{"as_of":"2026-08-09T19:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ef5e6f3e28f2635497f40866eafe878e4a801c3b78ed4673264f455dc1db7dc","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":55,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T14:27:57.474822Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":7,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2310.01728","last_updated":"2024-01-29T06:27:53Z","snapshot_observed_at":"2026-08-04T04:31:27.172482Z","submitted_at":"2023-10-03T01:31:25Z","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-05-16T16:03:17.015913Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2310.01728"},"observation_digest":"sha256:640f315ceab315a2ab7cf21ecc090a2e2800617e1540c52b17f15a5b38bf49f2","observation_id":"0b712967-d477-4fcc-a01b-d7d5c76cbbd6","resolution":{"observed_at":"2026-05-16T16:03:17.083782Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-13T11:32:36.738536Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2403.14608"},"observation_digest":"sha256:1e69cda9dd048f4b7de22ec8deaf66cae8cfaae4c8772e895fc904d3fb26cc7f","observation_id":"289cb62e-db3d-4d26-9c7a-771d383c2802","resolution":{"observed_at":"2026-05-13T11:32:37.013099Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-09T14:27:57.474822Z","title":"Y., Pang, T., Du, C., and Lin, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01804","last_updated":"2025-02-03T20:33:20Z","snapshot_observed_at":"2026-08-09T14:21:38.248358Z","submitted_at":"2025-02-03T20:33:20Z","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T14:27:57.474822Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2502.01804"},"observation_digest":"sha256:5dffea97b1d1857e9c297f8c6fb4d9de553c802f367109b47ca71a88fcdec10e","observation_id":"b40ae42d-0f3e-4bb2-b432-76a066acc317","resolution":{"observed_at":"2026-08-09T14:27:57.474822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-08T22:33:09.330446Z","title":"Y., Pang, T., Du, C., and Lin, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.04506","last_updated":"2025-02-06T21:13:44Z","snapshot_observed_at":"2026-08-09T04:44:07.719948Z","submitted_at":"2025-02-06T21:13:44Z","title":"When One LLM Drools, Multi-LLM Collaboration Rules","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T22:33:09.330446Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2502.04506"},"observation_digest":"sha256:b9840add686fc24b8a210788017374618b7f4a6577e4efc5551536e9e7e363ac","observation_id":"6929ccfa-8663-44ef-b91e-c6cde3429088","resolution":{"observed_at":"2026-08-08T22:33:09.330446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-08T21:03:23.697544Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.04923","last_updated":"2025-02-07T13:41:51Z","snapshot_observed_at":"2026-08-08T20:55:55.679816Z","submitted_at":"2025-02-07T13:41:51Z","title":"Cached Multi-Lora Composition for Multi-Concept Image Generation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T21:03:23.697544Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2502.04923"},"observation_digest":"sha256:d0e5490e2d13fce8569fd559ce195fa5cbf902a9d28d88944f851dc2972181c3","observation_id":"9b270e29-5965-4e10-b6ae-5931e57cdfa2","resolution":{"observed_at":"2026-08-08T21:03:23.697544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-08T17:26:09.280199Z","title":"Lorahub: Effi- cient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.05932","last_updated":"2025-03-16T11:57:19Z","snapshot_observed_at":"2026-08-09T04:00:24.605103Z","submitted_at":"2025-02-09T15:22:38Z","title":"Skill Expansion and Composition in Parameter Space","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-08T17:26:09.280199Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2502.05932"},"observation_digest":"sha256:41c5985c696502c90560b1edeabd0ab8fcc892d37aa6bf804c34942340ee6577","observation_id":"7b3463b7-b000-46d6-8908-5ec41306d2b8","resolution":{"observed_at":"2026-08-08T17:26:09.280199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T15:18:30.942304Z","title":"Lo- rahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15798","last_updated":"2025-05-21T17:51:05Z","snapshot_observed_at":"2026-08-09T06:40:37.968154Z","submitted_at":"2025-05-21T17:51:05Z","title":"Model Merging is Secretly Certifiable: Non-Vacuous Generalisation Bounds for