{"as_of":"2026-08-10T10:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e981038a0c804f9ac504fce4e729c31a21990c95ede766635dbc9a57108fc2b","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:03:14.342344Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-17T22:16:04.386706Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-17T22:16:04.891748Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"cited_work":{"arxiv_id":"2505.22934","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22934","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"6464693d-ea0f-4f5f-ac32-179c8c165859","year":2025},"citing_paper":{"arxiv_id":"2408.07666","last_updated":"2025-12-31T04:06:49Z","snapshot_observed_at":"2026-08-07T23:28:24.025478Z","submitted_at":"2024-08-14T16:58:48Z","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","version":5},"reference_index":288,"source":"pdf_text","source_observed_at":"2026-05-17T22:16:04.386706Z"},"links":{"cited_paper":"/paper/2505.22934","citing_paper":"/paper/2408.07666"},"observation_digest":"sha256:95d54198e4b9ac32152bf18abd0a29f1979d2195d42877f7fabb3b28932c2d7e","observation_id":"7b1ae573-3aa4-4420-9a66-3626ebef4cfd","resolution":{"observed_at":"2026-06-01T02:02:15.804469Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.22934/citation-record","integrity":"/paper/2505.22934/integrity","json":"/paper/2505.22934/citation-record.json","paper":"/paper/2505.22934"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T13:03:12.409270Z","title":"arXiv preprint arXiv:2407.21783","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.409270Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:956448a90f70043ef16c00e84fdc76f8781a0016d3d9cc72407cad86f2301922","observation_id":"f3221590-619f-490a-9701-07e148083f11","resolution":{"observed_at":"2026-08-07T13:03:12.409270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08994","last_updated":"2024-04-01T05:45:47Z","snapshot_observed_at":"2026-08-09T14:28:17.210379Z","submitted_at":"2024-03-13T23:25:30Z","title":"Ethos: Rectifying Language Models in Orthogonal Parameter Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08994","snapshot_observed_at":"2026-08-07T13:03:12.468319Z","title":"arXiv preprint arXiv:2403.08994","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.468319Z"},"links":{"cited_paper":"/paper/2403.08994","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:b3e7c79d77cea1119e8ab1cd7fa39aeefef722db9338a748430bea939bbb8e34","observation_id":"1b8f2b3f-b045-475d-9bfb-68a99d1f7e52","resolution":{"observed_at":"2026-08-07T13:03:12.468319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13656","last_updated":"2025-01-07T03:37:12Z","snapshot_observed_at":"2026-08-09T04:54:14.294842Z","submitted_at":"2024-08-24T19:14:02Z","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13656","snapshot_observed_at":"2026-08-07T13:03:12.563994Z","title":"arXiv preprint arXiv:2408.13656","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.563994Z"},"links":{"cited_paper":"/paper/2408.13656","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:08de4a384573d0a36578d321063e0a64a68fbec56ca00a7145607759de8e6d32","observation_id":"d75c328c-2c4d-42fc-b480-ad838db81328","resolution":{"observed_at":"2026-08-07T13:03:12.563994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17461","last_updated":"2024-09-27T11:34:05Z","snapshot_observed_at":"2026-07-06T18:20:48.343830Z","submitted_at":"2024-05-23T05:25:45Z","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17461","snapshot_observed_at":"2026-08-07T13:03:12.693254Z","title":"arXiv preprint arXiv:2405.17461","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.693254Z"},"links":{"cited_paper":"/paper/2405.17461","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:b0cdfeffea2f98ed23c6e3a9049692ae92d397639cd239a0ba984bce9fb6bb3b","observation_id":"716d6df1-c79c-4bdf-8f41-e68389ec52e4","resolution":{"observed_at":"2026-08-07T13:03:12.693254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04089","last_updated":"2023-03-31T15:27:01Z","snapshot_observed_at":"2026-08-03T22:12:27.993418Z","submitted_at":"2022-12-08T05:50:53Z","title":"Editing Models with Task Arithmetic","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04089","snapshot_observed_at":"2026-08-07T13:03:12.749204Z","title":"arXiv preprint arXiv:2212.04089","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.749204Z"},"links":{"cited_paper":"/paper/2212.04089","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:60a00288fbd483060281d4066ba09c7d484ee86ce6578769d24f2604e519e0c3","observation_id":"2756139f-e8ed-458a-ac20-2d9c44c2b829","resolution":{"observed_at":"2026-08-07T13:03:12.749204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09849","last_updated":"2025-05-21T23:53:00Z","snapshot_observed_at":"2026-08-07T00:34:34.195906Z","submitted_at":"2022-12-19T20:46:43Z","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09849","snapshot_observed_at":"2026-08-07T13:03:12.806623Z","title":"arXiv