{"as_of":"2026-08-23T20:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8d43f531646cf221a91e663662a7180ed03ea4cac58e5ced5b9c740af9b283c","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":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":54,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:31:02.917007Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T13:55:46.477835Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2406.00515","last_updated":"2024-11-10T22:02:27Z","snapshot_observed_at":"2026-08-14T16:40:35.729198Z","submitted_at":"2024-06-01T17:48:15Z","title":"A Survey on Large Language Models for Code Generation","version":2},"reference_index":156,"source":"pdf_text","source_observed_at":"2026-05-13T20:18:06.304134Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2406.00515"},"observation_digest":"sha256:51bce40f440054367adf1f497b89f3de73cedb4fec13150b0e814f3305c2c09f","observation_id":"957db797-1348-4010-aa42-6ba520eaa8eb","resolution":{"observed_at":"2026-05-13T20:18:06.840735Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2410.18856","last_updated":"2026-05-18T21:55:23Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-24T15:41:56Z","title":"Entry-level guide to the use of large language models for medical research","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-23T19:26:48.548573Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2410.18856"},"observation_digest":"sha256:3dd48df28a930fd6b323d1ba61b1fb98c7fd551945572dad0109ac182858930d","observation_id":"9d078c91-52fa-4c70-b587-81fd08d2a12a","resolution":{"observed_at":"2026-05-23T19:28:21.500014Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-12T13:37:19.204433Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.16099","last_updated":"2024-11-25T05:21:12Z","snapshot_observed_at":"2026-08-17T14:38:17.544678Z","submitted_at":"2024-11-25T05:21:12Z","title":"An Empirical Study of Vulnerability Detection using Federated Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T13:37:19.204433Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2411.16099"},"observation_digest":"sha256:c00657c178ce3dbb37a230254249a220ad593e2e13550d83ede12001ba95d812","observation_id":"326ae801-97f0-4a0f-87b3-0ae0e1a68bd3","resolution":{"observed_at":"2026-08-12T13:37:19.204433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-12T13:34:57.698928Z","title":"Lialin, V","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.16775","last_updated":"2024-11-25T07:06:09Z","snapshot_observed_at":"2026-08-18T07:06:17.356408Z","submitted_at":"2024-11-25T07:06:09Z","title":"Parameter Efficient Instruction Tuning: An Empirical Study","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T13:34:57.698928Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2411.16775"},"observation_digest":"sha256:ce53064f09197c54c3b4e3f4967f6e4d9a50544d70429026966e41af44d5921e","observation_id":"499f317e-596c-4346-9bf9-10a4964f55bc","resolution":{"observed_at":"2026-08-12T13:34:57.698928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-11T23:52:46.732850Z","title":"Available at http: //arxiv.org/abs/2303.15647","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04503","last_updated":"2024-12-03T02:45:02Z","snapshot_observed_at":"2026-08-19T13:15:53.155244Z","submitted_at":"2024-12-03T02:45:02Z","title":"A Primer on Large Language Models and their Limitations","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T23:52:46.732850Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.04503"},"observation_digest":"sha256:6fe4e0c06a11f3ac26e6e00dacafa762570ea51a64e36c6a11177a3e07fe3551","observation_id":"ba534501-e48a-4f66-a669-c15617b68837","resolution":{"observed_at":"2026-08-11T23:52:46.732850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-11T20:08:26.930250Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06071","last_updated":"2025-02-28T05:46:45Z","snapshot_observed_at":"2026-08-18T09:43:41.463846Z","submitted_at":"2024-12-08T21:26:22Z","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T20:08:26.930250Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.06071"},"observation_digest":"sha256:0524ccadb1afbfaa901dbf79a9994ea0dd9a9f5c0ecd67221f079b4301c0e230","observation_id":"c3652edb-8dec-4117-bd97-617112e71918","resolution":{"observed_at":"2026-08-11T20:08:26.930250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-11T19:43:44.673456Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06441","last_updated":"2024-12-09T12:35:58Z","snapshot_observed_at":"2026-08-12T02:36:34.515817Z","submitted_at":"2024-12-09T12:35:58Z","title":"BoRA: