{"as_of":"2026-08-21T05:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:75ed6c83fcd4b488b722ec3377dd99c8644f9e281cd6c05d7d678eb1e03bcdd3","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T11:58:39.003926Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T03:49:39.658872Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25414","snapshot_observed_at":"2026-08-03T03:49:39.658872Z","title":"and Ji, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.07218","last_updated":"2026-05-29T20:42:03Z","snapshot_observed_at":"2026-08-14T10:23:50.297310Z","submitted_at":"2026-02-06T21:59:40Z","title":"Collaborative and Efficient Fine-tuning: Leveraging Task Similarity","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-03T03:49:39.658872Z"},"links":{"cited_paper":"/paper/2509.25414","citing_paper":"/paper/2602.07218"},"observation_digest":"sha256:237cbd9fb93947d00baf01d16c76f91fd31cd8f07c5bfa47737d09ea842a8029","observation_id":"314344af-6f1d-48f2-8668-81b41432acdd","resolution":{"observed_at":"2026-08-03T03:49:39.658872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25414","snapshot_observed_at":"2026-07-14T06:34:55.089754Z","title":"Rethinking parameter sharing for llm fine-tuning with multiple loras,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.11163","last_updated":"2026-07-13T06:57:02Z","snapshot_observed_at":"2026-08-14T22:55:18.928901Z","submitted_at":"2026-07-13T06:57:02Z","title":"Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T06:34:55.089754Z"},"links":{"cited_paper":"/paper/2509.25414","citing_paper":"/paper/2607.11163"},"observation_digest":"sha256:4295c0bd6a631c37c70dac256bc30e2baccc3347cdab656ea2ea9029abe021b4","observation_id":"1e13dd72-06d9-4a50-a590-2089c1cca623","resolution":{"observed_at":"2026-07-14T06:34:55.089754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2509.25414/citation-record","integrity":"/paper/2509.25414/integrity","json":"/paper/2509.25414/citation-record.json","paper":"/paper/2509.25414"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":"2303.08774","doi":"10.1002/tea.20265","metadata_source":"pith","pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPT-4 Technical Report","venue":"cs.CL","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:f93d7b44510fdf50e14ff2b7aa27187dae77ff687785623c6942ff791d405ee7","observation_id":"285f5767-5067-4993-89cc-5c0b8b10225f","resolution":{"observed_at":"2026-05-18T12:01:21.188459Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.07883","last_updated":"2025-07-15T22:07:45Z","snapshot_observed_at":"2026-08-20T08:21:19.542297Z","submitted_at":"2025-07-10T16:06:02Z","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","version":3},"cited_work":{"arxiv_id":"2507.07883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07883","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Samo: A lightweight sharpness-aware approach for multi-task optimization with joint global-local perturbation.arXiv preprint arXiv:2507.07883","venue":null,"work_id":"c6c8d96a-5117-4181-a72e-df121d61a420","year":null},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2507.07883","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:8159a03b9ed48310870525130526dc8639666bbf3703b1a0f4c4b3e0dc78f926","observation_id":"237b4d15-59a0-4a4f-9670-19daf03d3532","resolution":{"observed_at":"2026-05-18T12:01:21.199581Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.11880","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fedalt: Federated fine-tuning through adaptive local training with rest-of-world lora.arXiv preprint arXiv:2503.11880","venue":null,"work_id":"7ad1ead7-680d-4c4a-86d5-10504fca108c","year":null},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:74706809cf32d49981de8b31517c92cdfecef25306f9d3847fb550358fcdb374","observation_id":"ad6d4819-7203-4f52-8aa6-28dabf3b6402","resolution":{"observed_at":"2026-05-18T12:01:21.140671Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.10945","last_updated":"2025-08-06T06:47:04Z","snapshot_observed_at":"2026-08-15T00:46:03.529876Z","submitted_at":"2025-01-19T04:56:55Z","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","version":3},"cited_work":{"arxiv_id":"2501.10945","doi":"10.48550/arxiv.2501.10945","metadata_source":"arxiv_reference","pith_arxiv_id":"2501.10945","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gradient-based multi-objective deep learning: Algorithms, theories, applications, and