Low-Shot Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:18:30.942304Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.15798"},"observation_digest":"sha256:7154fbac66eabc81a1975a31cc6f140d3248d1c7317283d09940e4cb7fbd4eda","observation_id":"0187f126-abfb-43a7-a20d-0a351751c25e","resolution":{"observed_at":"2026-08-07T15:18:30.942304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T14:36:20.045160Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18494","last_updated":"2025-05-24T04:12:12Z","snapshot_observed_at":"2026-08-09T13:16:27.056248Z","submitted_at":"2025-05-24T04:12:12Z","title":"FedHL: Federated Learning for Heterogeneous Low-Rank Adaptation via Unbiased Aggregation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:36:20.045160Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.18494"},"observation_digest":"sha256:177e836f1c860a6ec30aea9a7c82a5945110c32e7b77d1b72dd81ce683bdcfb7","observation_id":"9a931ea0-777c-4a64-897a-a286d0474af7","resolution":{"observed_at":"2026-08-07T14:36:20.045160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T14:30:20.027038Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18713","last_updated":"2025-05-24T14:27:20Z","snapshot_observed_at":"2026-08-09T18:45:55.540800Z","submitted_at":"2025-05-24T14:27:20Z","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:30:20.027038Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.18713"},"observation_digest":"sha256:6e2603a4de0094a05ecaa0385a15ad4989032c1fbb938e9662fb9164a76eb8bf","observation_id":"3d836108-1cb7-45ec-8162-aaac8afee9b8","resolution":{"observed_at":"2026-08-07T14:30:20.027038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T14:27:25.173916Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18867","last_updated":"2025-05-24T21:01:35Z","snapshot_observed_at":"2026-08-08T00:50:24.909244Z","submitted_at":"2025-05-24T21:01:35Z","title":"Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T14:27:25.173916Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.18867"},"observation_digest":"sha256:97626dd940a6f2fd00baaac2627ac4480d448040524cc968c13d7bbbb3df8a60","observation_id":"091aae92-11f3-404d-b488-a26cc0f0bb13","resolution":{"observed_at":"2026-08-07T14:27:25.173916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T13:58:12.917042Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20525","last_updated":"2025-05-26T21:05:28Z","snapshot_observed_at":"2026-08-07T13:50:25.311474Z","submitted_at":"2025-05-26T21:05:28Z","title":"MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:12.917042Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.20525"},"observation_digest":"sha256:1b7d442d3248dc7ddac32e62b86273cb7fecd26f08a1905f1c37c7b5b1d94593","observation_id":"056ee1f7-abd7-4fa1-be24-5029c697d236","resolution":{"observed_at":"2026-08-07T13:58:12.917042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T13:44:33.469848Z","title":"Lo- rahub: Efficient cross-task generalization via dynamic lora composition.arXiv preprint arXiv:2307.13269, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21226","last_updated":"2025-06-03T14:43:50Z","snapshot_observed_at":"2026-08-09T03:32:40.483446Z","submitted_at":"2025-05-27T14:10:46Z","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:33.469848Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2505.21226"},"observation_digest":"sha256:8772919b2f38a4726c8c2b2fa1a326d6c26fe5d514e0a63cbfe227ba9af2f909","observation_id":"f0422f54-d67a-40e6-af3e-8cd41f517f1e","resolution":{"observed_at":"2026-08-07T13:44:33.469848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T12:09:12.947347Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00495","last_updated":"2025-05-31T10:27:08Z","snapshot_observed_at":"2026-08-09T08:51:32.281143Z","submitted_at":"2025-05-31T10:27:08Z","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:09:12.947347Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2506.00495"},"observation_digest":"sha256:31d346a3dd92929dcc0d62ab2d832bbd0bc8182989e3f78d5ec756b50253f92c","observation_id":"59efa1c4-7256-4603-85e4-1dddbf36c5c0","resolution":{"observed_at":"2026-08-07T12:09:12.947347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T10:18:24.052738Z","title":"Y ., Pang, T., Du, C., and