{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HSC5N3AXB7EAAZ3ZZB47ZZFS54","short_pith_number":"pith:HSC5N3AX","schema_version":"1.0","canonical_sha256":"3c85d6ec170fc8006779c879fce4b2ef0632428c5d753bf0411d50919b8c8e96","source":{"kind":"arxiv","id":"2501.03152","version":1},"attestation_state":"computed","paper":{"title":"The Scaling Law for LoRA Base on Mutual Information Upper Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Yang, Hui Gao, Jing Zhang, Peng Zhang, Shuzhen Sun, Yuexian Hou","submitted_at":"2025-01-06T17:19:19Z","abstract_excerpt":"LoRA (Low-Rank Adaptation) is a widely used model fine-tuning method. In fine-tuning, the law among model performance, model parameters, and data complexity has been a focal issue in the field. Existing methods often leverage external metrics (such as cross-entropy or perplexity) to evaluate model performance. In the fine-tuning process for large models, two types of knowledge are typically involved: the frozen, general knowledge acquired by the model during pre-training and the new knowledge learned through the LoRA module from the current data. Generally, the less LoRA's learned knowledge re"},"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":"2501.03152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-06T17:19:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"974a736241330d9485e99f5ec9c708bf47e918642ee6de8c31fba7fbde4b1859","abstract_canon_sha256":"ef4155bc6c558351c0f866802ede0d24d7b8807a809cafd365f34df4a3a5e9b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:32.315891Z","signature_b64":"hCe1YFYIsIYIrLhpMRFMwwStusxNe1u9bs0WJbc63KBsreJFZFP2/OmJ4x812yo6K8xWq8iS+Ks1Tp7Y74SlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c85d6ec170fc8006779c879fce4b2ef0632428c5d753bf0411d50919b8c8e96","last_reissued_at":"2026-07-05T09:57:32.315351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:32.315351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Scaling Law for LoRA Base on Mutual Information Upper Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chang Yang, Hui Gao, Jing Zhang, Peng Zhang, Shuzhen Sun, Yuexian Hou","submitted_at":"2025-01-06T17:19:19Z","abstract_excerpt":"LoRA (Low-Rank Adaptation) is a widely used model fine-tuning method. In fine-tuning, the law among model performance, model parameters, and data complexity has been a focal issue in the field. Existing methods often leverage external metrics (such as cross-entropy or perplexity) to evaluate model performance. In the fine-tuning process for large models, two types of knowledge are typically involved: the frozen, general knowledge acquired by the model during pre-training and the new knowledge learned through the LoRA module from the current data. Generally, the less LoRA's learned knowledge re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03152","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/2501.03152/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":"2501.03152","created_at":"2026-07-05T09:57:32.315426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03152v1","created_at":"2026-07-05T09:57:32.315426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03152","created_at":"2026-07-05T09:57:32.315426+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSC5N3AXB7EA","created_at":"2026-07-05T09:57:32.315426+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSC5N3AXB7EAAZ3Z","created_at":"2026-07-05T09:57:32.315426+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSC5N3AX","created_at":"2026-07-05T09:57:32.315426+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/HSC5N3AXB7EAAZ3ZZB47ZZFS54","json":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54.json","graph_json":"https://pith.science/api/pith-number/HSC5N3AXB7EAAZ3ZZB47ZZFS54/graph.json","events_json":"https://pith.science/api/pith-number/HSC5N3AXB7EAAZ3ZZB47ZZFS54/events.json","paper":"https://pith.science/paper/HSC5N3AX"},"agent_actions":{"view_html":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54","download_json":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54.json","view_paper":"https://pith.science/paper/HSC5N3AX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03152&json=true","fetch_graph":"https://pith.science/api/pith-number/HSC5N3AXB7EAAZ3ZZB47ZZFS54/graph.json","fetch_events":"https://pith.science/api/pith-number/HSC5N3AXB7EAAZ3ZZB47ZZFS54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54/action/storage_attestation","attest_author":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54/action/author_attestation","sign_citation":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54/action/citation_signature","submit_replication":"https://pith.science/pith/HSC5N3AXB7EAAZ3ZZB47ZZFS54/action/replication_record"}},"created_at":"2026-07-05T09:57:32.315426+00:00","updated_at":"2026-07-05T09:57:32.315426+00:00"}