{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FPKHJUQU3Q7ZNBMBNXTRQM5IIH","short_pith_number":"pith:FPKHJUQU","schema_version":"1.0","canonical_sha256":"2bd474d214dc3f9685816de71833a841c021453ddb279b7ac1782ec49f0a0df1","source":{"kind":"arxiv","id":"2507.19887","version":1},"attestation_state":"computed","paper":{"title":"CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Didier Stricker, Ren\\'e Schuster, Shishir Muralidhara","submitted_at":"2025-07-26T09:36:05Z","abstract_excerpt":"In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of limited data access, without any restrictions imposed on computational resources. However, in real-world scenarios, the latter takes precedence as deployed systems are often computationally constrained. A major drawback of most CL methods is the need to retrain the entire model for each new task. The computational demands of retraining large models can be prohibit"},"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":"2507.19887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-26T09:36:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6e32ec346c126144942f1807786f557866904a8064e76209f48f6ffc91759ad0","abstract_canon_sha256":"7ae7cbb25133794101390836b3f2998a76deca3c453734c48ada0e04c298c45d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:44.330036Z","signature_b64":"Dvs3PpAQZeNX+BZzuT7Nj6opxG7Bmi42aSGVqDxxksOw1ODd5MGyirwFRbsCYYgCANxJhlcBSCg++YUe1JBKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd474d214dc3f9685816de71833a841c021453ddb279b7ac1782ec49f0a0df1","last_reissued_at":"2026-07-05T11:43:44.329497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:44.329497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Didier Stricker, Ren\\'e Schuster, Shishir Muralidhara","submitted_at":"2025-07-26T09:36:05Z","abstract_excerpt":"In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of limited data access, without any restrictions imposed on computational resources. However, in real-world scenarios, the latter takes precedence as deployed systems are often computationally constrained. A major drawback of most CL methods is the need to retrain the entire model for each new task. The computational demands of retraining large models can be prohibit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19887","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/2507.19887/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":"2507.19887","created_at":"2026-07-05T11:43:44.329568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19887v1","created_at":"2026-07-05T11:43:44.329568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19887","created_at":"2026-07-05T11:43:44.329568+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPKHJUQU3Q7Z","created_at":"2026-07-05T11:43:44.329568+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPKHJUQU3Q7ZNBMB","created_at":"2026-07-05T11:43:44.329568+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPKHJUQU","created_at":"2026-07-05T11:43:44.329568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03555","citing_title":"MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH","json":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH.json","graph_json":"https://pith.science/api/pith-number/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/graph.json","events_json":"https://pith.science/api/pith-number/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/events.json","paper":"https://pith.science/paper/FPKHJUQU"},"agent_actions":{"view_html":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH","download_json":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH.json","view_paper":"https://pith.science/paper/FPKHJUQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19887&json=true","fetch_graph":"https://pith.science/api/pith-number/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/graph.json","fetch_events":"https://pith.science/api/pith-number/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/action/storage_attestation","attest_author":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/action/author_attestation","sign_citation":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/action/citation_signature","submit_replication":"https://pith.science/pith/FPKHJUQU3Q7ZNBMBNXTRQM5IIH/action/replication_record"}},"created_at":"2026-07-05T11:43:44.329568+00:00","updated_at":"2026-07-05T11:43:44.329568+00:00"}