{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G72EQSQUGBMIPDCULWHEP2KLUY","short_pith_number":"pith:G72EQSQU","schema_version":"1.0","canonical_sha256":"37f4484a143058878c545d8e47e94ba6332889aebd64a891469275ba579d3134","source":{"kind":"arxiv","id":"2412.08341","version":1},"attestation_state":"computed","paper":{"title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Errui Ding, Gang Zhang, Guosheng Zhang, Haixiao Yue, Jingdong Wang, Keyao Wang, Sinan Du, Yuanrui Wang, Zhengzhuo Xu","submitted_at":"2024-12-11T12:31:30Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning task-specific weights while compressing parameter size. However, such approaches predominantly manipulate within the original feature space utilizing a single-branch structure, which might be suboptimal for decoupling the learned representations and patterns. In this paper, we propose ALoRE, a novel PETL method that reuses the hypercomplex parameteriz"},"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":"2412.08341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T12:31:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de51851eef6c52b91a5b67f53ec19eed99954215d3bf29f527afd03c66c98076","abstract_canon_sha256":"1a44e53ddc3f2591657e81569d889ea971b34c29db970a605d4a6f8f0c68fec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:48.424759Z","signature_b64":"5FaBquAt3OqvsyTIfnWHdyI1MWGBG59xFQng1a9NnWMCuSfuh7ALnStnZAm+VK9IPtR35R4/Ao1IsrlYf90iBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37f4484a143058878c545d8e47e94ba6332889aebd64a891469275ba579d3134","last_reissued_at":"2026-07-05T09:47:48.424342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:48.424342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Errui Ding, Gang Zhang, Guosheng Zhang, Haixiao Yue, Jingdong Wang, Keyao Wang, Sinan Du, Yuanrui Wang, Zhengzhuo Xu","submitted_at":"2024-12-11T12:31:30Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning task-specific weights while compressing parameter size. However, such approaches predominantly manipulate within the original feature space utilizing a single-branch structure, which might be suboptimal for decoupling the learned representations and patterns. In this paper, we propose ALoRE, a novel PETL method that reuses the hypercomplex parameteriz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08341","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/2412.08341/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":"2412.08341","created_at":"2026-07-05T09:47:48.424395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08341v1","created_at":"2026-07-05T09:47:48.424395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08341","created_at":"2026-07-05T09:47:48.424395+00:00"},{"alias_kind":"pith_short_12","alias_value":"G72EQSQUGBMI","created_at":"2026-07-05T09:47:48.424395+00:00"},{"alias_kind":"pith_short_16","alias_value":"G72EQSQUGBMIPDCU","created_at":"2026-07-05T09:47:48.424395+00:00"},{"alias_kind":"pith_short_8","alias_value":"G72EQSQU","created_at":"2026-07-05T09:47:48.424395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00992","citing_title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY","json":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY.json","graph_json":"https://pith.science/api/pith-number/G72EQSQUGBMIPDCULWHEP2KLUY/graph.json","events_json":"https://pith.science/api/pith-number/G72EQSQUGBMIPDCULWHEP2KLUY/events.json","paper":"https://pith.science/paper/G72EQSQU"},"agent_actions":{"view_html":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY","download_json":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY.json","view_paper":"https://pith.science/paper/G72EQSQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08341&json=true","fetch_graph":"https://pith.science/api/pith-number/G72EQSQUGBMIPDCULWHEP2KLUY/graph.json","fetch_events":"https://pith.science/api/pith-number/G72EQSQUGBMIPDCULWHEP2KLUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY/action/storage_attestation","attest_author":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY/action/author_attestation","sign_citation":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY/action/citation_signature","submit_replication":"https://pith.science/pith/G72EQSQUGBMIPDCULWHEP2KLUY/action/replication_record"}},"created_at":"2026-07-05T09:47:48.424395+00:00","updated_at":"2026-07-05T09:47:48.424395+00:00"}