{"as_of":"2026-08-21T17:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2e65a5b403385573c41ddc4ee973dca1a0fc69baf43c677097a1fabc94985281","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:38:53.866722Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.12433/citation-record","integrity":"/paper/2505.12433/integrity","json":"/paper/2505.12433/citation-record.json","paper":"/paper/2505.12433"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-15T20:38:53.441524Z","title":"Bert: Pre- training of deep bidirectional transformers for language understanding, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.441524Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:a2f5aeadc9817d50c4f32979afb410752537d4c7c5716d33c226561a69d7730c","observation_id":"10f3e969-6894-4ee7-a636-3ae4bf870db0","resolution":{"observed_at":"2026-08-15T20:38:53.441524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_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},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-15T20:38:53.447544Z","title":"Parameter- efficient fine-tuning for large models: A comprehensive survey, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.447544Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:90b1d3120a189611aeb34c575251d8c4e465a6cf6b287e60c78b01abeca93ed6","observation_id":"cc370ccb-a031-4389-9325-6353887578f1","resolution":{"observed_at":"2026-08-15T20:38:53.447544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.893703Z","title":"DeBERTav3: Improving deBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing","venue":null,"work_id":"2d7c21b7-a5b7-464c-9ef0-afbf7c20a349","year":2023},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.454205Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:00af3c388682963d286ba6cdbffe71a051d55b8b0101838cec63c51cae09aa99","observation_id":"e290684c-8b4c-4008-9a79-9bae26a84d71","resolution":{"observed_at":"2026-08-15T20:38:54.940086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.858576Z","title":"Parameter- efficient transfer learning for nlp, 2019","venue":null,"work_id":"6044ea8b-0159-489c-8547-b09c020f3c77","year":2019},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.462567Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:7e8dee5f092e3b122c69eb07be033f1eed89493f3a1fae44773dc2d8b60f32e7","observation_id":"0d0e84c8-7d1e-4e58-a75d-072555fcffb5","resolution":{"observed_at":"2026-08-15T20:38:54.865291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.806183Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"d8af21a4-ebec-43f8-a2ab-2dcc9b5e061e","year":2022},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.470347Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:0ecdd806f46594fa015d81e7b828357e3f9484ee2445a106ee8fb47bf902e0c1","observation_id":"0fd07a57-bb84-4b69-b197-f73ded2492cb","resolution":{"observed_at":"2026-08-15T20:38:54.825417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.739780Z","title":"LLM-adapters: An adapter family for parameter- efficient fine-tuning of large language models","venue":null,"work_id":"dcbf7ddf-b86b-44e3-8800-323344059131","year":2023},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.476835Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:98f7c98c58b14655bb8e608a12f2b08461adea88fb5cd6e08000c50f40c5409e","observation_id":"6ba3366c-a7ea-48d9-95cf-9057824b1379","resolution":{"observed_at":"2026-08-15T20:38:54.779698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-16T20:01:36.160048Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-15T20:38:53.483920Z","title":"The power of scale for parameter- efficient prompt tuning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.483920Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:78227c815f985c9b4cc552ea39d34b7ddb04eed74a54f6da8576dddde034ef23","observation_id":"17e40a80-ca00-413d-8030-657c90a2c44e","resolution":{"observed_at":"2026-08-15T20:38:53.483920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-21T16:24:51.670091Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-15T20:38:53.546734Z","title":"Prefix-tuning: Optimizing continuous prompts for generation, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.546734Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:0c675f2e4f2bcae39de26414b292b961b12e28913e15372fc3b87024b3ff5c8c","observation_id":"06671a20-7f6d-4828-82c8-e12b84ca6ad6","resolution":{"observed_at":"2026-08-15T20:38:53.546734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.12002","last_updated":"2021-06-08T14:58:31Z","snapshot_observed_at":"2026-08-17T18:10:58.093364Z","submitted_at":"2021-05-25T15:10:05Z","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.12002","snapshot_observed_at":"2026-08-15T20:38:53.658487Z","title":"Super tickets in pre-trained language models: From model compression to improving generalization, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.658487Z"},"links":{"cited_paper":"/paper/2105.12002","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:f3cb5f4a520d0e768e973d1dd757918f38b041ffa29ac3b4cd320b0810bb1cdf","observation_id":"69e1fea5-64b7-4424-b24e-d649a8782b11","resolution":{"observed_at":"2026-08-15T20:38:53.658487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.613003Z","title":"PiSSA: Principal singular values and singular vectors adaptation of large language models","venue":null,"work_id":"6a29bf6b-ecbe-4084-b812-f5bab1921747","year":2024},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.664396Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:344c1c2a65845047b33be549a0035e1b1f0042e6f6a0aac94bc4d9140c33e590","observation_id":"9e27a82e-940e-4cb8-b6c8-784e1f89b3ed","resolution":{"observed_at":"2026-08-15T20:38:54.657214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10650","last_updated":"2019-11-04T15:49:01Z","snapshot_observed_at":"2026-08-20T17:05:54.337297Z","submitted_at":"2019-05-25T18:27:28Z","title":"Are Sixteen Heads Really Better than One?