{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NMCLRFVULVAMF4LXSKM5KIAYBQ","short_pith_number":"pith:NMCLRFVU","schema_version":"1.0","canonical_sha256":"6b04b896b45d40c2f1779299d520180c18b97eee2a2bb447cc810aaea64be6e6","source":{"kind":"arxiv","id":"2508.16680","version":2},"attestation_state":"computed","paper":{"title":"CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Afra Majida Hariono, Kuntpong Woraratpanya, Muchammad Daniyal Kautsar, Syukron Abu Ishaq Alfarozi, Widyawan","submitted_at":"2025-08-21T13:16:02Z","abstract_excerpt":"Large Language Models (LLMs) present significant deployment challenges due to their immense size and computational requirements. Model compression techniques are essential for making these models practical for resource-constrained environments. A prominent compression strategy is low-rank factorization via Singular Value Decomposition (SVD) to reduce model parameters by approximating weight matrices. However, standard SVD focuses on minimizing matrix reconstruction error, often leading to a substantial loss of the model's functional performance. This performance degradation occurs because exis"},"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":"2508.16680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-21T13:16:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7700ae3cc6d30c381dc56e3bcd5e2d3d3adf17bee6f3d4504f98d4445b77e29a","abstract_canon_sha256":"b6c23cc297a5506e0137889f9030380da99507695830dc40303adfb3e4796816"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:20.801694Z","signature_b64":"S582OqPkLoyqY9sS2gPRqAJq+YfuInHd+cqPFkBSTYrdZg3ZADOkWgN2sJv4Z6RsNElZ/yTmi8HE6b1XymQ4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b04b896b45d40c2f1779299d520180c18b97eee2a2bb447cc810aaea64be6e6","last_reissued_at":"2026-07-05T11:59:20.801130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:20.801130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Afra Majida Hariono, Kuntpong Woraratpanya, Muchammad Daniyal Kautsar, Syukron Abu Ishaq Alfarozi, Widyawan","submitted_at":"2025-08-21T13:16:02Z","abstract_excerpt":"Large Language Models (LLMs) present significant deployment challenges due to their immense size and computational requirements. Model compression techniques are essential for making these models practical for resource-constrained environments. A prominent compression strategy is low-rank factorization via Singular Value Decomposition (SVD) to reduce model parameters by approximating weight matrices. However, standard SVD focuses on minimizing matrix reconstruction error, often leading to a substantial loss of the model's functional performance. This performance degradation occurs because exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16680","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/2508.16680/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":"2508.16680","created_at":"2026-07-05T11:59:20.801191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16680v2","created_at":"2026-07-05T11:59:20.801191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16680","created_at":"2026-07-05T11:59:20.801191+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMCLRFVULVAM","created_at":"2026-07-05T11:59:20.801191+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMCLRFVULVAMF4LX","created_at":"2026-07-05T11:59:20.801191+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMCLRFVU","created_at":"2026-07-05T11:59:20.801191+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/NMCLRFVULVAMF4LXSKM5KIAYBQ","json":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ.json","graph_json":"https://pith.science/api/pith-number/NMCLRFVULVAMF4LXSKM5KIAYBQ/graph.json","events_json":"https://pith.science/api/pith-number/NMCLRFVULVAMF4LXSKM5KIAYBQ/events.json","paper":"https://pith.science/paper/NMCLRFVU"},"agent_actions":{"view_html":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ","download_json":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ.json","view_paper":"https://pith.science/paper/NMCLRFVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16680&json=true","fetch_graph":"https://pith.science/api/pith-number/NMCLRFVULVAMF4LXSKM5KIAYBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NMCLRFVULVAMF4LXSKM5KIAYBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ/action/storage_attestation","attest_author":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ/action/author_attestation","sign_citation":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ/action/citation_signature","submit_replication":"https://pith.science/pith/NMCLRFVULVAMF4LXSKM5KIAYBQ/action/replication_record"}},"created_at":"2026-07-05T11:59:20.801191+00:00","updated_at":"2026-07-05T11:59:20.801191+00:00"}