Bi-dimensional Weight-Decomposed Low-Rank Adaptation","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T19:43:44.673456Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.06441"},"observation_digest":"sha256:63254a4c23223b4a3f7e0f33a2298d7ef3a9ae0f4af9c1c4bdbf4a1c0659e092","observation_id":"48dbe5e3-9ddc-4148-bdda-e7fc209dc946","resolution":{"observed_at":"2026-08-11T19:43:44.673456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-11T11:04:15.884615Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15891","last_updated":"2024-12-20T13:47:02Z","snapshot_observed_at":"2026-08-11T15:11:14.947889Z","submitted_at":"2024-12-20T13:47:02Z","title":"TelcoLM: collecting data, adapting, and benchmarking language models for the telecommunication domain","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T11:04:15.884615Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.15891"},"observation_digest":"sha256:2baa039dedc99ce97d6b0f37d95b36a0cef3c8359112c014904852e92c03c95b","observation_id":"5b8d23ce-1694-44dd-8048-9e4a227c2418","resolution":{"observed_at":"2026-08-11T11:04:15.884615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-11T15:18:38.402114Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19820","last_updated":"2024-12-15T12:28:13Z","snapshot_observed_at":"2026-08-18T16:39:55.999207Z","submitted_at":"2024-12-15T12:28:13Z","title":"GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T15:18:38.402114Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.19820"},"observation_digest":"sha256:dcb57f8fe8f5f5c21562da7381e0a322479340525c04e427b855ea6ef7056507","observation_id":"c8207180-fca1-4225-93d8-d25c9e3a9a4e","resolution":{"observed_at":"2026-08-11T15:18:38.402114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-10T23:41:59.935615Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.20040","last_updated":"2024-12-28T06:12:02Z","snapshot_observed_at":"2026-08-19T12:25:40.310499Z","submitted_at":"2024-12-28T06:12:02Z","title":"A Contrastive Pretrain Model with Prompt Tuning for Multi-center Medication Recommendation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T23:41:59.935615Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2412.20040"},"observation_digest":"sha256:5eac56d3172d58ae43a3ab6b842a852111e2d784938f807c8a5b6075702f70e5","observation_id":"5b006343-a4c3-4ae4-8548-d9a69a66e331","resolution":{"observed_at":"2026-08-10T23:41:59.935615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-10T21:48:15.146974Z","title":"Scaling Down to Scale Up: A Guide to Parameter- Efficient Fine-Tuning [Internet]","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.05479","last_updated":"2025-01-07T17:11:12Z","snapshot_observed_at":"2026-08-15T23:42:39.743707Z","submitted_at":"2025-01-07T17:11:12Z","title":"Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:48:15.146974Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2501.05479"},"observation_digest":"sha256:1a383d2a6c962969e3a8596ceae7aeb413eea62f055ff970b1ddce8371c43e8e","observation_id":"2b86a4a4-465f-4abb-a746-0414639a81c6","resolution":{"observed_at":"2026-08-10T21:48:15.146974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-10T20:14:59.002933Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.09223","last_updated":"2025-06-15T13:24:11Z","snapshot_observed_at":"2026-08-15T10:26:22.406164Z","submitted_at":"2025-01-16T01:03:56Z","title":"Foundations of Large Language Models","version":2},"reference_index":148,"source":"arxiv_source","source_observed_at":"2026-08-10T20:14:59.002933Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2501.09223"},"observation_digest":"sha256:4782889662e19a4a2390ad6ad5bb42ec578d5b10bc0ff0b760563c61f0f9b625","observation_id":"de38dba2-433d-406f-9f05-47cbdac70531","resolution":{"observed_at":"2026-08-10T20:14:59.002933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-10T19:05:42.179708Z","title":"arXiv preprint