preprint arXiv:2212.09849","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.806623Z"},"links":{"cited_paper":"/paper/2212.09849","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:f68b7b85d5aaa609a328254e2f7f9dc1c3c1ce44e28e0b17327e68d4e602bf8e","observation_id":"e790b3d5-e126-4eb8-9eb0-1e062945b0f4","resolution":{"observed_at":"2026-08-07T13:03:12.806623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14735","last_updated":"2025-02-17T06:26:58Z","snapshot_observed_at":"2026-08-10T05:44:43.936093Z","submitted_at":"2024-10-16T20:27:15Z","title":"Agent Skill Acquisition for Large Language Models via CycleQD","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14735","snapshot_observed_at":"2026-08-07T13:03:12.864493Z","title":"arXiv preprint arXiv:2410.14735","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.864493Z"},"links":{"cited_paper":"/paper/2410.14735","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:d42c21e9116c1f11fc89cdd3ad7dec9b68cd039cbca8bdaedc220e9eb3a29014","observation_id":"73df85f8-c6a2-48ab-9a62-3a752ad23e6a","resolution":{"observed_at":"2026-08-07T13:03:12.864493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T13:03:12.971390Z","title":"arXiv preprint arXiv:1711.05101","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.971390Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:7b19c657636a49fcf67aceda4695b0584b6ab5df8bb56c97bf47e556c77015cb","observation_id":"cec4bdaf-9998-491e-a41b-203fcb8b1b0f","resolution":{"observed_at":"2026-08-07T13:03:12.971390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15479","last_updated":"2024-10-14T04:14:26Z","snapshot_observed_at":"2026-07-06T18:35:08.874127Z","submitted_at":"2024-06-17T02:31:55Z","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15479","snapshot_observed_at":"2026-08-07T13:03:13.027695Z","title":"arXiv preprint arXiv:2406.15479","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.027695Z"},"links":{"cited_paper":"/paper/2406.15479","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:cf29bf2246f321b097d74f1b0a84dcb921ebf4abb9100d7d1b61f6d7348cb65a","observation_id":"72de6dc0-9b2a-4704-92d6-da1a0c490a3f","resolution":{"observed_at":"2026-08-07T13:03:13.027695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13025","last_updated":"2024-12-02T06:40:50Z","snapshot_observed_at":"2026-08-10T10:18:23.819891Z","submitted_at":"2024-10-16T20:33:06Z","title":"LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13025","snapshot_observed_at":"2026-08-07T13:03:13.083909Z","title":"arXiv preprint arXiv:2410.13025","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.083909Z"},"links":{"cited_paper":"/paper/2410.13025","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:fa27acc7875e5eecc2e874eecb9ad0900b00da4fd1d345af42588d7a34bc2fbc","observation_id":"108405f3-383b-4a05-8fb5-c9c62358b95e","resolution":{"observed_at":"2026-08-07T13:03:13.083909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:03:15.184013Z","title":"Nevertheless, the merged performance remains largely preserved, demonstrating the effectiveness of our method","venue":null,"work_id":"e38922c9-1daf-4ee6-ad7a-64ce7e3124c3","year":2025},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:14.235760Z"},"links":{"citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:2d16d01f397a1d7cda54d31b5db439f9372e5b11095e0a18355bcc12511fd191","observation_id":"a39a45b8-e133-44be-a925-3734ad89c0ad","resolution":{"observed_at":"2026-08-07T13:03:15.308691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19735","last_updated":"2024-10-25T17:59:55Z","snapshot_observed_at":"2026-07-31T01:08:27.383308Z","submitted_at":"2024-10-25T17:59:55Z","title":"Model merging with SVD to tie the Knots","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19735","snapshot_observed_at":"2026-08-07T13:03:13.197354Z","title":"arXiv preprint arXiv:2410.19735","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.197354Z"},"links":{"cited_paper":"/paper/2410.19735","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:f744bf7e2c0c55b93c171f9764e60545090433e82e7e314cefe8a2f3fceab532","observation_id":"c58042e0-c3be-41fc-b2bb-deedf74120dc","resolution":{"observed_at":"2026-08-07T13:03:13.197354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04742","last_updated":"2024-03-11T10:07:08Z","snapshot_observed_at":"2026-08-10T08:11:07.796410Z","submitted_at":"2023-10-07T08:55:54Z","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04742","snapshot_observed_at":"2026-08-07T13:03:13.277297Z","title":"Transactions