{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2QDH7XZ2R4UT74KZN3V7EU76G5","short_pith_number":"pith:2QDH7XZ2","schema_version":"1.0","canonical_sha256":"d4067fdf3a8f293ff1596eebf253fe3759a9ad78eb0353d7316c9b4b3beb5e19","source":{"kind":"arxiv","id":"2509.13211","version":4},"attestation_state":"computed","paper":{"title":"GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Nuertey Coleman, Irene Testa, Julio Hurtado, Luigi Quarantiello, Samrat Mukherjee, Vincenzo Lomonaco","submitted_at":"2025-09-16T16:18:19Z","abstract_excerpt":"The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich representations learned by large pre-trained models can partially mitigate catastrophic forgetting, they still struggle to adapt efficiently to evolving data distributions. A key challenge remains, how to continually add new knowledge to a large pretrained model in a way that is scalable and computationally efficient over long task sequences. In this work, we introduce GLAM, a simple and effective framework for class-incremental continu"},"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":"2509.13211","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-16T16:18:19Z","cross_cats_sorted":[],"title_canon_sha256":"c85e01df1b91d1dde6d3083ebb8b12a8c9ec53756800ea38061e577ff041edad","abstract_canon_sha256":"e7b5177160e057f31f295e1d674fba5af334f93e1e2dd65e9bd74b40b94c99a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:21:17.788597Z","signature_b64":"6eCFLEN2rkwMHVWTHOSQ1b4ent3OxnSc+z4Mk79j+C/wHq+EPFr7Orqt5vrVSa5ij9OmimWI/MP2rt17R3XtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4067fdf3a8f293ff1596eebf253fe3759a9ad78eb0353d7316c9b4b3beb5e19","last_reissued_at":"2026-08-12T01:21:17.786263Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:21:17.786263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Nuertey Coleman, Irene Testa, Julio Hurtado, Luigi Quarantiello, Samrat Mukherjee, Vincenzo Lomonaco","submitted_at":"2025-09-16T16:18:19Z","abstract_excerpt":"The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich representations learned by large pre-trained models can partially mitigate catastrophic forgetting, they still struggle to adapt efficiently to evolving data distributions. A key challenge remains, how to continually add new knowledge to a large pretrained model in a way that is scalable and computationally efficient over long task sequences. In this work, we introduce GLAM, a simple and effective framework for class-incremental continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13211","kind":"arxiv","version":4},"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/2509.13211/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":"2509.13211","created_at":"2026-08-12T01:21:17.790178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.13211v4","created_at":"2026-08-12T01:21:17.790178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13211","created_at":"2026-08-12T01:21:17.790178+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QDH7XZ2R4UT","created_at":"2026-08-12T01:21:17.790178+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QDH7XZ2R4UT74KZ","created_at":"2026-08-12T01:21:17.790178+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QDH7XZ2","created_at":"2026-08-12T01:21:17.790178+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/2QDH7XZ2R4UT74KZN3V7EU76G5","json":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5.json","graph_json":"https://pith.science/api/pith-number/2QDH7XZ2R4UT74KZN3V7EU76G5/graph.json","events_json":"https://pith.science/api/pith-number/2QDH7XZ2R4UT74KZN3V7EU76G5/events.json","paper":"https://pith.science/paper/2QDH7XZ2"},"agent_actions":{"view_html":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5","download_json":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5.json","view_paper":"https://pith.science/paper/2QDH7XZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.13211&json=true","fetch_graph":"https://pith.science/api/pith-number/2QDH7XZ2R4UT74KZN3V7EU76G5/graph.json","fetch_events":"https://pith.science/api/pith-number/2QDH7XZ2R4UT74KZN3V7EU76G5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5/action/storage_attestation","attest_author":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5/action/author_attestation","sign_citation":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5/action/citation_signature","submit_replication":"https://pith.science/pith/2QDH7XZ2R4UT74KZN3V7EU76G5/action/replication_record"}},"created_at":"2026-08-12T01:21:17.790178+00:00","updated_at":"2026-08-12T01:21:17.790178+00:00"}