arXiv:2303.15647","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.10638","last_updated":"2025-01-18T02:51:43Z","snapshot_observed_at":"2026-08-19T13:15:55.201124Z","submitted_at":"2025-01-18T02:51:43Z","title":"A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T19:05:42.179708Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2501.10638"},"observation_digest":"sha256:e2f7c4c46f97347f493457328f495a61d62fed8b518f8e186f7c840c773f663e","observation_id":"cd304e8f-8070-4904-8333-64832a19cef3","resolution":{"observed_at":"2026-08-10T19:05:42.179708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-10T17:39:51.864033Z","title":"SP o T : Better Frozen Model Adaptation through Soft Prompt Transfer","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.12067","last_updated":"2025-01-21T11:42:09Z","snapshot_observed_at":"2026-08-17T05:02:28.800047Z","submitted_at":"2025-01-21T11:42:09Z","title":"EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T17:39:51.864033Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2501.12067"},"observation_digest":"sha256:fe804d08e1050b9852b3a37307404dcf55cc4f68c5c434fa46dc8a4d7f1335fa","observation_id":"7ddb5dc0-8f77-4506-a2c7-ec47c86f7bda","resolution":{"observed_at":"2026-08-10T17:39:51.864033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-09T21:23:48.609368Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.19099","last_updated":"2025-05-23T12:41:11Z","snapshot_observed_at":"2026-08-18T09:27:52.410768Z","submitted_at":"2025-01-31T12:46:04Z","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T21:23:48.609368Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2501.19099"},"observation_digest":"sha256:186c587a619ca7d89f5dbf19d254b626ccc1265bccdc3bc08bd6d0d848287a56","observation_id":"22164077-f528-439d-8fa5-b98ca4e72490","resolution":{"observed_at":"2026-08-09T21:23:48.609368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-09T11:56:24.907626Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02527","last_updated":"2025-02-04T17:49:44Z","snapshot_observed_at":"2026-08-15T03:40:56.924900Z","submitted_at":"2025-02-04T17:49:44Z","title":"TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T11:56:24.907626Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2502.02527"},"observation_digest":"sha256:5f1e4847ccaf309659dda353409c780deb0a0a3ed3488a70034222f9feeeebd3","observation_id":"a0754d0a-d311-4cc6-8b83-0ae33142da49","resolution":{"observed_at":"2026-08-09T11:56:24.907626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-16T10:31:02.917007Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.18020","last_updated":"2025-04-25T02:20:25Z","snapshot_observed_at":"2026-08-19T13:15:54.181658Z","submitted_at":"2025-04-25T02:20:25Z","title":"Federated Client-tailored Adapter for Medical Image Segmentation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T10:31:02.917007Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2504.18020"},"observation_digest":"sha256:12261cb11de812fb96f9a35dfecee4794b5807417340f4f4aec394677c706ffd","observation_id":"9fb68245-40eb-4386-b5d0-91a442bfb2fc","resolution":{"observed_at":"2026-08-16T10:31:02.917007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-16T05:21:42.965894Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21569","last_updated":"2025-08-15T02:02:19Z","snapshot_observed_at":"2026-08-18T13:51:43.378145Z","submitted_at":"2025-04-29T16:19:25Z","title":"A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-16T05:21:42.965894Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2504.21569"},"observation_digest":"sha256:722ea7ab544a2ca7b997728e9830e35d670a4928e3856566f5b5773e89da04d9","observation_id":"ab2e1f95-e702-4778-95dd-00fd5c66d55b","resolution":{"observed_at":"2026-08-16T05:21:42.965894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-15T23:41:18.315334Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04666","last_updated":"2025-05-07T05:04:30Z","snapshot_observed_at":"2026-08-19T00:09:07.318375Z","submitted_at":"2025-05-07T05:04:30Z","title":"Fine-Tuning Large Language Models and Evaluating Retrieval Methods for Improved Question Answering on Building Codes","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T23:41:18.315334Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2505.04666"},"observation_digest":"sha256:fa524925ed44247042fa227e0f9e4a09eb888950511db803917165f8a8d42f06","observation_id":"33d9b392-31cb-4317-a9f0-40dc8299598b","resolution":{"observed_at":"2026-08-15T23:41:18.315334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-07T13:15:40.547680Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22355","last_updated":"2025-05-28T13:35:12Z","snapshot_observed_at":"2026-08-19T05:30:07.444478Z","submitted_at":"2025-05-28T13:35:12Z","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:40.547680Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2505.22355"},"observation_digest":"sha256:5df43e8bc9fb70e316512f87fd987d475ff8dc41072e74c2ed8a0e23506fc2c8","observation_id":"851674e6-c71a-4aa2-9dee-5f4cb0250ae5","resolution":{"observed_at":"2026-08-07T13:15:40.547680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-07T04:23:50.018642Z","title":"arXiv