{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3DHUOWWYHPUXLVMLXVGCF4OPBY","short_pith_number":"pith:3DHUOWWY","schema_version":"1.0","canonical_sha256":"d8cf475ad83be975d58bbd4c22f1cf0e177928ecc6484e898bc76d444108823b","source":{"kind":"arxiv","id":"2308.14316","version":2},"attestation_state":"computed","paper":{"title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Wan, Haiwen Diao, Huchuan Lu, Long Chen, Xu Jia, Ying Zhang","submitted_at":"2023-08-28T05:38:43Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more valuable memory-efficient characteristic. In this paper, we argue that the scalability, adaptability, and generalizability of state-of-the-art methods are hindered by structural dependency and pertinency on specific pre-trained backbones. To this end, we propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT), to mitigate thes"},"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":"2308.14316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T05:38:43Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"15884a5fc16b29861713e0e88a2e5c16db9f9a6074a982b946f09f065525fbbb","abstract_canon_sha256":"afcb9c25affdb7932d97b275d84c508ea50a3bc4a34263b6fefe4664007f0abb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:32.510346Z","signature_b64":"P6y5wGKIHr2RhoNF9bFRgWe3dSDWnA4pTrwOUt4+tMbIbfL3xbB51vK0jixuvFQ4SsuV/dUaGzlOkfLQTL41DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8cf475ad83be975d58bbd4c22f1cf0e177928ecc6484e898bc76d444108823b","last_reissued_at":"2026-07-05T07:54:32.509930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:32.509930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Wan, Haiwen Diao, Huchuan Lu, Long Chen, Xu Jia, Ying Zhang","submitted_at":"2023-08-28T05:38:43Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more valuable memory-efficient characteristic. In this paper, we argue that the scalability, adaptability, and generalizability of state-of-the-art methods are hindered by structural dependency and pertinency on specific pre-trained backbones. To this end, we propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT), to mitigate thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14316","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/2308.14316/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":"2308.14316","created_at":"2026-07-05T07:54:32.509987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14316v2","created_at":"2026-07-05T07:54:32.509987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14316","created_at":"2026-07-05T07:54:32.509987+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DHUOWWYHPUX","created_at":"2026-07-05T07:54:32.509987+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DHUOWWYHPUXLVML","created_at":"2026-07-05T07:54:32.509987+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DHUOWWY","created_at":"2026-07-05T07:54:32.509987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00784","citing_title":"EDTformer: An Efficient Decoder Transformer for Visual Place Recognition","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY","json":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY.json","graph_json":"https://pith.science/api/pith-number/3DHUOWWYHPUXLVMLXVGCF4OPBY/graph.json","events_json":"https://pith.science/api/pith-number/3DHUOWWYHPUXLVMLXVGCF4OPBY/events.json","paper":"https://pith.science/paper/3DHUOWWY"},"agent_actions":{"view_html":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY","download_json":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY.json","view_paper":"https://pith.science/paper/3DHUOWWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14316&json=true","fetch_graph":"https://pith.science/api/pith-number/3DHUOWWYHPUXLVMLXVGCF4OPBY/graph.json","fetch_events":"https://pith.science/api/pith-number/3DHUOWWYHPUXLVMLXVGCF4OPBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY/action/storage_attestation","attest_author":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY/action/author_attestation","sign_citation":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY/action/citation_signature","submit_replication":"https://pith.science/pith/3DHUOWWYHPUXLVMLXVGCF4OPBY/action/replication_record"}},"created_at":"2026-07-05T07:54:32.509987+00:00","updated_at":"2026-07-05T07:54:32.509987+00:00"}