beyond","venue":"ArXiv.org","work_id":"a7d8924d-4346-4e15-ad9a-4f76d83c5f52","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2501.10945","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:0904effbd09243b4d98aea895f7b6ae73c9b47e124bc3e42cece7ddaec7da5a3","observation_id":"7ae9456a-0b9b-4c0b-b950-ebaa72fc891b","resolution":{"observed_at":"2026-05-18T12:01:21.183657Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Heterogeneous lora for fed- erated fine-tuning of on-device foundation models","venue":null,"work_id":"7c8116ee-aa6c-4867-a0a0-f9204f9c2d3e","year":2024},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:b1b9e741e7cf658819c0745f7d3cec10aad25e12ab7d9e6e52fb9642e6baf9fe","observation_id":"372d923f-7c7a-4b6e-9283-9c2512cdabfb","resolution":{"observed_at":"2026-05-18T12:01:21.784918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":"dead2d5c-2ad4-40b7-9cc8-87b1e112cfd0","year":2019},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:e62421f46c356c0094433cd29da3fc42f6c45c58f44cd895f6aceb8e1f31fa51","observation_id":"186053ec-877b-4abb-8a83-d456d4fcd029","resolution":{"observed_at":"2026-05-18T12:01:21.791673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-08-14T19:36:07.505691Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":"1803.05457","doi":"10.1162/tacl_a_00448.https://aclanthology.org/2022.tacl-1.5","metadata_source":"pith","pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","venue":"cs.AI","work_id":"28ea1282-d657-4c61-a83c-f1249be6d6b1","year":2018},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:6265755feab93504307fb2e6f42606800db806ec905e36445c429e4eeb571e3a","observation_id":"5e59e526-6acb-470b-a100-c7b13f104856","resolution":{"observed_at":"2026-05-18T12:01:21.110278Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":"2110.14168","doi":"10.1002/j.1545-","metadata_source":"pith","pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training Verifiers to Solve Math Word Problems","venue":"cs.LG","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":2021},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:cd001ec981e7a3a51f5b125517f5ae5673af1cf41ce2c7771716d068f15224c8","observation_id":"0838c22e-0a89-42b2-b7a4-93ca3adacae7","resolution":{"observed_at":"2026-05-18T12:01:21.177823Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.06261","last_updated":"2025-12-19T14:25:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-07T17:36:04Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","version":6},"cited_work":{"arxiv_id":"2507.06261","doi":"10.48550/arxiv.2503.19","metadata_source":"pith","pith_arxiv_id":"2507.06261","snapshot_observed_at":"2026-07-11T03:17:51.364436Z","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","venue":"cs.CL","work_id":"008df105-2fdd-45d8-857a-8e35868aecb6","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2507.06261","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:9478b4173b71d370993afab1437deb872d98c86d0547bd37e32c0f355c688b1c","observation_id":"3921b301-dffc-4911-88e6-0c49342c77ae","resolution":{"observed_at":"2026-05-18T12:01:21.172839Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Dongshang Deng, Xuangou Wu, Tao Zhang, Xiangyun Tang, Hongyang Du, Jiawen Kang, Jiqiang Liu, and Dusit Niyato","venue":null,"work_id":"c970f5ad-d406-4eca-ad11-240df986d1e6","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:a637fbcd0e1f172475125707083b5084cdcbc8bb6f7d4ff2c655155630b6771a","observation_id":"187f6b39-1f88-4e10-928d-551f3ae33ccf","resolution":{"observed_at":"2026-05-18T12:01:21.740795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Loramoe: Alleviating world knowledge forgetting in large language models via moe-style plugin","venue":null,"work_id":"f54739f8-63e5-4370-aa0c-5646718718b5","year":1932},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:e651b79ac7536168df6ada9a9220dd2d56e94f789ba017590a5bb612cb70c60f","observation_id":"f37c0fe3-5a71-49c8-b43b-d3abe593cd42","resolution":{"observed_at":"2026-05-18T12:01:21.774267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models","venue":null,"work_id":"b3856a09-69f5-4867-ac83-dd56925f6de2","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:a3ef5834333d5467ad8f454e675d716f1cea9d75a4d9d887c541808f288e2b3b","observation_id":"bd35b123-6067-4155-a080-d727af6e3a25","resolution":{"observed_at":"2026-05-18T12:01:21.777646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Mawps: A math word problem