{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YEYDIQTOEIPRFSX7J7JURTRH4V","short_pith_number":"pith:YEYDIQTO","schema_version":"1.0","canonical_sha256":"c13034426e221f12caff4fd348ce27e54c4dd09c9c3a96251e06a0371fe7a053","source":{"kind":"arxiv","id":"2508.01558","version":1},"attestation_state":"computed","paper":{"title":"EvoVLMA: Evolutionary Vision-Language Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Ding, Shiming Xiang, Ying Wang","submitted_at":"2025-08-03T03:11:01Z","abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) have been exploited in various Computer Vision tasks (e.g., few-shot recognition) via model adaptation, such as prompt tuning and adapters. However, existing adaptation methods are designed by human experts, requiring significant time cost and experience. Inspired by recent advances in Large Language Models (LLMs) based code generation, we propose an Evolutionary Vision-Language Model Adaptation (EvoVLMA) method to automatically search training-free efficient adaptation algorithms for VLMs. We recognize feature selection and logits computation as the k"},"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":"2508.01558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-03T03:11:01Z","cross_cats_sorted":[],"title_canon_sha256":"a626b0c4b060a271bb8b3404854c87b846ffbac6a07433efb190466215d8d68c","abstract_canon_sha256":"dc7b2f01c5816172547fc0813564f1e9b2eba8a6f0709f20eb92b02e16391e32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:41.166365Z","signature_b64":"xP9fwkA0tbZaSv5WFeU/1dad3tmqvjgpVyd0BLLWXnPHXuQQFHyJv9ms1GqhsGe2DJSR1ZL4Ye5p69l8lgD4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c13034426e221f12caff4fd348ce27e54c4dd09c9c3a96251e06a0371fe7a053","last_reissued_at":"2026-07-05T11:47:41.165906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:41.165906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoVLMA: Evolutionary Vision-Language Model Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Ding, Shiming Xiang, Ying Wang","submitted_at":"2025-08-03T03:11:01Z","abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) have been exploited in various Computer Vision tasks (e.g., few-shot recognition) via model adaptation, such as prompt tuning and adapters. However, existing adaptation methods are designed by human experts, requiring significant time cost and experience. Inspired by recent advances in Large Language Models (LLMs) based code generation, we propose an Evolutionary Vision-Language Model Adaptation (EvoVLMA) method to automatically search training-free efficient adaptation algorithms for VLMs. We recognize feature selection and logits computation as the k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01558","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/2508.01558/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":"2508.01558","created_at":"2026-07-05T11:47:41.165964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01558v1","created_at":"2026-07-05T11:47:41.165964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01558","created_at":"2026-07-05T11:47:41.165964+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEYDIQTOEIPR","created_at":"2026-07-05T11:47:41.165964+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEYDIQTOEIPRFSX7","created_at":"2026-07-05T11:47:41.165964+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEYDIQTO","created_at":"2026-07-05T11:47:41.165964+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/YEYDIQTOEIPRFSX7J7JURTRH4V","json":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V.json","graph_json":"https://pith.science/api/pith-number/YEYDIQTOEIPRFSX7J7JURTRH4V/graph.json","events_json":"https://pith.science/api/pith-number/YEYDIQTOEIPRFSX7J7JURTRH4V/events.json","paper":"https://pith.science/paper/YEYDIQTO"},"agent_actions":{"view_html":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V","download_json":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V.json","view_paper":"https://pith.science/paper/YEYDIQTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01558&json=true","fetch_graph":"https://pith.science/api/pith-number/YEYDIQTOEIPRFSX7J7JURTRH4V/graph.json","fetch_events":"https://pith.science/api/pith-number/YEYDIQTOEIPRFSX7J7JURTRH4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V/action/storage_attestation","attest_author":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V/action/author_attestation","sign_citation":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V/action/citation_signature","submit_replication":"https://pith.science/pith/YEYDIQTOEIPRFSX7J7JURTRH4V/action/replication_record"}},"created_at":"2026-07-05T11:47:41.165964+00:00","updated_at":"2026-07-05T11:47:41.165964+00:00"}