{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3GPV7MONYHMWGCQZE4YRBAIMP2","short_pith_number":"pith:3GPV7MON","schema_version":"1.0","canonical_sha256":"d99f5fb1cdc1d9630a19273110810c7e96b6dc2fa6f407ac6ba321d9a67ea384","source":{"kind":"arxiv","id":"2608.03885","version":1},"attestation_state":"computed","paper":{"title":"MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokui Chen, Chang Liu, Gengyuan Liu, Jiacong Wang, Nanzhou Wang, Qinwen Wu, Xiangyang Ji, Zhenhao Wang","submitted_at":"2026-08-04T16:20:54Z","abstract_excerpt":"Vision-language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-time adaptation (TTA) via Low-Rank Adaptation offers a parameter-efficient solution, we identify a fundamental bottleneck in current methods: the reliance on static rank configurations. Because visual inputs inherently possess varying information densities, a fixed rank forces an inevitable optimization compromise, leading to underfitting on complex scenes and overfitting on simple ones. To bridge this gap, we propose Multi-Rank Adaptation (MuRA)"},"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":"2608.03885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T16:20:54Z","cross_cats_sorted":[],"title_canon_sha256":"14a18947f972dd0717e0bbecc02f74d29283e905f3da4382077e2bf36561db85","abstract_canon_sha256":"1b8437e66f2be602d46bee0e7d1c5188d348e5d18120fc1d88088968791cdc76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:19.317063Z","signature_b64":"hOlVEi1jSPlJANSXhAa51ln734rEsy4KQq6MHSX8MSbEo1FRAHRS5PRt0X4wdWtzjlCAHlQrZI7YWjtEjQ73Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99f5fb1cdc1d9630a19273110810c7e96b6dc2fa6f407ac6ba321d9a67ea384","last_reissued_at":"2026-08-05T01:37:19.315650Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:19.315650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokui Chen, Chang Liu, Gengyuan Liu, Jiacong Wang, Nanzhou Wang, Qinwen Wu, Xiangyang Ji, Zhenhao Wang","submitted_at":"2026-08-04T16:20:54Z","abstract_excerpt":"Vision-language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-time adaptation (TTA) via Low-Rank Adaptation offers a parameter-efficient solution, we identify a fundamental bottleneck in current methods: the reliance on static rank configurations. Because visual inputs inherently possess varying information densities, a fixed rank forces an inevitable optimization compromise, leading to underfitting on complex scenes and overfitting on simple ones. To bridge this gap, we propose Multi-Rank Adaptation (MuRA)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03885","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/2608.03885/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":"2608.03885","created_at":"2026-08-05T01:37:19.316113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03885v1","created_at":"2026-08-05T01:37:19.316113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03885","created_at":"2026-08-05T01:37:19.316113+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GPV7MONYHMW","created_at":"2026-08-05T01:37:19.316113+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GPV7MONYHMWGCQZ","created_at":"2026-08-05T01:37:19.316113+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GPV7MON","created_at":"2026-08-05T01:37:19.316113+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/3GPV7MONYHMWGCQZE4YRBAIMP2","json":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2.json","graph_json":"https://pith.science/api/pith-number/3GPV7MONYHMWGCQZE4YRBAIMP2/graph.json","events_json":"https://pith.science/api/pith-number/3GPV7MONYHMWGCQZE4YRBAIMP2/events.json","paper":"https://pith.science/paper/3GPV7MON"},"agent_actions":{"view_html":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2","download_json":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2.json","view_paper":"https://pith.science/paper/3GPV7MON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03885&json=true","fetch_graph":"https://pith.science/api/pith-number/3GPV7MONYHMWGCQZE4YRBAIMP2/graph.json","fetch_events":"https://pith.science/api/pith-number/3GPV7MONYHMWGCQZE4YRBAIMP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2/action/storage_attestation","attest_author":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2/action/author_attestation","sign_citation":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2/action/citation_signature","submit_replication":"https://pith.science/pith/3GPV7MONYHMWGCQZE4YRBAIMP2/action/replication_record"}},"created_at":"2026-08-05T01:37:19.316113+00:00","updated_at":"2026-08-05T01:37:19.316113+00:00"}