repository","venue":null,"work_id":"35c5eca6-d290-43dd-952d-022c05fd2d87","year":2016},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:976d6a8eaf626d267a3e4b64df6b824bb2b52f9b088d9c23d824e647eb16b4ba","observation_id":"59869abe-c2b2-44c0-953c-eeebefffa063","resolution":{"observed_at":"2026-05-18T12:01:21.770714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"1ccb54a8-7ae5-42d6-b3a2-961daa311421","year":2021},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:eb0a7b19a13bb848890a4f04219695cd34af74f71f2635a31913a8fa1847f8fd","observation_id":"9e6013b3-4c68-4b14-95db-6dd6c78cc3c9","resolution":{"observed_at":"2026-05-18T12:01:21.767604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03371","last_updated":"2020-08-07T20:45:12Z","snapshot_observed_at":"2026-08-14T20:23:06.504001Z","submitted_at":"2020-08-07T20:45:12Z","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","version":1},"cited_work":{"arxiv_id":"2008.03371","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2008.03371","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2008.03371 , year=","venue":null,"work_id":"81871c30-800b-4792-a94f-a3962601d737","year":2008},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2008.03371","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:3815cce1c5bbb8f1fc8f8a4eb4f5ba8156f067ce7b55ac51e3145b6ceca1dc2e","observation_id":"685ce54f-051d-4972-8d7f-008f9a1dd5d3","resolution":{"observed_at":"2026-05-18T12:01:21.167519Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.00661","last_updated":"2025-04-01T11:14:19Z","snapshot_observed_at":"2026-08-16T12:44:59.331610Z","submitted_at":"2025-04-01T11:14:19Z","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","version":1},"cited_work":{"arxiv_id":"2504.00661","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.00661","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dynmole: Boosting mixture of lora experts fine-tuning with a hybrid routing mechanism","venue":null,"work_id":"b9c1b9a1-2390-4c2b-89dc-ad5bab885342","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2504.00661","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:1230b5e95a06200f03d4fe3259eaf9ff2184efd667be7a946fdf71f1da235f51","observation_id":"fc4d66da-3ffd-4d03-93c9-f81682b2a87b","resolution":{"observed_at":"2026-05-18T12:01:21.151871Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.18640","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:49:44.465424Z","title":"Bgefl: Enabling communication-efficient federated learning via bandit gradient estimation in resource-constrained networks.IEEE Transactions on Networking, 2025b","venue":null,"work_id":"977facab-e848-4de9-bc59-c6355426fe17","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:556446002ab2cec83f4ba04e2607898441b90bf2154d627844b69436254ad03a","observation_id":"526aa889-1e83-45c5-87ec-6a6aa6ebea00","resolution":{"observed_at":"2026-05-18T12:01:21.130205Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12851","last_updated":"2024-02-20T09:30:48Z","snapshot_observed_at":"2026-08-18T09:40:41.097122Z","submitted_at":"2024-02-20T09:30:48Z","title":"MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models","version":1},"cited_work":{"arxiv_id":"2402.12851","doi":"10.48550/arxiv.2402.12851","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.12851","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Moelora: Contrastive learning guided mixture of experts on parameter-efficient fine-tuning for large language models","venue":"arXiv (Cornell University)","work_id":"4c3623d4-ea20-4210-b7ca-0374e0b7e099","year":2024},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2402.12851","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:ff53ef3768e776696cadad593660fdc2d049e94fe124ea338b722e4a496a1a94","observation_id":"6c75303b-ed94-44a0-a3eb-73df5018b2ba","resolution":{"observed_at":"2026-05-18T12:01:21.205507Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-15T03:08:17.7861+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-15T03:08:17.7861+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Can a suit of armor conduct elec- tricity? a new dataset for open book question answering","venue":null,"work_id":"1c438dfd-1bbb-4354-871b-5718031c2ddb","year":2018},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:b750423f92f229de6014dc8d36af5d03f5b0bdab1b37aafb671bafb6f77d6e63","observation_id":"6a2313bb-4323-4ba5-aa90-7435628dae61","resolution":{"observed_at":"2026-05-18T12:01:21.761119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"91671dce-713c-4dea-9dce-fc61e93722a7","year":2021},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:27467d76d2998c1ae296e3493f14f92e12108b81aa51f01dcdd56c3e15c5a0ee","observation_id":"9ff972c6-0526-4b26-88db-982ef39e79f7","resolution":{"observed_at":"2026-05-18T12:01:21.764386Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2211.13723","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T18:13:48.908106Z","title":"Improving