Lin, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05713","last_updated":"2025-07-27T08:06:57Z","snapshot_observed_at":"2026-08-08T06:35:08.618663Z","submitted_at":"2025-06-06T03:33:06Z","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T10:18:24.052738Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2506.05713"},"observation_digest":"sha256:9b2e3eb1dee73a330d0824b3d17e66ca22061997309abea6315dc16207fb7fad","observation_id":"75878931-2665-4e4d-b2e7-2494b4d9cdde","resolution":{"observed_at":"2026-08-07T10:18:24.052738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T06:04:30.151824Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition.arXiv preprint arXiv:2307.13269, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06266","last_updated":"2025-06-13T17:58:55Z","snapshot_observed_at":"2026-08-07T05:54:59.580995Z","submitted_at":"2025-06-06T17:48:23Z","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:30.151824Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2506.06266"},"observation_digest":"sha256:6d86dfdd4a4e7dc332a86585a003372104e877511e8939ec6f83936de32cc05a","observation_id":"45ecebc8-ea23-474c-9aa1-817af1ba0b3b","resolution":{"observed_at":"2026-08-07T06:04:30.151824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T05:41:31.038292Z","title":"Lo- rahub: Efficient cross-task generalization via dynamic lora composition.arXiv preprint arXiv:2307.13269, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07280","last_updated":"2025-06-10T11:37:10Z","snapshot_observed_at":"2026-08-09T17:26:05.683665Z","submitted_at":"2025-06-08T20:52:34Z","title":"From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:41:31.038292Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2506.07280"},"observation_digest":"sha256:c727a03b13297343fa2c62ed3b6868688ede874145f8689fea64e265970fb5ce","observation_id":"3b29580e-2e53-47c1-9b1b-a1f72d26afbe","resolution":{"observed_at":"2026-08-07T05:41:31.038292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-07T04:09:24.687837Z","title":"Y ., Pang, T., Du, C., and Lin, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.11638","last_updated":"2025-06-13T10:11:01Z","snapshot_observed_at":"2026-08-09T06:20:14.015637Z","submitted_at":"2025-06-13T10:11:01Z","title":"LoRA-Gen: Specializing Large Language Model via Online LoRA Generation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T04:09:24.687837Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2506.11638"},"observation_digest":"sha256:6c28afb926c182456ed7070d8eb171c758bff466bb5367c486582a54617a89c4","observation_id":"712ba173-b534-498d-8a7f-9ce9e02797b4","resolution":{"observed_at":"2026-08-07T04:09:24.687837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2507.00029","last_updated":"2026-05-13T05:28:39Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-17T14:58:54Z","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-19T09:05:25.236355Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2507.00029"},"observation_digest":"sha256:4ea2eb830a3add1ed8ee4e93c0f570867c8ee4dc7f13e3f9a73c43f8eb167113","observation_id":"9814c6e9-d4b1-496e-a5b1-b59cf8f1de35","resolution":{"observed_at":"2026-05-19T09:07:14.676848Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-06T19:25:28.175661Z","title":"Lorahub: Efficient cross- task generalization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.05678","last_updated":"2025-07-08T05:00:17Z","snapshot_observed_at":"2026-08-06T19:17:57.988428Z","submitted_at":"2025-07-08T05:00:17Z","title":"LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:25:28.175661Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2507.05678"},"observation_digest":"sha256:70d7f5c1a9c001b704c92af9249450941b05f77144dbe5e3208dd4d158a256d9","observation_id":"8297e1c4-b74b-4044-b004-dc1303d9888e","resolution":{"observed_at":"2026-08-06T19:25:28.175661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-06T19:07:35.140559Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07140","last_updated":"2025-07-14T04:57:05Z","snapshot_observed_at":"2026-08-07T03:13:31.294588Z","submitted_at":"2025-07-09T03:25:45Z","title":"Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T19:07:35.140559Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2507.07140"},"observation_digest":"sha256:e12fac1f0e65cc8cca130e20c0a243bcccff3781e1ed856f980b1c75599dfc6a","observation_id":"88e4e900-82aa-4c00-815d-1a88128a8f51","resolution":{"observed_at":"2026-08-06T19:07:35.140559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-06T01:01:49.129551Z","title":"Y.; Pang, T.; Du, C.; and