on Machine Learning Research","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.277297Z"},"links":{"cited_paper":"/paper/2310.04742","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:c2cb43000e7ed562f159d86e3a85e18d456e838efdc88969dcd7cfecff62020a","observation_id":"60297b49-ec46-4169-870f-2b682b248b4c","resolution":{"observed_at":"2026-08-07T13:03:13.277297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18607","last_updated":"2025-07-11T02:24:39Z","snapshot_observed_at":"2026-07-06T19:58:09.591787Z","submitted_at":"2024-11-27T18:53:41Z","title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.18607","snapshot_observed_at":"2026-08-07T13:03:13.382199Z","title":"arXiv preprint arXiv:2411.18607","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.382199Z"},"links":{"cited_paper":"/paper/2411.18607","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:dd9c00322e7303e03b3a976b451bfc806f41fae438bec1f894c43fc1a5bcdb04","observation_id":"591fe8c2-36a9-4b81-8a57-08829d2fbc5a","resolution":{"observed_at":"2026-08-07T13:03:13.382199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T13:03:13.473748Z","title":"arXiv preprint arXiv:2307.09288","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.473748Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:dbd7bdff0d191dc6c2c004123742322fa28fd59e0f9a283957035359c4a97e0a","observation_id":"07e8fcc8-811d-4927-8b95-05b72bf992d4","resolution":{"observed_at":"2026-08-07T13:03:13.473748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17146","last_updated":"2025-02-28T10:53:12Z","snapshot_observed_at":"2026-08-02T18:59:33.544719Z","submitted_at":"2024-10-22T16:26:05Z","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17146","snapshot_observed_at":"2026-08-07T13:03:13.606591Z","title":"In the Pro- ceedings of ICLR","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.606591Z"},"links":{"cited_paper":"/paper/2410.17146","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:4d30afaef39501b2477f73512f52ecb3651c3ab1883c136e71ca94a5c3da722c","observation_id":"1dba31c3-a6de-4516-ac55-b5667a848622","resolution":{"observed_at":"2026-08-07T13:03:13.606591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16167","last_updated":"2024-10-22T02:29:22Z","snapshot_observed_at":"2026-08-10T10:19:48.913452Z","submitted_at":"2024-09-24T15:08:41Z","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16167","snapshot_observed_at":"2026-08-07T13:03:13.828382Z","title":"arXiv preprint arXiv:2409.16167","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.828382Z"},"links":{"cited_paper":"/paper/2409.16167","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:b81df951e29db13e2274cc6b205dd78fe600b0671ee57a7ee29a850d7022f8c6","observation_id":"940480c6-7e4e-4ba8-8535-8f8a8a6a9212","resolution":{"observed_at":"2026-08-07T13:03:13.828382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11385","last_updated":"2024-06-27T16:01:28Z","snapshot_observed_at":"2026-07-06T18:32:06.826381Z","submitted_at":"2024-06-17T10:12:45Z","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11385","snapshot_observed_at":"2026-08-07T13:03:13.968064Z","title":"arXiv preprint arXiv:2406.11385","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.968064Z"},"links":{"cited_paper":"/paper/2406.11385","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:e138c8b4651a815ab06e8388abe4ca438f28a8a839ed850ff87f6cdb4d870d1f","observation_id":"4a4dd69e-d35a-48d0-afde-43736c00e3f6","resolution":{"observed_at":"2026-08-07T13:03:13.968064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:03:15.460243Z","title":"All the experiments are conducted on eight NVIDIA RTX A6000 GPUs","venue":null,"work_id":"509c329a-6181-43a3-98fd-76686e8ea3c9","year":2019},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:14.062405Z"},"links":{"citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:7dcdb36d85256b738f90ed31f9a12bdd65f558f3e125a15c3c7256f8cbac8194","observation_id":"b64e254a-b583-4685-9518-950d329cbbec","resolution":{"observed_at":"2026-08-07T13:03:15.622986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:03:14.903381Z","title":"Individual","venue":null,"work_id":"8cb35a7f-6ac4-4178-8400-11747b5b1043","year":2024},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:14.342344Z"},"links":{"citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:f9776336baaf27889a5e7be2c6423368dacce7bb26b154a8c9ad9dc1927b5d3b","observation_id":"91c6f069-5006-4180-bfdb-604a694fc046","resolution":{"observed_at":"2026-08-07T13:03:14.977210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00055","last_updated":"2017-07-31T20:12:06Z","snapshot_observed_at":"2026-08-04T03:50:51.013049Z","submitted_at":"2017-07-31T20:12:06Z","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00055","snapshot_observed_at":"2026-08-07T13:03:12.284996Z","title":"arXiv