{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:67Q6JIVY4Z4CQUDGCMKUTDURSJ","short_pith_number":"pith:67Q6JIVY","canonical_record":{"source":{"id":"2504.00254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T21:58:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"3e077da5bb93a8759bb7d7303f5311c093f64735a02135a0d12b4db7b8110fa2","abstract_canon_sha256":"bea2afa46e3cf21754cc9e1a225dead65a2550f6bf351f9196993281404015aa"},"schema_version":"1.0"},"canonical_sha256":"f7e1e4a2b8e6782850661315498e91927ee40e3cda7c1186992641a48f6263bb","source":{"kind":"arxiv","id":"2504.00254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00254","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00254v1","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00254","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"67Q6JIVY4Z4C","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"67Q6JIVY4Z4CQUDG","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"67Q6JIVY","created_at":"2026-07-05T10:42:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:67Q6JIVY4Z4CQUDGCMKUTDURSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T21:58:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"3e077da5bb93a8759bb7d7303f5311c093f64735a02135a0d12b4db7b8110fa2","abstract_canon_sha256":"bea2afa46e3cf21754cc9e1a225dead65a2550f6bf351f9196993281404015aa"},"schema_version":"1.0"},"canonical_sha256":"f7e1e4a2b8e6782850661315498e91927ee40e3cda7c1186992641a48f6263bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:22.552434Z","signature_b64":"T6b8Pni8yTp+OXwJMkfCEZ4JEY/u6JjwASKlo8Fwzt3gkqGJJokAufxoIaX6ztNv3NfhcIpVtGiRxgYYX6/bAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e1e4a2b8e6782850661315498e91927ee40e3cda7c1186992641a48f6263bb","last_reissued_at":"2026-07-05T10:42:22.551972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:22.551972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00254","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":"2026-07-05T10:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qaCp+vLGsENnl2KDU0wXnh+gK+f1vqRrxsRU5z7iCoeIrb9sB3jf7Q/Suy3VHDW9lHehOiLlpydPhw0IZUoUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:47:09.980919Z"},"content_sha256":"484f652b7d18f4acdca788b507af407b0308e54213a05f52f73fc185300f2ddc","schema_version":"1.0","event_id":"sha256:484f652b7d18f4acdca788b507af407b0308e54213a05f52f73fc185300f2ddc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:67Q6JIVY4Z4CQUDGCMKUTDURSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew Sabot, Hong Jiang, H. T. Kung, Huandong Chang, Mingyuan Ma, Zhenting Qi, Zicheng Ma","submitted_at":"2025-03-31T21:58:25Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) has become a widely adopted technique for fine-tuning large-scale pre-trained models with minimal parameter updates. However, existing methods rely on fixed ranks or focus solely on either rank pruning or expansion, failing to adapt ranks dynamically to match the importance of different layers during training. In this work, we propose ElaLoRA, an adaptive low-rank adaptation framework that dynamically prunes and expands ranks based on gradient-derived importance scores. To the best of our knowledge, ElaLoRA is the first method that enables both rank pruning and expan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00254","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/2504.00254/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":"2026-07-05T10:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjvtTauCaxjjD4GAgDKh1xZo/PMTqKRxKp9jf/17ya1FRbVG0Pwl5Vy1i4RwtfNn7ibcmdfWWl6UnHbiWyEkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:47:09.981835Z"},"content_sha256":"14f09b353aefbb95cf80ea308587e799e6f66fb71a9463c8eb775be24fbaef16","schema_version":"1.0","event_id":"sha256:14f09b353aefbb95cf80ea308587e799e6f66fb71a9463c8eb775be24fbaef16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/bundle.json","state_url":"https://pith.science/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/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":"2026-08-10T18:47:09Z","links":{"resolver":"https://pith.science/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ","bundle":"https://pith.science/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/bundle.json","state":"https://pith.science/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67Q6JIVY4Z4CQUDGCMKUTDURSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:67Q6JIVY4Z4CQUDGCMKUTDURSJ","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":"bea2afa46e3cf21754cc9e1a225dead65a2550f6bf351f9196993281404015aa","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T21:58:25Z","title_canon_sha256":"3e077da5bb93a8759bb7d7303f5311c093f64735a02135a0d12b4db7b8110fa2"},"schema_version":"1.0","source":{"id":"2504.00254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00254","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00254v1","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00254","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"67Q6JIVY4Z4C","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"67Q6JIVY4Z4CQUDG","created_at":"2026-07-05T10:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"67Q6JIVY","created_at":"2026-07-05T10:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:14f09b353aefbb95cf80ea308587e799e6f66fb71a9463c8eb775be24fbaef16","target":"graph","created_at":"2026-07-05T10:42:22Z","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/2504.00254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-Rank Adaptation (LoRA) has become a widely adopted technique for fine-tuning large-scale pre-trained models with minimal parameter updates. However, existing methods rely on fixed ranks or focus solely on either rank pruning or expansion, failing to adapt ranks dynamically to match the importance of different layers during training. In this work, we propose ElaLoRA, an adaptive low-rank adaptation framework that dynamically prunes and expands ranks based on gradient-derived importance scores. To the best of our knowledge, ElaLoRA is the first method that enables both rank pruning and expan","authors_text":"Andrew Sabot, Hong Jiang, H. T. Kung, Huandong Chang, Mingyuan Ma, Zhenting Qi, Zicheng Ma","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T21:58:25Z","title":"ElaLoRA: Elastic & Learnable Low-Rank Adaptation for Efficient Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00254","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":"sha256:484f652b7d18f4acdca788b507af407b0308e54213a05f52f73fc185300f2ddc","target":"record","created_at":"2026-07-05T10:42:22Z","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":"bea2afa46e3cf21754cc9e1a225dead65a2550f6bf351f9196993281404015aa","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T21:58:25Z","title_canon_sha256":"3e077da5bb93a8759bb7d7303f5311c093f64735a02135a0d12b4db7b8110fa2"},"schema_version":"1.0","source":{"id":"2504.00254","kind":"arxiv","version":1}},"canonical_sha256":"f7e1e4a2b8e6782850661315498e91927ee40e3cda7c1186992641a48f6263bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7e1e4a2b8e6782850661315498e91927ee40e3cda7c1186992641a48f6263bb","first_computed_at":"2026-07-05T10:42:22.551972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:22.551972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T6b8Pni8yTp+OXwJMkfCEZ4JEY/u6JjwASKlo8Fwzt3gkqGJJokAufxoIaX6ztNv3NfhcIpVtGiRxgYYX6/bAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:22.552434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:484f652b7d18f4acdca788b507af407b0308e54213a05f52f73fc185300f2ddc","sha256:14f09b353aefbb95cf80ea308587e799e6f66fb71a9463c8eb775be24fbaef16"],"state_sha256":"ec11405fd42f0df24614d343c918193d6b4827ea3b9ef99c4ce62d0f6c20190c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yjkbvEJmEss5RLbAC6AlSXWHz22KASLCFI2ZfHFkSN0mSuqzrWQNXilqQCwKjhj92wkKS9UAtSG9Lz8hOT3yAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:47:09.994323Z","bundle_sha256":"7ad12ef56bb926abf37cf19375c521136c15edc3aaa288e49ec5ab247323babb"}}