Lin, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.03999","last_updated":"2025-08-06T01:26:43Z","snapshot_observed_at":"2026-08-06T01:01:43.978821Z","submitted_at":"2025-08-06T01:26:43Z","title":"Tensorized Clustered LoRA Merging for Multi-Task Interference","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T01:01:49.129551Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2508.03999"},"observation_digest":"sha256:3ec48d07f05b564692ef3910903010c650000186ed8540396a99069380f8bd9b","observation_id":"aa5382ff-6992-4ef0-9f31-3da0570f372e","resolution":{"observed_at":"2026-08-06T01:01:49.129551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T12:54:05.429528Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.01158","last_updated":"2025-09-09T07:14:16Z","snapshot_observed_at":"2026-08-05T12:54:04.080007Z","submitted_at":"2025-09-01T06:28:33Z","title":"Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-05T12:54:05.429528Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2509.01158"},"observation_digest":"sha256:8c50434f70d92755b419136985490fbb3e435e2dfbbdaa9f18cfa0dde7a0b5c8","observation_id":"c00e9c35-9d85-44da-9e8b-2f01249c3ce2","resolution":{"observed_at":"2026-08-05T12:54:05.429528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T05:37:05.950405Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition.arXiv preprint arXiv:2307.13269,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10535","last_updated":"2025-09-05T14:43:41Z","snapshot_observed_at":"2026-08-06T07:07:31.562426Z","submitted_at":"2025-09-05T14:43:41Z","title":"Semantic-guided LoRA Parameters Generation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T05:37:05.950405Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2509.10535"},"observation_digest":"sha256:559c70befbfe01e2ec7ed86e07bd64af4acca234df8520b0d897541810781e20","observation_id":"b00fdbd6-519d-42ad-9c4c-d066329759de","resolution":{"observed_at":"2026-08-05T05:37:05.950405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-03T23:37:55.781717Z","title":"arXiv preprint arXiv:2307.13269(2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.07457","last_updated":"2026-07-20T02:41:15Z","snapshot_observed_at":"2026-08-06T01:49:16.929228Z","submitted_at":"2025-11-06T21:56:58Z","title":"GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T23:37:55.781717Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2511.07457"},"observation_digest":"sha256:b2de3830d924574101454eb09aff26e952c462e0cc1e63b7312eb8b9331e44b5","observation_id":"1c3460a2-315e-4135-b7db-f1f8ca6f0e8e","resolution":{"observed_at":"2026-08-03T23:37:55.781717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2604.19048","last_updated":"2026-04-21T03:55:02Z","snapshot_observed_at":"2026-07-06T23:05:48.885141Z","submitted_at":"2026-04-21T03:55:02Z","title":"SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-05-10T02:26:55.896058Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2604.19048"},"observation_digest":"sha256:99fdd825894419c51633e5b6d10d7d36af37378879b3a930f69c0ebef70ec150","observation_id":"7db980d0-f40e-4964-be05-0818cbe9f3fb","resolution":{"observed_at":"2026-05-10T02:27:36.476640Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2604.21571","last_updated":"2026-04-23T11:51:31Z","snapshot_observed_at":"2026-07-06T23:08:10.140279Z","submitted_at":"2026-04-23T11:51:31Z","title":"Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-09T22:26:34.487400Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2604.21571"},"observation_digest":"sha256:a421c0819402a063d6b165c5a19f2d6007d942bf08d35c30f2177e2f038fcc57","observation_id":"2ca2ca2b-2cb8-413f-a1ab-bef4a28f1c80","resolution":{"observed_at":"2026-05-09T22:34:07.445943Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2604.21905","last_updated":"2026-04-23T17:50:23Z","snapshot_observed_at":"2026-07-06T23:08:23.939574Z","submitted_at":"2026-04-23T17:50:23Z","title":"Low-Rank Adaptation Redux for