{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JYRHSP5EU7WTQG3MHXQGGPN6IS","short_pith_number":"pith:JYRHSP5E","schema_version":"1.0","canonical_sha256":"4e22793fa4a7ed381b6c3de0633dbe449b518bbb2eb9c2cd348770be254f657e","source":{"kind":"arxiv","id":"2506.00620","version":1},"attestation_state":"computed","paper":{"title":"Model Reprogramming Demystified: A Neural Tangent Kernel Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Hancheng Ye, Jiashuo Fan, Ming-Yu Chung, Pin-Yu Chen, Qinsi Wang, Sy-Yen Kuo, Wei-Chen Shen","submitted_at":"2025-05-31T16:15:04Z","abstract_excerpt":"Model Reprogramming (MR) is a resource-efficient framework that adapts large pre-trained models to new tasks with minimal additional parameters and data, offering a promising solution to the challenges of training large models for diverse tasks. Despite its empirical success across various domains such as computer vision and time-series forecasting, the theoretical foundations of MR remain underexplored. In this paper, we present a comprehensive theoretical analysis of MR through the lens of the Neural Tangent Kernel (NTK) framework. We demonstrate that the success of MR is governed by the eig"},"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":"2506.00620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T16:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"d408b4a36e393f5e4740d19117126399591e829a0c18764c1e07d48d2421d486","abstract_canon_sha256":"9f18d00ccf0a8d53cbe3764dea660ed66dd8f7a4b4e0ab41727f58051e93d0d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:37.781145Z","signature_b64":"CSRmjdzGJ5soesDNvT1or4xZd0NzjHfn5yG/EbYhyrQw1jefs1MoysZGU7vd2fO6rCMvzUfXdMh6jyqVHrdYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e22793fa4a7ed381b6c3de0633dbe449b518bbb2eb9c2cd348770be254f657e","last_reissued_at":"2026-07-05T11:13:37.780677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:37.780677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Reprogramming Demystified: A Neural Tangent Kernel Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Hancheng Ye, Jiashuo Fan, Ming-Yu Chung, Pin-Yu Chen, Qinsi Wang, Sy-Yen Kuo, Wei-Chen Shen","submitted_at":"2025-05-31T16:15:04Z","abstract_excerpt":"Model Reprogramming (MR) is a resource-efficient framework that adapts large pre-trained models to new tasks with minimal additional parameters and data, offering a promising solution to the challenges of training large models for diverse tasks. Despite its empirical success across various domains such as computer vision and time-series forecasting, the theoretical foundations of MR remain underexplored. In this paper, we present a comprehensive theoretical analysis of MR through the lens of the Neural Tangent Kernel (NTK) framework. We demonstrate that the success of MR is governed by the eig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00620","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/2506.00620/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":"2506.00620","created_at":"2026-07-05T11:13:37.780735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00620v1","created_at":"2026-07-05T11:13:37.780735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00620","created_at":"2026-07-05T11:13:37.780735+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYRHSP5EU7WT","created_at":"2026-07-05T11:13:37.780735+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYRHSP5EU7WTQG3M","created_at":"2026-07-05T11:13:37.780735+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYRHSP5E","created_at":"2026-07-05T11:13:37.780735+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/JYRHSP5EU7WTQG3MHXQGGPN6IS","json":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS.json","graph_json":"https://pith.science/api/pith-number/JYRHSP5EU7WTQG3MHXQGGPN6IS/graph.json","events_json":"https://pith.science/api/pith-number/JYRHSP5EU7WTQG3MHXQGGPN6IS/events.json","paper":"https://pith.science/paper/JYRHSP5E"},"agent_actions":{"view_html":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS","download_json":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS.json","view_paper":"https://pith.science/paper/JYRHSP5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00620&json=true","fetch_graph":"https://pith.science/api/pith-number/JYRHSP5EU7WTQG3MHXQGGPN6IS/graph.json","fetch_events":"https://pith.science/api/pith-number/JYRHSP5EU7WTQG3MHXQGGPN6IS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS/action/storage_attestation","attest_author":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS/action/author_attestation","sign_citation":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS/action/citation_signature","submit_replication":"https://pith.science/pith/JYRHSP5EU7WTQG3MHXQGGPN6IS/action/replication_record"}},"created_at":"2026-07-05T11:13:37.780735+00:00","updated_at":"2026-07-05T11:13:37.780735+00:00"}