{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BHW6LGKWVRZPHTZWBL5YRC7Y3B","short_pith_number":"pith:BHW6LGKW","schema_version":"1.0","canonical_sha256":"09ede59956ac72f3cf360afb888bf8d86508d4f00c1c6a60890d3a167efd6329","source":{"kind":"arxiv","id":"2410.21042","version":1},"attestation_state":"computed","paper":{"title":"Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Huang, Mengke Li, Yang Lu, Ye Liu, Yiqun Zhang, Yiu-ming Cheung","submitted_at":"2024-10-28T13:58:17Z","abstract_excerpt":"Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising Sharpness-Aware Minimization (SAM) can effectively improve the generalization capability of models by seeking out flat minima in the loss landscape, which, however, comes at the cost of doubling the computational time. Since the update rule of SAM necessitates two consecutive (non-parallelizable) forward and backpropagation at each step. To address this issue,"},"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":"2410.21042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T13:58:17Z","cross_cats_sorted":[],"title_canon_sha256":"ed12c8192a2f2925396e2339afba11edb2206454fac05316e692ff06dd293274","abstract_canon_sha256":"27a0da32411b7fc0f4127428e4962b858a16ee257562c65a7ad4e2b598f42b2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:14.811442Z","signature_b64":"ifP1nj+vSflTtr3NV2kHkry3daCADLOtB8WH0rcMH+ocf38jOfCTb+mBmvbaFHrlA0psALePXi4LdxA73KjdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ede59956ac72f3cf360afb888bf8d86508d4f00c1c6a60890d3a167efd6329","last_reissued_at":"2026-07-05T09:27:14.811006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:14.811006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hui Huang, Mengke Li, Yang Lu, Ye Liu, Yiqun Zhang, Yiu-ming Cheung","submitted_at":"2024-10-28T13:58:17Z","abstract_excerpt":"Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising Sharpness-Aware Minimization (SAM) can effectively improve the generalization capability of models by seeking out flat minima in the loss landscape, which, however, comes at the cost of doubling the computational time. Since the update rule of SAM necessitates two consecutive (non-parallelizable) forward and backpropagation at each step. To address this issue,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21042","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/2410.21042/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":"2410.21042","created_at":"2026-07-05T09:27:14.811062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21042v1","created_at":"2026-07-05T09:27:14.811062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21042","created_at":"2026-07-05T09:27:14.811062+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHW6LGKWVRZP","created_at":"2026-07-05T09:27:14.811062+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHW6LGKWVRZPHTZW","created_at":"2026-07-05T09:27:14.811062+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHW6LGKW","created_at":"2026-07-05T09:27:14.811062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00374","citing_title":"Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B","json":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B.json","graph_json":"https://pith.science/api/pith-number/BHW6LGKWVRZPHTZWBL5YRC7Y3B/graph.json","events_json":"https://pith.science/api/pith-number/BHW6LGKWVRZPHTZWBL5YRC7Y3B/events.json","paper":"https://pith.science/paper/BHW6LGKW"},"agent_actions":{"view_html":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B","download_json":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B.json","view_paper":"https://pith.science/paper/BHW6LGKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21042&json=true","fetch_graph":"https://pith.science/api/pith-number/BHW6LGKWVRZPHTZWBL5YRC7Y3B/graph.json","fetch_events":"https://pith.science/api/pith-number/BHW6LGKWVRZPHTZWBL5YRC7Y3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B/action/storage_attestation","attest_author":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B/action/author_attestation","sign_citation":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B/action/citation_signature","submit_replication":"https://pith.science/pith/BHW6LGKWVRZPHTZWBL5YRC7Y3B/action/replication_record"}},"created_at":"2026-07-05T09:27:14.811062+00:00","updated_at":"2026-07-05T09:27:14.811062+00:00"}