{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YLBMTWPAWIPDQU5FAYPIQQV7UI","short_pith_number":"pith:YLBMTWPA","schema_version":"1.0","canonical_sha256":"c2c2c9d9e0b21e3853a5061e8842bfa207d88067702b76784219f1dff6aa9af5","source":{"kind":"arxiv","id":"2405.18069","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albin Soutif--Cormerais, Andew D. Bagdanov, Joost Van De Weijer, Simone Magistri","submitted_at":"2024-05-28T11:29:25Z","abstract_excerpt":"Broad, open source availability of large pretrained foundation models on the internet through platforms such as HuggingFace has taken the world of practical deep learning by storm. A classical pipeline for neural network training now typically consists of finetuning these pretrained network on a small target dataset instead of training from scratch. In the case of large models this can be done even on modest hardware using a low rank training technique known as Low-Rank Adaptation (LoRA). While Low Rank training has already been studied in the continual learning setting, existing works often c"},"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":"2405.18069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"8ef282dfa9d35b8d798de818b011bf1b34bd31191d1809a6cfa76a909b23a2af","abstract_canon_sha256":"552cdce10f1718194fe6f05f9c7dc2e81dce3d5b2381a57b6d88194890c3fff3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:33.128104Z","signature_b64":"zlEsbDZRhAQGnIAEgJpsIvwJ6Qy0IN2sHqRLE9MVoKXDSg8N1xujKf9Zd5JaX+7GohblRglWWEnXD+KIwEcOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c2c9d9e0b21e3853a5061e8842bfa207d88067702b76784219f1dff6aa9af5","last_reissued_at":"2026-07-05T11:05:33.127645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:33.127645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albin Soutif--Cormerais, Andew D. Bagdanov, Joost Van De Weijer, Simone Magistri","submitted_at":"2024-05-28T11:29:25Z","abstract_excerpt":"Broad, open source availability of large pretrained foundation models on the internet through platforms such as HuggingFace has taken the world of practical deep learning by storm. A classical pipeline for neural network training now typically consists of finetuning these pretrained network on a small target dataset instead of training from scratch. In the case of large models this can be done even on modest hardware using a low rank training technique known as Low-Rank Adaptation (LoRA). While Low Rank training has already been studied in the continual learning setting, existing works often c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18069","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/2405.18069/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":"2405.18069","created_at":"2026-07-05T11:05:33.127704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18069v2","created_at":"2026-07-05T11:05:33.127704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18069","created_at":"2026-07-05T11:05:33.127704+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLBMTWPAWIPD","created_at":"2026-07-05T11:05:33.127704+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLBMTWPAWIPDQU5F","created_at":"2026-07-05T11:05:33.127704+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLBMTWPA","created_at":"2026-07-05T11:05:33.127704+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10710","citing_title":"Continual Hyperbolic Learning of Instances and Classes","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI","json":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI.json","graph_json":"https://pith.science/api/pith-number/YLBMTWPAWIPDQU5FAYPIQQV7UI/graph.json","events_json":"https://pith.science/api/pith-number/YLBMTWPAWIPDQU5FAYPIQQV7UI/events.json","paper":"https://pith.science/paper/YLBMTWPA"},"agent_actions":{"view_html":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI","download_json":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI.json","view_paper":"https://pith.science/paper/YLBMTWPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18069&json=true","fetch_graph":"https://pith.science/api/pith-number/YLBMTWPAWIPDQU5FAYPIQQV7UI/graph.json","fetch_events":"https://pith.science/api/pith-number/YLBMTWPAWIPDQU5FAYPIQQV7UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI/action/storage_attestation","attest_author":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI/action/author_attestation","sign_citation":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI/action/citation_signature","submit_replication":"https://pith.science/pith/YLBMTWPAWIPDQU5FAYPIQQV7UI/action/replication_record"}},"created_at":"2026-07-05T11:05:33.127704+00:00","updated_at":"2026-07-05T11:05:33.127704+00:00"}