preprint arXiv:2303.15647 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.10687","last_updated":"2025-06-12T13:33:27Z","snapshot_observed_at":"2026-08-19T13:17:23.313416Z","submitted_at":"2025-06-12T13:33:27Z","title":"Large Language Models for Detection of Life-Threatening Texts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:23:50.018642Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.10687"},"observation_digest":"sha256:224d6d6b950a3e39f0fdb8f8087cd86a843e70432dbeab6a4be396bd135f9e49","observation_id":"075d33fa-40cf-44d7-9153-436195678b2a","resolution":{"observed_at":"2026-08-07T04:23:50.018642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-07T15:11:32.064975Z","title":"Lialin, V","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11049","last_updated":"2025-08-14T14:50:40Z","snapshot_observed_at":"2026-08-19T14:05:22.236325Z","submitted_at":"2025-05-21T21:53:19Z","title":"15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T15:11:32.064975Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.11049"},"observation_digest":"sha256:cd18b733a00dde23927763cab66a1aeaab27f7c3316e964abda089e83a51bb44","observation_id":"aab46512-2e68-40ea-864c-85365a198a3f","resolution":{"observed_at":"2026-08-07T15:11:32.064975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-07T00:58:09.192106Z","title":"Lialin, V","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12394","last_updated":"2025-06-14T08:19:11Z","snapshot_observed_at":"2026-08-18T15:15:31.683063Z","submitted_at":"2025-06-14T08:19:11Z","title":"LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.192106Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.12394"},"observation_digest":"sha256:cd58e0b69b2e06d37f6f6f4b15730023d06e72d31f48d7f5faf062f45567f329","observation_id":"3f195d69-9ae7-4a7d-85a9-7e43fbad0053","resolution":{"observed_at":"2026-08-07T00:58:09.192106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T22:44:44.225640Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.ArXiv preprint, abs/2303.15647, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20917","last_updated":"2025-06-26T00:49:35Z","snapshot_observed_at":"2026-08-16T11:36:05.798105Z","submitted_at":"2025-06-26T00:49:35Z","title":"Optimising Language Models for Downstream Tasks: A Post-Training Perspective","version":1},"reference_index":132,"source":"pdf_text","source_observed_at":"2026-08-06T22:44:44.225640Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.20917"},"observation_digest":"sha256:da84a8a8f05d7763a3526440bf543ee79e551142ac8babec5327a94bbc8ca3d3","observation_id":"66d82331-549e-4a36-8a47-6267b4f02cf6","resolution":{"observed_at":"2026-08-06T22:44:44.225640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T22:41:50.824671Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20989","last_updated":"2025-06-26T04:06:20Z","snapshot_observed_at":"2026-08-13T02:18:11.999477Z","submitted_at":"2025-06-26T04:06:20Z","title":"Can Gradient Descent Simulate Prompting?","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T22:41:50.824671Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.20989"},"observation_digest":"sha256:c8c74a3d4469297593735839db9dc3fba2c3a17b4d9d8edca6852ad01bdd1f67","observation_id":"1ab1e313-c5a3-4798-857b-76feb20a982b","resolution":{"observed_at":"2026-08-06T22:41:50.824671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T22:43:55.838312Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21119","last_updated":"2025-06-26T09:37:15Z","snapshot_observed_at":"2026-08-22T03:13:48.642763Z","submitted_at":"2025-06-26T09:37:15Z","title":"Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:43:55.838312Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2506.21119"},"observation_digest":"sha256:c357ae54ff0b741dc22535aae91b6d1f9e6f0654d7e7036318a9087192a3fb0a","observation_id":"d03f7099-3624-40fe-937a-35c325fa38b9","resolution":{"observed_at":"2026-08-06T22:43:55.838312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