preprint arXiv:1708.00055","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.284996Z"},"links":{"cited_paper":"/paper/1708.00055","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:025c545a9103cabb5136c85b967fe6025666c595233225099faf4daf348a1a81","observation_id":"459b0f1a-33b6-4216-a33e-9079f80f2e02","resolution":{"observed_at":"2026-08-07T13:03:12.284996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.12471","last_updated":"2019-10-01T18:41:05Z","snapshot_observed_at":"2026-07-06T06:42:15.167440Z","submitted_at":"2018-05-31T13:52:06Z","title":"Neural Network Acceptability Judgments","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.12471","snapshot_observed_at":"2026-08-07T13:03:13.700940Z","title":"arXiv preprint 1805.12471","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.700940Z"},"links":{"cited_paper":"/paper/1805.12471","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:f4722772f5365ef08d7e1228b8a9260ed117ca827367f7b4d56bef875719c95a","observation_id":"099b5deb-fa5d-498b-a030-d986393a59b0","resolution":{"observed_at":"2026-08-07T13:03:13.700940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-07T13:03:12.917555Z","title":"arXiv preprint arXiv:1907.11692,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.917555Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:6160a50ac675f5033684911a2f57645a4df24118bcb0232b7a311bce721773ac","observation_id":"2195641f-97be-4392-a580-db008d822682","resolution":{"observed_at":"2026-08-07T13:03:12.917555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T13:03:12.638394Z","title":"arXiv preprint arXiv:2106.09685","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.638394Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:4bba7b752d1a95d3f40576ffc0eae4147077736a45b8f15b5964746ebfa1cc6b","observation_id":"ff1c04e1-e811-4b87-a959-52dbfd78c47c","resolution":{"observed_at":"2026-08-07T13:03:12.638394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.04836","last_updated":"2023-03-01T22:17:16Z","snapshot_observed_at":"2026-08-10T04:12:42.383543Z","submitted_at":"2022-09-11T10:44:27Z","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.04836","snapshot_observed_at":"2026-08-07T13:03:12.198439Z","title":"arXiv preprint arXiv:2209.04836","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.198439Z"},"links":{"cited_paper":"/paper/2209.04836","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:0f056b22e32b497f3928298628af5e7b493390c8b686d94cc798b14cba4e5d20","observation_id":"c6471c50-791f-4d31-9dd7-c0b3feff7bf5","resolution":{"observed_at":"2026-08-07T13:03:12.198439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03053","last_updated":"2024-03-13T02:04:06Z","snapshot_observed_at":"2026-08-04T16:00:39.222919Z","submitted_at":"2023-05-04T17:59:58Z","title":"ZipIt! Merging Models from Different Tasks without Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03053","snapshot_observed_at":"2026-08-07T13:03:13.110708Z","title":"arXiv preprint arXiv:2305.03053","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:13.110708Z"},"links":{"cited_paper":"/paper/2305.03053","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:419f469acf8abf52f516828e580146d37160925a8c21529b7545e17904141029","observation_id":"d7647234-63d5-492f-8cdc-2aca4ceba9f5","resolution":{"observed_at":"2026-08-07T13:03:13.110708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02396","last_updated":"2024-10-03T11:17:58Z","snapshot_observed_at":"2026-07-06T19:26:54.335667Z","submitted_at":"2024-10-03T11:17:58Z","title":"Parameter Competition Balancing for Model Merging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02396","snapshot_observed_at":"2026-08-07T13:03:12.342067Z","title":"arXiv preprint arXiv:2410.02396","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T13:03:12.342067Z"},"links":{"cited_paper":"/paper/2410.02396","citing_paper":"/paper/2505.22934"},"observation_digest":"sha256:1553e98483878134c1524d71311e40ad04d5e976d556f3783a12277ff5c3ac31","observation_id":"352a4688-1a74-4905-b3a7-10b49cc3aa1a","resolution":{"observed_at":"2026-08-07T13:03:12.342067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.22934","last_updated":"2026-05-28T18:21:08Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-10T10:19:55.731709Z","submitted_at":"2025-05-28T23:28:12Z","title":"Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2505.22934."}