{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NQZ2NCDGWKRBIODNOIBA6B2EN","short_pith_number":"pith:6NQZ2NCD","schema_version":"1.0","canonical_sha256":"f3619d3443359510a1c36b9010783a235beb9b2b2467d18550a58d4fe102ecbc","source":{"kind":"arxiv","id":"2412.16956","version":2},"attestation_state":"computed","paper":{"title":"Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Fangyuan Zhang, Haowei Zhu, Junhai Yong, Rui Qin, Tianxiang Pan","submitted_at":"2024-12-22T10:28:52Z","abstract_excerpt":"As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indiscriminately applying prompts to every layer without considering their inherent correlations, can cause significant disturbances, leading to suboptimal transferability. Additionally, VPT disrupts the original self-attention structure, affecting the aggregation of visual features, and lacks a mechanism for explicitly mining discriminative visual features, which are crucial for c"},"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":"2412.16956","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T10:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"c186f11ec2ee50d69eb01301f9b5cb4fe587f306687cf8e3fb31b69be5207abb","abstract_canon_sha256":"56cd58e88542a916098b9225fe0a0f917a5926985115528b1f963dd8a6897927"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:47.797899Z","signature_b64":"u61Ivnz1FkEwmr3uNWuvi9IK65xBoSvofNA77lD8oU1cD+WNDvs7ppKdO5PZ1wPYFGAtfkkU/V+i00Oc5GSzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3619d3443359510a1c36b9010783a235beb9b2b2467d18550a58d4fe102ecbc","last_reissued_at":"2026-07-05T09:53:47.797490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:47.797490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Fangyuan Zhang, Haowei Zhu, Junhai Yong, Rui Qin, Tianxiang Pan","submitted_at":"2024-12-22T10:28:52Z","abstract_excerpt":"As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indiscriminately applying prompts to every layer without considering their inherent correlations, can cause significant disturbances, leading to suboptimal transferability. Additionally, VPT disrupts the original self-attention structure, affecting the aggregation of visual features, and lacks a mechanism for explicitly mining discriminative visual features, which are crucial for c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16956","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/2412.16956/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":"2412.16956","created_at":"2026-07-05T09:53:47.797552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16956v2","created_at":"2026-07-05T09:53:47.797552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16956","created_at":"2026-07-05T09:53:47.797552+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NQZ2NCDGWKR","created_at":"2026-07-05T09:53:47.797552+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NQZ2NCDGWKRBIOD","created_at":"2026-07-05T09:53:47.797552+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NQZ2NCD","created_at":"2026-07-05T09:53:47.797552+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/6NQZ2NCDGWKRBIODNOIBA6B2EN","json":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN.json","graph_json":"https://pith.science/api/pith-number/6NQZ2NCDGWKRBIODNOIBA6B2EN/graph.json","events_json":"https://pith.science/api/pith-number/6NQZ2NCDGWKRBIODNOIBA6B2EN/events.json","paper":"https://pith.science/paper/6NQZ2NCD"},"agent_actions":{"view_html":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN","download_json":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN.json","view_paper":"https://pith.science/paper/6NQZ2NCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16956&json=true","fetch_graph":"https://pith.science/api/pith-number/6NQZ2NCDGWKRBIODNOIBA6B2EN/graph.json","fetch_events":"https://pith.science/api/pith-number/6NQZ2NCDGWKRBIODNOIBA6B2EN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN/action/storage_attestation","attest_author":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN/action/author_attestation","sign_citation":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN/action/citation_signature","submit_replication":"https://pith.science/pith/6NQZ2NCDGWKRBIODNOIBA6B2EN/action/replication_record"}},"created_at":"2026-07-05T09:53:47.797552+00:00","updated_at":"2026-07-05T09:53:47.797552+00:00"}