multi-task learning via seeking task-based flat regions.arXiv preprint arXiv:2211.13723","venue":null,"work_id":"744248f9-428c-44a2-afdd-f181541f099f","year":2022},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:5d649cf79e659a61aed762c6615ac9da211b9e116ffc7decdf7b4498467cb903","observation_id":"18b91ce3-806c-4ada-8229-d1718ec2ee62","resolution":{"observed_at":"2026-05-18T12:01:21.157079Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2506.05568","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ravan: Multi-head low-rank adaptation for federated fine-tuning.arXiv preprint arXiv:2506.05568","venue":null,"work_id":"f9c408dc-bf8f-4e4b-bb6f-ca7466fdbef3","year":null},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:06182a0b842b97a43a96061055de2375978b058424123a9da64b63f10e86bfd1","observation_id":"e722d1cf-9d38-445f-98be-c443225ba0ba","resolution":{"observed_at":"2026-05-18T12:01:21.146573Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Social iqa: Common- sense reasoning about social interactions","venue":null,"work_id":"2617c5ef-3eb6-40ca-8dd7-318a075345ba","year":2019},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:0ff76c3e506d6608f75d290e6a860404e00fa57c4480be5120363bf2db8bda10","observation_id":"29e6820c-a3e9-4c8d-8e4d-919e5266e0ed","resolution":{"observed_at":"2026-05-18T12:01:21.757865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2307.09288","doi":"10.24963/ijcai.2025/706","metadata_source":"pith","pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","venue":"cs.CL","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:cc168bf5c51449f129cad1359573500c29f4c69b9be7d059006204f6d100a1bb","observation_id":"f9f7e3dc-10f1-49e3-a115-70a74f0f6c9e","resolution":{"observed_at":"2026-05-18T12:01:21.134824Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Aprompt: Attention prompt tuning for efficient adaptation of pre-trained language models","venue":null,"work_id":"22ff4fc8-dc6a-4d18-a6f9-c3f5afce0db0","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:3ca30d0c7fdd9a4e326b8a4f966988189014159f665b38ebe4dcc8773ebc5308","observation_id":"d892b6ba-d1b1-4f92-a28e-05348fb5f3ae","resolution":{"observed_at":"2026-05-18T12:01:21.747897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Mixture-of-subspaces in low-rank adapta- tion","venue":null,"work_id":"04439cd7-0424-42be-b304-b8c83822a8d0","year":2024},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:d74c6b5b18968cf9481f7b039f7aaf4d31b2a662fa772061fd74598ebc55a6c5","observation_id":"b4093c47-ee5a-4fdf-83cb-7a4e3b41a684","resolution":{"observed_at":"2026-05-18T12:01:21.751536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2501.00365","doi":"10.48550/arxiv.2501.00365","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Low-rank adaptation for foundation models: A comprehensive review.arXiv preprint arXiv:2501.00365","venue":"arXiv (Cornell University)","work_id":"fc75c475-18a1-4908-a0ab-4634ce635fc8","year":2024},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:39540c5f475583ea644bbd0440f826dbfbda3fc2647662ceeca578bd44fb102a","observation_id":"ef7be5d3-7969-4f74-bc2a-59239d0127c4","resolution":{"observed_at":"2026-05-18T12:01:21.124931Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-05-25T23:23:28.480934+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T23:23:28.480934+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22694","last_updated":"2025-05-28T12:32:09Z","snapshot_observed_at":"2026-08-17T09:56:52.008111Z","submitted_at":"2025-05-28T12:32:09Z","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","version":1},"cited_work":{"arxiv_id":"2505.22694","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22694","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"More: A mixture of low-rank experts for adaptive multi-task learning.arXiv preprint arXiv:2505.22694","venue":null,"work_id":"ab7cbbea-39de-4eee-a6d7-104f036d1c7c","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2505.22694","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:7cbdafcb223e93ea072444a8090bfebd78b496875b835c83873271aaec7d6f31","observation_id":"c436db0d-d2d5-400e-a280-6014667a2a94","resolution":{"observed_at":"2026-05-18T12:01:21.193961Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12213","last_updated":"2025-06-13T20:31:17Z","snapshot_observed_at":"2026-08-16T14:53:24.699190Z","submitted_at":"2025-06-13T20:31:17Z","title":"Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation","version":1},"cited_work":{"arxiv_id":"2506.12213","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12213","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"To- wards