Large Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-09T21:48:48.992712Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2604.21905"},"observation_digest":"sha256:beb2d2b073e2f3052e5fc8ca78dd431e5d6d9db8fbfb09fd9ed05b5fe14e7a71","observation_id":"f8dc5272-40e0-4a2c-a115-4cd1e538baf2","resolution":{"observed_at":"2026-05-11T14:26:03.912220Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2604.23750","last_updated":"2026-05-11T16:19:42Z","snapshot_observed_at":"2026-08-02T22:26:32.919600Z","submitted_at":"2026-04-26T14:59:14Z","title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-08T06:39:00.768904Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2604.23750"},"observation_digest":"sha256:e2213376dc66088482779aaa0f627011a381a29cc1406d9101bc4ac61c4d922f","observation_id":"83fd2a8d-6413-4ed2-814b-4736b7368b4b","resolution":{"observed_at":"2026-05-11T21:11:09.985837Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2604.23750","last_updated":"2026-05-11T16:19:42Z","snapshot_observed_at":"2026-08-02T22:26:32.919600Z","submitted_at":"2026-04-26T14:59:14Z","title":"The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T03:21:58.428036Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2604.23750"},"observation_digest":"sha256:9fdcb766df6aa886381c2a1def65116fdf95cc7b0e6aeba2ca4997c432c0e362","observation_id":"5c5da74b-3c5b-4c47-9b79-805fc00a51f3","resolution":{"observed_at":"2026-05-12T07:21:26.842211Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.04079","last_updated":"2026-04-14T16:32:50Z","snapshot_observed_at":"2026-07-06T23:16:54.673178Z","submitted_at":"2026-04-14T16:32:50Z","title":"Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T15:42:17.370111Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.04079"},"observation_digest":"sha256:e7576cf79426843bd07578b2646208da67cbca62a3d1f22a750467821f47c3ea","observation_id":"6d3081a0-d7ac-4752-9824-850483b728e8","resolution":{"observed_at":"2026-05-11T10:01:01.186979Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.12345","last_updated":"2026-05-12T16:21:43Z","snapshot_observed_at":"2026-08-02T19:24:50.214261Z","submitted_at":"2026-05-12T16:21:43Z","title":"Output Composability of QLoRA PEFT Modules for Plug-and-Play Attribute-Controlled Text Generation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-13T04:32:30.631217Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.12345"},"observation_digest":"sha256:dc95331dcd3fd5f6b77c183495ac4d50fd8e1681cea1e8d13138ebf6961f9aef","observation_id":"82575656-e725-4fbd-948f-740a9197edd1","resolution":{"observed_at":"2026-05-13T04:37:15.924237Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.14055","last_updated":"2026-05-13T19:25:56Z","snapshot_observed_at":"2026-08-01T07:49:53.576982Z","submitted_at":"2026-05-13T19:25:56Z","title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-15T05:25:38.967645Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.14055"},"observation_digest":"sha256:442e7f4b9f292ae3561d009b14cbb15d7f3e62b40ac88fd238fc96618c5dd80f","observation_id":"438803ec-618f-4807-ad0c-39e237afe02b","resolution":{"observed_at":"2026-05-15T05:29:48.367727Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.14084","last_updated":"2026-06-09T19:01:29Z","snapshot_observed_at":"2026-07-06T23:25:34.835136Z","submitted_at":"2026-05-13T20:09:35Z","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-15T04:45:39.641535Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.14084"},"observation_digest":"sha256:32548f36609d579f96e7611a8c604d56577107aa043ebbae0a6a3da7074f7034","observation_id":"4c3ebcc2-a4d1-4dd7-9ab2-7557b50108c1","resolution":{"observed_at":"2026-05-15T04:49:44.558381Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.14084","last_updated":"2026-06-09T19:01:29Z","snapshot_observed_at":"2026-07-06T23:25:34.835136Z","submitted_at":"2026-05-13T20:09:35Z","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-30T21:12:37.353935Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.14084"},"observation_digest":"sha256:8e4494298198c77751697a2556807f41b51d5ee43df7bf68791cac9b6adc7e97","observation_id":"0ea84ac0-0d71-4aac-98ad-272b106c8419","resolution":{"observed_at":"2026-06-30T21:15:04.213610Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.15207","last_updated":"2026-07-08T14:36:15Z","snapshot_observed_at":"2026-07-12T17:52:34.996306Z","submitted_at":"2026-05-01T23:42:57Z","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-05-19T18:01:06.649723Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