{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6BVJPITBQ52OI7QGLNWV424Y2V","short_pith_number":"pith:6BVJPITB","schema_version":"1.0","canonical_sha256":"f06a97a2618774e47e065b6d5e6b98d5722f54e57fcd82dbc73bf405151e31a1","source":{"kind":"arxiv","id":"2403.19243","version":5},"attestation_state":"computed","paper":{"title":"Efficient Learning With Sine-Activated Low-rank Matrices","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Cameron Gordon, Hemanth Saratchandran, Simon Lucey, Yiping Ji, Zeyu Zhang","submitted_at":"2024-03-28T08:58:20Z","abstract_excerpt":"Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performance. However, a common challenge has been the compromise between parameter efficiency and the accuracy of the model, where reduced parameters often lead to diminished accuracy compared to their full-rank counterparts. In this work, we propose a novel theoretical framework that integrates a sinusoidal"},"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":"2403.19243","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-28T08:58:20Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"ba02841eac701a317a4a99b63be9a64fe87631aa1ba01abe8915b56d22e2ccb1","abstract_canon_sha256":"b4364b6cf0e13f57a47f0f347295acef5ca45d2c2a50514215a7d8c6a79c8118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:25.823746Z","signature_b64":"TscrIi9P1BurM+Z7OOucu7URoKiymWcuoTD+hQ0LaDWV5dFLMZxfhLT3a35lsXJCPlKK02llsCyatuYSOW4mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06a97a2618774e47e065b6d5e6b98d5722f54e57fcd82dbc73bf405151e31a1","last_reissued_at":"2026-07-05T10:32:25.822792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:25.822792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Learning With Sine-Activated Low-rank Matrices","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Cameron Gordon, Hemanth Saratchandran, Simon Lucey, Yiping Ji, Zeyu Zhang","submitted_at":"2024-03-28T08:58:20Z","abstract_excerpt":"Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learning. These techniques significantly lower the number of parameters, striking a balance between compactness and performance. However, a common challenge has been the compromise between parameter efficiency and the accuracy of the model, where reduced parameters often lead to diminished accuracy compared to their full-rank counterparts. In this work, we propose a novel theoretical framework that integrates a sinusoidal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19243","kind":"arxiv","version":5},"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/2403.19243/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":"2403.19243","created_at":"2026-07-05T10:32:25.822901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19243v5","created_at":"2026-07-05T10:32:25.822901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19243","created_at":"2026-07-05T10:32:25.822901+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BVJPITBQ52O","created_at":"2026-07-05T10:32:25.822901+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BVJPITBQ52OI7QG","created_at":"2026-07-05T10:32:25.822901+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BVJPITB","created_at":"2026-07-05T10:32:25.822901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22383","citing_title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29498","citing_title":"Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13381","citing_title":"Beyond Linearity in Attention Projections: The Case for Nonlinear Queries","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17451","citing_title":"SegTTA: Training-Free Test-Time Augmentation for Zero-Shot Medical Imaging Segmentation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V","json":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V.json","graph_json":"https://pith.science/api/pith-number/6BVJPITBQ52OI7QGLNWV424Y2V/graph.json","events_json":"https://pith.science/api/pith-number/6BVJPITBQ52OI7QGLNWV424Y2V/events.json","paper":"https://pith.science/paper/6BVJPITB"},"agent_actions":{"view_html":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V","download_json":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V.json","view_paper":"https://pith.science/paper/6BVJPITB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19243&json=true","fetch_graph":"https://pith.science/api/pith-number/6BVJPITBQ52OI7QGLNWV424Y2V/graph.json","fetch_events":"https://pith.science/api/pith-number/6BVJPITBQ52OI7QGLNWV424Y2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V/action/storage_attestation","attest_author":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V/action/author_attestation","sign_citation":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V/action/citation_signature","submit_replication":"https://pith.science/pith/6BVJPITBQ52OI7QGLNWV424Y2V/action/replication_record"}},"created_at":"2026-07-05T10:32:25.822901+00:00","updated_at":"2026-07-05T10:32:25.822901+00:00"}