{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N3RRHG75PDZJETGR3UTAP277AM","short_pith_number":"pith:N3RRHG75","schema_version":"1.0","canonical_sha256":"6ee3139bfd78f2924cd1dd2607ebff0331c861e76fee3afef44604fd51e0ad1a","source":{"kind":"arxiv","id":"2603.09493","version":2},"attestation_state":"computed","paper":{"title":"EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Enming Zhang, Jiayang Li, Yang Li, Yanlong Wang, Yanru Wu, Zhenyu Liu","submitted_at":"2026-03-10T10:53:01Z","abstract_excerpt":"The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from catastrophic forgetting of pre-trained knowledge. Toward addressing this limitation, our work is grounded in the insight that governing the evolutionary path of prompts is essential for forgetting-free adaptation. To this end, we propose EvoPrompt, a novel framework designed to explicitly steer the prompt trajectory for knowledge-preserving fine-tuning. Specific"},"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":"2603.09493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T10:53:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b8b5a6f489c34f115b3c5fd1b1209cc3b70ace8599192233d0c5aa76a88a639","abstract_canon_sha256":"de58c11747aed47c68e27e301e6ac1eb94c633c5b34212761cfd36a41a75bd9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:47.899695Z","signature_b64":"OMoQC4Hc23gUVO5AEr48pMuwonAsX3t87f4i0rDh6pNBXygR2Cqw6wNPNaPvIrT9FHzQTEJqqU4FLbDaEK38Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ee3139bfd78f2924cd1dd2607ebff0331c861e76fee3afef44604fd51e0ad1a","last_reissued_at":"2026-06-04T01:08:47.898834Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:47.898834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Enming Zhang, Jiayang Li, Yang Li, Yanlong Wang, Yanru Wu, Zhenyu Liu","submitted_at":"2026-03-10T10:53:01Z","abstract_excerpt":"The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from catastrophic forgetting of pre-trained knowledge. Toward addressing this limitation, our work is grounded in the insight that governing the evolutionary path of prompts is essential for forgetting-free adaptation. To this end, we propose EvoPrompt, a novel framework designed to explicitly steer the prompt trajectory for knowledge-preserving fine-tuning. Specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09493","kind":"arxiv","version":2},"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/2603.09493/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":"2603.09493","created_at":"2026-06-04T01:08:47.898947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.09493v2","created_at":"2026-06-04T01:08:47.898947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09493","created_at":"2026-06-04T01:08:47.898947+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3RRHG75PDZJ","created_at":"2026-06-04T01:08:47.898947+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3RRHG75PDZJETGR","created_at":"2026-06-04T01:08:47.898947+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3RRHG75","created_at":"2026-06-04T01:08:47.898947+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/N3RRHG75PDZJETGR3UTAP277AM","json":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM.json","graph_json":"https://pith.science/api/pith-number/N3RRHG75PDZJETGR3UTAP277AM/graph.json","events_json":"https://pith.science/api/pith-number/N3RRHG75PDZJETGR3UTAP277AM/events.json","paper":"https://pith.science/paper/N3RRHG75"},"agent_actions":{"view_html":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM","download_json":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM.json","view_paper":"https://pith.science/paper/N3RRHG75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.09493&json=true","fetch_graph":"https://pith.science/api/pith-number/N3RRHG75PDZJETGR3UTAP277AM/graph.json","fetch_events":"https://pith.science/api/pith-number/N3RRHG75PDZJETGR3UTAP277AM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM/action/storage_attestation","attest_author":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM/action/author_attestation","sign_citation":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM/action/citation_signature","submit_replication":"https://pith.science/pith/N3RRHG75PDZJETGR3UTAP277AM/action/replication_record"}},"created_at":"2026-06-04T01:08:47.898947+00:00","updated_at":"2026-06-04T01:08:47.898947+00:00"}