adaptive prefix tuning for parameter-efficient language model fine-tuning","venue":null,"work_id":"6035112a-c993-4e2f-a205-ea680fd6197a","year":null},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2506.12213","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:516ea7f24acd92a3ee01dc3e2ef33b9c4a7cb75f90681bef9ce30603faceb9e3","observation_id":"0ab99250-ab6f-4360-a65b-314433ffc06c","resolution":{"observed_at":"2026-05-18T12:01:21.162053Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.02411","last_updated":"2023-09-05T17:40:34Z","snapshot_observed_at":"2026-08-16T15:03:06.682102Z","submitted_at":"2023-09-05T17:40:34Z","title":"Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices","version":1},"cited_work":{"arxiv_id":"2309.02411","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.02411","snapshot_observed_at":"2026-07-04T19:10:05.841009Z","title":"Delta-lora: Fine-tuning high-rank parameters with the delta of low-rank matrices","venue":null,"work_id":"fa689478-6be8-4a21-b812-1a059e0af5f7","year":2023},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"cited_paper":"/paper/2309.02411","citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:5a51b7baac6760323f748ecd0002b09c808ad9d581e5cc12d0080e5e0f409543","observation_id":"975b06d7-dae1-43c9-ac5c-5da8b03fdc4a","resolution":{"observed_at":"2026-05-18T12:01:21.118378Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"SUPPLEMENTARYMATERIALS A ADDITIONALRELATEDWORK Parameter-efficient fine-tuning","venue":null,"work_id":"4ef22bb4-a1a6-4809-b21b-95dd3c6521a8","year":2019},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:6b7db719d453f409c65efe048cfef803e409bcce5a83d381d262e2d4976216c0","observation_id":"b9735c9b-2e2e-4686-afe5-51f04a0a402d","resolution":{"observed_at":"2026-05-18T12:01:21.733877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2d30f068-1203-4856-90bf-2eb8974c60f5","year":2012},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:ac250b630e3cfda57e59e4bdb4787f9f40dde14f1de7871f143c291dfba5eba5","observation_id":"82ec64cf-a1dc-4526-a272-4f6233cc0206","resolution":{"observed_at":"2026-05-18T12:01:21.754442Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Other methods examine MTL from the perspective of label noise (He et al., 2024), fairness (Navon et al., 2022; Ban & Ji","venue":null,"work_id":"867baa76-c831-47e4-82e3-c525dc4a6b6c","year":2021},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:b4fa16f70b8e1ef923cdf8c8582606f8aebab69e4b74045551eb85cf750a28aa","observation_id":"a6b11bd9-ca5d-45c9-9d54-fb087e9df5b6","resolution":{"observed_at":"2026-05-18T12:01:21.788534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"Federated learning","venue":null,"work_id":"7880dd60-4fc4-4f7b-bcad-c9dc4120e4a7","year":2022},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:3f0f21a155f377517554b49c9528a6afc2d2b5cb9926a83c8179c0f9c4bf177a","observation_id":"2aa67e03-1d8a-48b1-991b-8969769a5424","resolution":{"observed_at":"2026-05-18T12:01:21.781242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"10.0% CloQA 40.1% GenQA50.0% IE 24.8% OpnQA 25.3% Figure 7: Data distribution of clients","venue":null,"work_id":"4e689e47-f606-4318-b103-2d9166dc2f3c","year":2025},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:08da453a146bf9ce53915ca6a3f285df530e0b7603de92a2ef7e258c46c0eee9","observation_id":"17cf1b36-6679-4679-983a-c7244e53c8ad","resolution":{"observed_at":"2026-05-18T12:01:21.737583Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-06-05T21:23:00.469572Z","title":"The methods are applied toq proj andv proj modules","venue":null,"work_id":"2ea49f39-c689-4ff8-a9ca-743f8728e524","year":2018},"citing_paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-18T11:58:39.003926Z"},"links":{"citing_paper":"/paper/2509.25414"},"observation_digest":"sha256:8524db5cbf5f1c3f1fb852d7e48455e742c4ed0c8cc645e716c6fd3b3ff2b5b3","observation_id":"bc5bfe00-3a82-45b8-8d8d-ab2eadc5cd61","resolution":{"observed_at":"2026-05-18T12:01:21.744355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.25414","last_updated":"2026-04-24T20:59:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T10:23:03.892400Z","submitted_at":"2025-09-29T19:16:14Z","title":"Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":18,"verified_fuzzy":15},"total_outbound_references":36},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2509.25414."}