (VLM) has been designed for large scale image-text alignment as a pretrained foundation model. For downstream few shot classification tasks, parameter efficient fine-tuning (PEFT) VLM has gained much popularity in the computer vision community. PEFT methods like prompt tuning and linear adapter have been studied for fine-tuning VLM while low rank adaptation (LoRA) algorithm has rarely been considered for few shot fine-tuning VLM. The main obstacle to use LoRA for few shot fine-tuning is the catastrophic forgetting problem. Because the visual language alignment knowledge i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15040","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/2501.15040/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":"2501.15040","created_at":"2026-07-05T10:05:22.530398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15040v1","created_at":"2026-07-05T10:05:22.530398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15040","created_at":"2026-07-05T10:05:22.530398+00:00"},{"alias_kind":"pith_short_12","alias_value":"UI3VP7GG3JED","created_at":"2026-07-05T10:05:22.530398+00:00"},{"alias_kind":"pith_short_16","alias_value":"UI3VP7GG3JEDH6W3","created_at":"2026-07-05T10:05:22.530398+00:00"},{"alias_kind":"pith_short_8","alias_value":"UI3VP7GG","created_at":"2026-07-05T10:05:22.530398+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/UI3VP7GG3JEDH6W3AQOTS2CBOR","json":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR.json","graph_json":"https://pith.science/api/pith-number/UI3VP7GG3JEDH6W3AQOTS2CBOR/graph.json","events_json":"https://pith.science/api/pith-number/UI3VP7GG3JEDH6W3AQOTS2CBOR/events.json","paper":"https://pith.science/paper/UI3VP7GG"},"agent_actions":{"view_html":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR","download_json":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR.json","view_paper":"https://pith.science/paper/UI3VP7GG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15040&json=true","fetch_graph":"https://pith.science/api/pith-number/UI3VP7GG3JEDH6W3AQOTS2CBOR/graph.json","fetch_events":"https://pith.science/api/pith-number/UI3VP7GG3JEDH6W3AQOTS2CBOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR/action/storage_attestation","attest_author":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR/action/author_attestation","sign_citation":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR/action/citation_signature","submit_replication":"https://pith.science/pith/UI3VP7GG3JEDH6W3AQOTS2CBOR/action/replication_record"}},"created_at":"2026-07-05T10:05:22.530398+00:00","updated_at":"2026-07-05T10:05:22.530398+00:00"}