.15207"},"observation_digest":"sha256:ce2604c8a3d562407bb85ec3e9e0b6f9a1825ab36d3936050ca1921cb53f7069","observation_id":"d8d9bf74-67e9-4768-ae99-b5374be9b251","resolution":{"observed_at":"2026-05-19T18:02:42.330507Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.16727","last_updated":"2026-05-16T00:29:35Z","snapshot_observed_at":"2026-08-09T13:41:57.056244Z","submitted_at":"2026-05-16T00:29:35Z","title":"PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-19T21:37:56.570173Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.16727"},"observation_digest":"sha256:04a0a0fb34bebe2892da1b2cad565630e311af171d92826ef026bcf252d0f285","observation_id":"e31b7214-9d1a-47ce-a17a-81103f1432bd","resolution":{"observed_at":"2026-05-19T21:42:48.077383Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.19042","last_updated":"2026-05-18T19:05:40Z","snapshot_observed_at":"2026-07-06T23:29:47.081347Z","submitted_at":"2026-05-18T19:05:40Z","title":"Interference-Aware Multi-Task Unlearning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-20T10:25:57.025905Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.19042"},"observation_digest":"sha256:cf0af22a47644dbd6c2960d6cfaaacd26bf76f926d2cf1b3c11462cbde3d8722","observation_id":"c36e1f09-e3b9-43a8-a4f5-74b933c44718","resolution":{"observed_at":"2026-05-20T10:28:12.050579Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.29498","last_updated":"2026-05-28T07:22:39Z","snapshot_observed_at":"2026-07-06T23:38:56.014434Z","submitted_at":"2026-05-28T07:22:39Z","title":"Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T07:36:24.624420Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.29498"},"observation_digest":"sha256:861d4f76021349f005e868d96c359ac7466cc8350091974a0212caa06d1ef5d4","observation_id":"6b0266d1-8286-4e6b-beca-ceb984155718","resolution":{"observed_at":"2026-06-29T07:43:14.087091Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2605.29569","last_updated":"2026-06-07T04:09:10Z","snapshot_observed_at":"2026-08-07T19:41:57.092904Z","submitted_at":"2026-05-28T08:17:28Z","title":"LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T06:39:15.694127Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2605.29569"},"observation_digest":"sha256:99921583b076ed7942651f904d47e40759dc80482b60f31d24f3b85aa1b0c70b","observation_id":"9c2e5115-40e9-4f11-927e-ef3ed8753c0c","resolution":{"observed_at":"2026-06-29T14:33:30.981000Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.01858","last_updated":"2026-06-01T08:10:25Z","snapshot_observed_at":"2026-07-06T23:42:21.252086Z","submitted_at":"2026-06-01T08:10:25Z","title":"Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-06-28T15:07:03.439928Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.01858"},"observation_digest":"sha256:2fe617cabd5a9c8693154e298560a298496e60aff4c3313a2746a555e89b70e9","observation_id":"6d1b9797-41a7-4de9-a99e-fef8a56dae07","resolution":{"observed_at":"2026-07-01T22:46:18.652144Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.03723","last_updated":"2026-06-02T14:42:46Z","snapshot_observed_at":"2026-07-06T23:43:55.632508Z","submitted_at":"2026-06-02T14:42:46Z","title":"Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T11:24:45.010310Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.03723"},"observation_digest":"sha256:1efe5032e61774c2bc569564cc13f7a4ded77e44185aadb7ccbc18614453a36a","observation_id":"985d7a21-0e7e-4eec-85c3-52bab4ec8c2a","resolution":{"observed_at":"2026-07-02T01:56:27.671576Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.03979","last_updated":"2026-07-10T17:52:03Z","snapshot_observed_at":"2026-07-15T23:18:25.559225Z","submitted_at":"2026-06-02T17:56:55Z","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-28T10:56:13.058872Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.03979"},"observation_digest":"sha256:1012f8399722d83c97c67f2e32739291cdfa6737742f64d609b4a42824219b50","observation_id":"e09cbf6c-750e-4b28-8e5a-dab20b374c2e","resolution":{"observed_at":"2026-07-02T02:26:26.720149Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-07-13T07:44:25.325808Z","title":"Lorahub: Efficient cross-task generalization via dynamic lora composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03979","last_updated":"2026-07-10T17:52:03Z","snapshot_observed_at":"2026-07-15T23:18:25.559225Z","submitted_at":"2026-06-02T17:56:55Z","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-13T07:44:25.325808Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.03979"},"observation_digest":"sha256:d7e4330384fef9cd306b6b5b56fc93805525724c93adb3206332db51b15ac9ab","observation_id":"7ca25be4-2451-41d4-8aac-d37606628cfe","resolution":{"observed_at":"2026-07-13T07:44:25.325808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.05889","last_updated":"2026-06-04T08:58:57Z","snapshot_observed_at":"2026-07-06T23:45:47.161248Z","submitted_at":"2026-06-04T08:58:57Z","title":"GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-27T23:53:55.385445Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.05889"},"observation_digest":"sha256:d3054dd548b1ba72643496b3f609eeb0cd5a9150466c966319f1de8a87c81bba","observation_id":"d9e54ee7-178a-4d15-9602-cbbe59d9e1e3","resolution":{"observed_at":"2026-07-02T15:27:04.861463Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.06492","last_updated":"2026-06-04T17:59:46Z","snapshot_observed_at":"2026-08-08T09:46:24.994823Z","submitted_at":"2026-06-04T17:59:46Z","title":"Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-06-28T00:05:29.087525Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.06492"},"observation_digest":"sha256:5f9047607d217356f248d21c05f70f63c2d855a9640eadebdb79f80bb5211dd4","observation_id":"9f84f579-7350-4564-858e-16c9d3a4d657","resolution":{"observed_at":"2026-07-02T15:07:04.824829Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.11712","last_updated":"2026-06-10T06:39:20Z","snapshot_observed_at":"2026-07-31T05:34:22.696346Z","submitted_at":"2026-06-10T06:39:20Z","title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-06-27T09:58:16.639702Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.11712"},"observation_digest":"sha256:a2eb33e7c8054b2aaeba47f6e4ddcf6b367ff9247a44676af88c642147408af3","observation_id":"93955428-8773-4afb-bb04-60b0b84b4cd6","resolution":{"observed_at":"2026-07-03T10:27:57.082610Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.19079","last_updated":"2026-06-17T13:50:51Z","snapshot_observed_at":"2026-08-06T12:44:16.039483Z","submitted_at":"2026-06-17T13:50:51Z","title":"ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-26T20:53:11.180717Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.19079"},"observation_digest":"sha256:b9f428694f1980dbc2670a5738cbc4621d5c1dee6d4a668ddacf38e98a4060ee","observation_id":"a1334558-a918-4255-9270-f7de6d87a922","resolution":{"observed_at":"2026-07-04T00:49:19.539395Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.19172","last_updated":"2026-06-17T15:15:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-06-17T15:15:19Z","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-06-26T20:37:01.382431Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.19172"},"observation_digest":"sha256:5d2881709a3e8dbbbeb807faa2e179d3635a40661f6ffe8c0361d16e95a7cb73","observation_id":"4c2ca41f-2337-4fa7-b2a9-085b964e850e","resolution":{"observed_at":"2026-07-04T01:09:19.461320Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":"2307.13269","doi":"10.48550/arxiv.2307.13269","metadata_source":"arxiv_reference","pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huang, Q","venue":"arXiv (Cornell University)","work_id":"66ee831a-2b33-423d-87ec-ba52b341a21b","year":2023},"citing_paper":{"arxiv_id":"2606.19549","last_updated":"2026-06-17T19:40:51Z","snapshot_observed_at":"2026-08-02T14:09:04.600861Z","submitted_at":"2026-06-17T19:40:51Z","title":"Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-06-26T21:01:04.043286Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2606.19549"},"observation_digest":"sha256:0055fe813c829c78fd58163396daa72345f773cf19575aa1653c6f7d06d98b50","observation_id":"605d9910-bb74-45ca-81a6-babd010b07b8","resolution":{"observed_at":"2026-07-04T00:49:17.725222Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T21:53:05.128527+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-07-11T08:38:02.220727Z","title":"Huang, Q","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.05114","last_updated":"2026-07-06T14:06:18Z","snapshot_observed_at":"2026-08-02T14:03:06.708038Z","submitted_at":"2026-07-06T14:06:18Z","title":"Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T08:38:02.220727Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.05114"},"observation_digest":"sha256:4693583f32c65bc851ed98b714d15df0b7012832f71f3ff910101c3089bc69fa","observation_id":"33836869-1ece-4c18-91d7-2696433ca496","resolution":{"observed_at":"2026-07-11T08:38:02.220727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-07-14T07:52:08.823198Z","title":"arXiv