T19:18:38.234160Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06013","last_updated":"2025-07-08T14:17:07Z","snapshot_observed_at":"2026-08-15T18:44:57.866944Z","submitted_at":"2025-07-08T14:17:07Z","title":"CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:18:38.234160Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.06013"},"observation_digest":"sha256:a48a412f9ddc2bb7a78011cc30aa518c371501a9b4d61e06c391096afd21b656","observation_id":"d978c357-d912-4761-8ffd-c9bff06b1690","resolution":{"observed_at":"2026-08-06T19:18:38.234160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T18:49:26.011700Z","title":"Lialin, V","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07296","last_updated":"2025-07-09T21:43:06Z","snapshot_observed_at":"2026-08-18T00:06:49.684722Z","submitted_at":"2025-07-09T21:43:06Z","title":"Time Series Foundation Models for Multivariate Financial Time Series Forecasting","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:26.011700Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.07296"},"observation_digest":"sha256:3f9ee85e4678320bdadb5cd7b68023efb16dc6ccc8dbb5047894ee419b1cc02e","observation_id":"3421a396-4e4e-4763-a549-8c5324ffc215","resolution":{"observed_at":"2026-08-06T18:49:26.011700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T18:11:16.772525Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09016","last_updated":"2025-07-16T09:24:11Z","snapshot_observed_at":"2026-08-18T07:10:23.074131Z","submitted_at":"2025-07-11T20:49:04Z","title":"Enhancing RLHF with Human Gaze Modeling","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T18:11:16.772525Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.09016"},"observation_digest":"sha256:67f7784a843cbd40cb674a4361d96ef6711c3348c778156a61c667c9771b38b5","observation_id":"e119e292-0593-46ab-983b-5bea322f6833","resolution":{"observed_at":"2026-08-06T18:11:16.772525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T17:16:06.881395Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.11515","last_updated":"2025-07-15T17:36:37Z","snapshot_observed_at":"2026-08-19T13:18:06.405707Z","submitted_at":"2025-07-15T17:36:37Z","title":"AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:16:06.881395Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.11515"},"observation_digest":"sha256:16a6e6f46981c05aad6271fc9d940e03bcd8a401b4164224514ebe2110da9cb8","observation_id":"95ca019a-dbf4-4475-a06f-f54cd7f2a08d","resolution":{"observed_at":"2026-08-06T17:16:06.881395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-06T15:49:02.897231Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14898","last_updated":"2025-07-20T10:23:03Z","snapshot_observed_at":"2026-08-19T20:32:50.220781Z","submitted_at":"2025-07-20T10:23:03Z","title":"Parameter-Efficient Fine-Tuning of Foundation Models for CLP Speech Classification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:49:02.897231Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.14898"},"observation_digest":"sha256:6f668ebc9011f9b376a359afc6bcbff6c24212ee71854aa5faeda9a3cb33aed1","observation_id":"0fa31b33-3814-4d83-939e-b5a26824ff43","resolution":{"observed_at":"2026-08-06T15:49:02.897231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-15T18:22:34.695171Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17706","last_updated":"2025-07-23T17:12:19Z","snapshot_observed_at":"2026-08-15T18:16:06.562729Z","submitted_at":"2025-07-23T17:12:19Z","title":"HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:34.695171Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2507.17706"},"observation_digest":"sha256:67c8cb3925a3de5951637100ad0d29e9a05390304bb387bd8fa829b3f4ebf493","observation_id":"e7d928b0-ade8-46d1-ada8-d37f4b091e3e","resolution":{"observed_at":"2026-08-15T18:22:34.695171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-05T14:28:02.212342Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.21273","last_updated":"2025-08-29T00:27:35Z","snapshot_observed_at":"2026-08-15T18:38:24.150321Z","submitted_at":"2025-08-29T00:27:35Z","title":"CALM: A Framework for Continuous, Adaptive, and LLM-Mediated Anomaly Detection in Time-Series