{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F5RW7EGVJOQV6R3ZSVVFDBGYXZ","short_pith_number":"pith:F5RW7EGV","canonical_record":{"source":{"id":"2502.14816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:37:32Z","cross_cats_sorted":[],"title_canon_sha256":"6a4d1e771e160156b44b0393402588965a729dda12034dfef186f80e1f5c20d7","abstract_canon_sha256":"ef07e75770dc3ac2b0050d90df0605b4813b66238425d2b65c1b3034142fb0f3"},"schema_version":"1.0"},"canonical_sha256":"2f636f90d54ba15f4779956a5184d8be647a242ccbb17de2a62d8118a6635a3d","source":{"kind":"arxiv","id":"2502.14816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14816","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14816v1","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14816","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"F5RW7EGVJOQV","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"F5RW7EGVJOQV6R3Z","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"F5RW7EGV","created_at":"2026-07-05T10:17:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F5RW7EGVJOQV6R3ZSVVFDBGYXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:37:32Z","cross_cats_sorted":[],"title_canon_sha256":"6a4d1e771e160156b44b0393402588965a729dda12034dfef186f80e1f5c20d7","abstract_canon_sha256":"ef07e75770dc3ac2b0050d90df0605b4813b66238425d2b65c1b3034142fb0f3"},"schema_version":"1.0"},"canonical_sha256":"2f636f90d54ba15f4779956a5184d8be647a242ccbb17de2a62d8118a6635a3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:33.003075Z","signature_b64":"y7JS4JL10Juup6dWtoO090VbBMVY3lLbFS6//5AyF5VGHreevpdLhfaFWlwZ6JUcSwtOIS2U2OlTU9GWwH7sAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f636f90d54ba15f4779956a5184d8be647a242ccbb17de2a62d8118a6635a3d","last_reissued_at":"2026-07-05T10:17:33.002591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:33.002591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14816","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Ov/+x2a1uv7WC7m0jcKsbsZJip0XZRxyuldQJYD1+H/+a77yFfEx8PF0K/qw6pEqcGNrxlN2my3ddnu6++bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:04:51.938261Z"},"content_sha256":"66360eab7c5a556581d0ac0646eb36237a928897eba66e19e3be1719e0fccbf9","schema_version":"1.0","event_id":"sha256:66360eab7c5a556581d0ac0646eb36237a928897eba66e19e3be1719e0fccbf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F5RW7EGVJOQV6R3ZSVVFDBGYXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jing Lin, Rongrong Ji, Weizhong Huang, Xiawu Zheng, Yang Liu, Yiwu Yao, Yuxin Zhang","submitted_at":"2025-02-20T18:37:32Z","abstract_excerpt":"Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Adaptation (LoRA) to fine-tune the sparse LLMs offers an intuitive approach to counter this predicament, while it holds shortcomings include: 1) The inability to integrate LoRA weights into sparse LLMs post-training, and 2) Insufficient performance recovery at high sparsity ratios. In this paper, we introduce dynamic Low-rank Sparse Adaptation (LoSA), a novel method that seamlessly integrates low-rank adaptation into LL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14816","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/2502.14816/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAbEzNozCPAfMPFDHsl345uxk7wyx5YMz18K9JnJr1SEzO27uhDyJKVGxUFV6s/Eu6R7l1WWXs/IdsKEH7bSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:04:51.938647Z"},"content_sha256":"5b7060fa973dfb9377a0ae34d0b3bbe9c3792baa21bb582edaa86c19b43f85de","schema_version":"1.0","event_id":"sha256:5b7060fa973dfb9377a0ae34d0b3bbe9c3792baa21bb582edaa86c19b43f85de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/bundle.json","state_url":"https://pith.science/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T05:04:51Z","links":{"resolver":"https://pith.science/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ","bundle":"https://pith.science/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/bundle.json","state":"https://pith.science/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5RW7EGVJOQV6R3ZSVVFDBGYXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F5RW7EGVJOQV6R3ZSVVFDBGYXZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ef07e75770dc3ac2b0050d90df0605b4813b66238425d2b65c1b3034142fb0f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:37:32Z","title_canon_sha256":"6a4d1e771e160156b44b0393402588965a729dda12034dfef186f80e1f5c20d7"},"schema_version":"1.0","source":{"id":"2502.14816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14816","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14816v1","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14816","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"F5RW7EGVJOQV","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"F5RW7EGVJOQV6R3Z","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"F5RW7EGV","created_at":"2026-07-05T10:17:33Z"}],"graph_snapshots":[{"event_id":"sha256:5b7060fa973dfb9377a0ae34d0b3bbe9c3792baa21bb582edaa86c19b43f85de","target":"graph","created_at":"2026-07-05T10:17:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.14816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Adaptation (LoRA) to fine-tune the sparse LLMs offers an intuitive approach to counter this predicament, while it holds shortcomings include: 1) The inability to integrate LoRA weights into sparse LLMs post-training, and 2) Insufficient performance recovery at high sparsity ratios. In this paper, we introduce dynamic Low-rank Sparse Adaptation (LoSA), a novel method that seamlessly integrates low-rank adaptation into LL","authors_text":"Jing Lin, Rongrong Ji, Weizhong Huang, Xiawu Zheng, Yang Liu, Yiwu Yao, Yuxin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:37:32Z","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14816","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66360eab7c5a556581d0ac0646eb36237a928897eba66e19e3be1719e0fccbf9","target":"record","created_at":"2026-07-05T10:17:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ef07e75770dc3ac2b0050d90df0605b4813b66238425d2b65c1b3034142fb0f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-20T18:37:32Z","title_canon_sha256":"6a4d1e771e160156b44b0393402588965a729dda12034dfef186f80e1f5c20d7"},"schema_version":"1.0","source":{"id":"2502.14816","kind":"arxiv","version":1}},"canonical_sha256":"2f636f90d54ba15f4779956a5184d8be647a242ccbb17de2a62d8118a6635a3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f636f90d54ba15f4779956a5184d8be647a242ccbb17de2a62d8118a6635a3d","first_computed_at":"2026-07-05T10:17:33.002591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:33.002591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y7JS4JL10Juup6dWtoO090VbBMVY3lLbFS6//5AyF5VGHreevpdLhfaFWlwZ6JUcSwtOIS2U2OlTU9GWwH7sAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:33.003075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66360eab7c5a556581d0ac0646eb36237a928897eba66e19e3be1719e0fccbf9","sha256:5b7060fa973dfb9377a0ae34d0b3bbe9c3792baa21bb582edaa86c19b43f85de"],"state_sha256":"6ba058cc7bf3a81b712f42917f9fdb183d202a272b71d7b0e4c15261282f394f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpoSCtM6W4VIpVS9H3lWqXiqltTKSFQW92PLo+qkqTvUC6kHV3T+5YE6YyBRTCATmUocE6ELoyolXds2cq/AAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T05:04:51.940673Z","bundle_sha256":"107f239b8707243e483dd31c3fc6f078ced67f1b6408c5e8589bbf65926b613c"}}