preprint arXiv:2307.13269 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.10985","last_updated":"2026-07-13T01:18:32Z","snapshot_observed_at":"2026-08-06T03:54:20.273185Z","submitted_at":"2026-07-13T01:18:32Z","title":"MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T07:52:08.823198Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.10985"},"observation_digest":"sha256:40fbec301f06e9ba0753cf8e1652a29abf3c7bc13ae768e5f5e768dffad25cc0","observation_id":"b3cd21cc-3fd4-4e93-9677-6b9770e698a4","resolution":{"observed_at":"2026-07-14T07:52:08.823198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-01T22:57:59.837823Z","title":"Lorahub: Effi- cient cross-task generalization via dynamic LoRA composition.arXiv preprint arXiv:2307.13269,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15587","last_updated":"2026-07-17T03:18:17Z","snapshot_observed_at":"2026-08-09T17:50:56.609811Z","submitted_at":"2026-07-17T03:18:17Z","title":"Rethinking Transfer in Continual Learning: A Replay-Based Realisation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T22:57:59.837823Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.15587"},"observation_digest":"sha256:7446a8b7138975234cd7437a1838296838cdc2027f4cb1de02a0dc94b6091de3","observation_id":"d464988d-6bee-4703-9dbb-4d22ff0b7982","resolution":{"observed_at":"2026-08-01T22:57:59.837823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-01T22:43:39.527353Z","title":"arXiv preprint arXiv:2307.13269 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15661","last_updated":"2026-07-17T06:13:13Z","snapshot_observed_at":"2026-08-09T02:39:21.898725Z","submitted_at":"2026-07-17T06:13:13Z","title":"Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T22:43:39.527353Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.15661"},"observation_digest":"sha256:0bce543e893db6e968540b4ea2a7b37390a39aa9ff6315d94c41076a0de48a78","observation_id":"4f3994e5-5d43-42dd-9295-dc031b4b8888","resolution":{"observed_at":"2026-08-01T22:43:39.527353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-01T06:52:15.838281Z","title":"arXiv preprint arXiv:2307.13269 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27497","last_updated":"2026-07-29T22:28:36Z","snapshot_observed_at":"2026-08-07T17:35:55.711937Z","submitted_at":"2026-07-29T22:28:36Z","title":"SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-01T06:52:15.838281Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2607.27497"},"observation_digest":"sha256:ec1ed822f7f2385e930ee9bcdd3fd071743435d5673132390857db1dbb0bbe06","observation_id":"8c13b5b3-212d-4086-ab96-f12f1ba5829c","resolution":{"observed_at":"2026-08-01T06:52:15.838281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13269","snapshot_observed_at":"2026-08-08T11:15:06.829944Z","title":"arXiv preprint arXiv:2307.13269 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.05541","last_updated":"2026-08-06T02:39:10Z","snapshot_observed_at":"2026-08-09T19:11:35.218983Z","submitted_at":"2026-08-06T02:39:10Z","title":"Hyper-ES: Effective Evolution Strategies for LLM Reasoning via Descent Direction Merging","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T11:15:06.829944Z"},"links":{"cited_paper":"/paper/2307.13269","citing_paper":"/paper/2608.05541"},"observation_digest":"sha256:3812c8ffd3a18cba7b901410a48c7a7841204e217d4e87f8dbe1577a72cd8f84","observation_id":"0bc0f811-9f18-4163-a63c-8e36cdc13815","resolution":{"observed_at":"2026-08-08T11:15:06.829944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.13269/citation-record","integrity":"/paper/2307.13269/integrity","json":"/paper/2307.13269/citation-record.json","paper":"/paper/2307.13269"},"outbound":[],"paper":{"arxiv_id":"2307.13269","last_updated":"2024-08-19T03:31:19Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T05:39:21Z","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 55 inbound Pith citation observations for arXiv:2307.13269."}