Streams","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-05T14:28:02.212342Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2508.21273"},"observation_digest":"sha256:971ff6fa9a79dabc4be219779fab5567d91ecb6175bda542fa17c97f393fba00","observation_id":"def5e55a-038f-4829-91b5-53d6193121d7","resolution":{"observed_at":"2026-08-05T14:28:02.212342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2509.03740","last_updated":"2026-04-22T16:33:26Z","snapshot_observed_at":"2026-08-16T21:47:37.241619Z","submitted_at":"2025-09-03T22:00:23Z","title":"CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-18T18:55:31.923309Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2509.03740"},"observation_digest":"sha256:8d868bca8e3d51a055c6ca0804fc413d69190d2e42a8d34afe28befd4acf3c50","observation_id":"33523daa-722b-4eb3-862f-fc3862b74efc","resolution":{"observed_at":"2026-05-18T18:56:45.955971Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-04T06:54:11.356436Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.00382","last_updated":"2026-08-03T16:22:30Z","snapshot_observed_at":"2026-08-13T23:55:51.184827Z","submitted_at":"2025-11-01T03:29:56Z","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T06:54:11.356436Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2511.00382"},"observation_digest":"sha256:ac24c7d8843ceb7697d31c565694869c61fe1ab4e99d647da350224e23aee456","observation_id":"18911837-8c3d-49fa-9db1-abcc9e9553be","resolution":{"observed_at":"2026-08-04T06:54:11.356436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2511.11362","last_updated":"2026-05-05T10:40:45Z","snapshot_observed_at":"2026-08-17T06:52:14.637887Z","submitted_at":"2025-11-14T14:46:29Z","title":"On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-17T22:03:53.594703Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2511.11362"},"observation_digest":"sha256:f650878a1b664c79fccfabccadad0515e039f734a7a291f07287e01f59589a70","observation_id":"78fd4de2-2ade-4a07-84a8-809a77add72a","resolution":{"observed_at":"2026-05-17T22:05:21.478953Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2511.21285","last_updated":"2026-05-12T18:52:26Z","snapshot_observed_at":"2026-08-11T01:44:10.080638Z","submitted_at":"2025-11-26T11:18:06Z","title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-17T05:08:42.031800Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2511.21285"},"observation_digest":"sha256:c5792a44b4d66f886ff5b86fe3f4b8e7b3236d79f2a448c21d6636903da7b303","observation_id":"59e346ea-8bc4-4c57-9c93-8ef45e486146","resolution":{"observed_at":"2026-05-17T05:09:03.671753Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2512.02764","last_updated":"2026-05-12T18:50:51Z","snapshot_observed_at":"2026-08-08T14:14:37.879309Z","submitted_at":"2025-12-02T13:44:41Z","title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-17T02:38:11.118057Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2512.02764"},"observation_digest":"sha256:0199384246579a548bd0ef0d2bdfdce7321d431b0deec8d14796a6477c4b0287","observation_id":"4941e733-774d-4ce5-a655-9ce0ee01fe04","resolution":{"observed_at":"2026-05-17T02:38:53.832766Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2512.12677","last_updated":"2026-05-25T16:57:18Z","snapshot_observed_at":"2026-08-20T21:52:01.205893Z","submitted_at":"2025-12-14T13:02:06Z","title":"Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-25T07:23:53.703286Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2512.12677"},"observation_digest":"sha256:d989defb7c8e291b818e54644e2c1427e703769f8375d6b4fc29feeb9e114a70","observation_id":"4224fa63-6ed3-4c2d-a954-898d45322e76","resolution":{"observed_at":"2026-05-25T07:25:29.087875Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-03T16:38:11.883445Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.12677","last_updated":"2026-05-25T16:57:18Z","snapshot_observed_at":"2026-08-20T21:52:01.205893Z","submitted_at":"2025-12-14T13:02:06Z","title":"Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T16:38:11.883445Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2512.12677"},"observation_digest":"sha256:35084e56f21db914cc1f9f3b358efed1ee46f421b89be1655e71928009b17f37","observation_id":"bc20433a-7a68-478d-8f2d-6f9e7971e9ee","resolution":{"observed_at":"2026-08-03T16:38:11.883445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2601.09448","last_updated":"2026-07-03T08:22:03Z","snapshot_observed_at":"2026-08-15T05:39:18.575957Z","submitted_at":"2026-01-14T12:51:36Z","title":"One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-16T14:26:36.236424Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2601.09448"},"observation_digest":"sha256:f1bb39198ae10fae625bbf34f90e6009d8ff14b057b976aa3bf7570f0b4b032a","observation_id":"8f32954c-ec42-4e40-88c7-d2b02062876e","resolution":{"observed_at":"2026-05-16T14:27:59.232048Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-03T10:39:37.534409Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.09448","last_updated":"2026-07-03T08:22:03Z","snapshot_observed_at":"2026-08-15T05:39:18.575957Z","submitted_at":"2026-01-14T12:51:36Z","title":"One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T10:39:37.534409Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2601.09448"},"observation_digest":"sha256:2664fd400c478ce77e0385fc4f9de591022b0dd9f81111e90cbc20b731b3913c","observation_id":"901ab418-b92b-422a-8b49-45cdf70f3c3d","resolution":{"observed_at":"2026-08-03T10:39:37.534409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2602.20409","last_updated":"2026-04-21T14:05:24Z","snapshot_observed_at":"2026-08-16T02:20:15.500679Z","submitted_at":"2026-02-23T23:17:12Z","title":"CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-15T20:05:30.406701Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2602.20409"},"observation_digest":"sha256:bcc79f8c8ba8b66cee858a3890bb220fd1ce9baa280933344a3dc30bcf70d645","observation_id":"fa37d5df-e2a4-405d-ba1f-d0fb21dad015","resolution":{"observed_at":"2026-05-15T20:06:33.733221Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2604.19342","last_updated":"2026-04-21T11:25:22Z","snapshot_observed_at":"2026-08-12T12:38:50.535093Z","submitted_at":"2026-04-21T11:25:22Z","title":"Are Large Language Models Economically Viable for Industry Deployment?","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-10T02:28:12.686424Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2604.19342"},"observation_digest":"sha256:06d727e1565fda5a887e70076a732b10246c7d83fb135d4a3b210b7a3f7ec347","observation_id":"eea2ccce-4369-44d8-8af1-1f1ecf39525e","resolution":{"observed_at":"2026-05-11T13:01:19.105740Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2604.27818","last_updated":"2026-04-30T12:58:57Z","snapshot_observed_at":"2026-08-14T09:45:57.469301Z","submitted_at":"2026-04-30T12:58:57Z","title":"MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-07T05:31:47.682478Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2604.27818"},"observation_digest":"sha256:80eade444e4fa0909b512173e2e429d717be606233fcc5740e5f00fc06bd3572","observation_id":"821292b5-745b-4c19-a867-8ec71331ac1d","resolution":{"observed_at":"2026-05-12T10:36:30.198207Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2605.05659","last_updated":"2026-05-07T04:21:04Z","snapshot_observed_at":"2026-08-14T11:18:32.733690Z","submitted_at":"2026-05-07T04:21:04Z","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-08T15:05:34.990424Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2605.05659"},"observation_digest":"sha256:426939f13add19b2bc487c25141dbee3fbe5884ad9a33f519fc8d5d8a2ef1b3d","observation_id":"81f00695-028d-4aba-916a-b93e23680834","resolution":{"observed_at":"2026-05-11T18:36:07.896448Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2605.09781","last_updated":"2026-06-18T23:32:10Z","snapshot_observed_at":"2026-08-17T16:29:06.892706Z","submitted_at":"2026-05-10T22:00:15Z","title":"Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-12T03:38:18.983068Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2605.09781"},"observation_digest":"sha256:ef26ec893c5da0b4933e677c0764fb8e477b06df4dfed3cf0b4b0120991532a5","observation_id":"fd22335a-bfcf-4577-9e20-5ff1fad93643","resolution":{"observed_at":"2026-05-12T07:11:25.783765Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2605.09781","last_updated":"2026-06-18T23:32:10Z","snapshot_observed_at":"2026-08-17T16:29:06.892706Z","submitted_at":"2026-05-10T22:00:15Z","title":"Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-30T22:29:26.178639Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2605.09781"},"observation_digest":"sha256:891717c89d826549b938cbf9325581af3cc238cb2646ac3c113b8999158ad82d","observation_id":"5ede5335-d156-4e02-af0e-8ffcb4856eee","resolution":{"observed_at":"2026-07-01T13:55:46.479266Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2605.13421","last_updated":"2026-05-13T12:16:04Z","snapshot_observed_at":"2026-08-14T14:45:28.825095Z","submitted_at":"2026-05-13T12:16:04Z","title":"Combining pre-trained models via localized model averaging","version":1},"reference_index":151,"source":"arxiv_source","source_observed_at":"2026-05-14T17:56:34.111280Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2605.13421"},"observation_digest":"sha256:9c25c8ae5af9e27739a1bc5a4e85773bd10affd0af333e1511a8208fa73dd747","observation_id":"43baa535-edba-4ff4-a51a-0765001f6666","resolution":{"observed_at":"2026-05-14T17:57:32.977532Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2605.27968","last_updated":"2026-05-27T05:03:25Z","snapshot_observed_at":"2026-08-15T21:19:40.258834Z","submitted_at":"2026-05-27T05:03:25Z","title":"Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T09:55:33.247813Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2605.27968"},"observation_digest":"sha256:727886c92683aa2029c544dfd7fa15aefc751258e141f42d88142288aff25f2e","observation_id":"6fae0f60-f413-41a8-b584-c66737e1ccc7","resolution":{"observed_at":"2026-06-29T10:03:17.284235Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2303.15647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-01T13:55:46.477835Z","title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning.arXiv preprint arXiv:2303.15647","venue":null,"work_id":"57ac9386-0e04-45d3-8cb8-7bf370819655","year":2024},"citing_paper":{"arxiv_id":"2606.02606","last_updated":"2026-05-23T15:56:16Z","snapshot_observed_at":"2026-08-13T13:09:03.610770Z","submitted_at":"2026-05-23T15:56:16Z","title":"ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-30T15:06:08.515588Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2606.02606"},"observation_digest":"sha256:e0903b48fa66db90306bfff23d9a6b96e622f94c336014af81a4633f0c71c924","observation_id":"fad8b116-36fe-4403-a8bf-2f4eac67dd8e","resolution":{"observed_at":"2026-06-30T15:34:48.826605Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-07-11T06:09:35.110633Z","title":"arXiv preprint arXiv:2303.15647 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05537","last_updated":"2026-07-06T18:18:44Z","snapshot_observed_at":"2026-08-14T09:22:40.153094Z","submitted_at":"2026-07-06T18:18:44Z","title":"Prompt engineering using order-of-addition experiments: An application to generating two-level fractional factorial designs","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-07-11T06:09:35.110633Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2607.05537"},"observation_digest":"sha256:fd65cfe5d6317ccf30fc3942e962a9442f835c29a75cd38797fb0a9513980ca8","observation_id":"0f4cecbd-f25e-4a49-bd7a-2056e6b79bd2","resolution":{"observed_at":"2026-07-11T06:09:35.110633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-08T17:05:01.897883Z","title":"arXiv preprint arXiv:2303.15647 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.05253","last_updated":"2026-08-05T16:05:13Z","snapshot_observed_at":"2026-08-19T13:15:53.682485Z","submitted_at":"2026-08-05T16:05:13Z","title":"Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T17:05:01.897883Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2608.05253"},"observation_digest":"sha256:a05e8f45fa3c094e4ea488675d4634690aefb764614a344848a7eb19af63d67c","observation_id":"c8123b33-4c6b-4407-941a-4eed5330fb7a","resolution":{"observed_at":"2026-08-08T17:05:01.897883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15647","snapshot_observed_at":"2026-08-12T11:27:14.533197Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.11047","last_updated":"2026-08-11T15:18:47Z","snapshot_observed_at":"2026-08-17T07:31:46.012323Z","submitted_at":"2026-08-11T15:18:47Z","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T11:27:14.533197Z"},"links":{"cited_paper":"/paper/2303.15647","citing_paper":"/paper/2608.11047"},"observation_digest":"sha256:87aa6ac39788ea9a9b4537cdefa57e6d0e69220c1d3a6c3e051b42e3403a1251","observation_id":"b1df4501-1674-4086-84be-0c3ad29511a4","resolution":{"observed_at":"2026-08-12T11:27:14.533197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2303.15647/citation-record","integrity":"/paper/2303.15647/integrity","json":"/paper/2303.15647/citation-record.json","paper":"/paper/2303.15647"},"outbound":[],"paper":{"arxiv_id":"2303.15647","last_updated":"2024-11-22T05:02:26Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T13:15:16.269468Z","submitted_at":"2023-03-28T00:06:38Z","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 54 inbound Pith citation observations for arXiv:2303.15647."}