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10650","snapshot_observed_at":"2026-08-15T20:38:53.671132Z","title":"Are sixteen heads really better than one?, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.671132Z"},"links":{"cited_paper":"/paper/1905.10650","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:dfe8a30bf2cc0ec929e544c3691f5c45470e901f3f39e2c7621b21880a64209c","observation_id":"6c14c590-e01b-4db6-bd78-b3c08cd0f7e9","resolution":{"observed_at":"2026-08-15T20:38:53.671132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-15T20:38:53.679280Z","title":"Very deep convolutional networks for large- scale image recognition, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.679280Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:91c1db74c632daebc4c8854dcea095e447e3c50b217e64e6c212a2b29dadb506","observation_id":"d229f685-0811-45c9-8b6f-e635a1c09543","resolution":{"observed_at":"2026-08-15T20:38:53.679280Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07558","last_updated":"2023-04-19T04:28:24Z","snapshot_observed_at":"2026-08-18T10:49:26.769534Z","submitted_at":"2022-10-14T06:29:22Z","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07558","snapshot_observed_at":"2026-08-15T20:38:53.687554Z","title":"Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.687554Z"},"links":{"cited_paper":"/paper/2210.07558","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:5d8c4efce24fe987a084d0d6e04eaf0dd540490cd4198dd80e982645b916c512","observation_id":"3d084f88-1277-40a0-84be-2015041c5a6d","resolution":{"observed_at":"2026-08-15T20:38:53.687554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.590648Z","title":"LoRA-GA: Low-rank adaptation with gra- dient approximation","venue":null,"work_id":"62613621-f854-40b1-8d0e-0160edfa1dd0","year":2024},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.696111Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:e84475319c3eb1438d91dc52c9e62aab9340cc46479ed08e6ab971dfefa015d0","observation_id":"9ae74fcf-0177-4bc5-b3c7-0a0175e7b482","resolution":{"observed_at":"2026-08-15T20:38:54.598397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12148","last_updated":"2023-12-19T13:31:24Z","snapshot_observed_at":"2026-08-16T14:33:23.059607Z","submitted_at":"2023-12-19T13:31:24Z","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12148","snapshot_observed_at":"2026-08-15T20:38:53.842572Z","title":"Parameter- efficient fine-tuning methods for pretrained language models: A critical review and assessment, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.842572Z"},"links":{"cited_paper":"/paper/2312.12148","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:384fbca40c13ee8f790770110c27a14b2e71eeae99d694b393d358d69714caec","observation_id":"c3d94cb3-64bd-4405-ae2e-4a25dc875717","resolution":{"observed_at":"2026-08-15T20:38:53.842572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:53.848826Z","title":"Bitfit: Simple parameter- efficient fine-tuning for transformer-based masked language-models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.848826Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:34254357830dc66f2edd4d3d64e6abf29054cc6bee48862c160293acb93f0242","observation_id":"ed1a915f-9a74-4c6a-9599-4eacd0015f40","resolution":{"observed_at":"2026-08-15T20:38:53.848826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.12562","last_updated":"2022-06-25T05:38:39Z","snapshot_observed_at":"2026-08-20T04:51:10.624502Z","submitted_at":"2022-06-25T05:38:39Z","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","version":1},"cited_work":{"arxiv_id":"2206.12562","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.12562","snapshot_observed_at":"2026-08-15T20:38:53.944504Z","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","venue":"cs.LG","work_id":"7e7efc3e-f69c-416b-aa3a-aa1dba4746b8","year":2022},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.858703Z"},"links":{"cited_paper":"/paper/2206.12562","citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:4c09317a9d8109a8feb29cc78b2308b1e3d07c06af8d11b7a11975cb06ba8b8a","observation_id":"bc12eea0-9de6-4d07-941d-a2d443b732a7","resolution":{"observed_at":"2026-08-15T20:38:54.011331Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:38:54.519712Z","title":"Adaptive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"1ea33c11-10cf-4fb6-86c9-1ee1d2bf2603","year":2023},"citing_paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:38:53.866722Z"},"links":{"citing_paper":"/paper/2505.12433"},"observation_digest":"sha256:1db17605c33f54221f3b92b208d687bdbdf2e4c21b789b2378e456212750c514","observation_id":"3a33aa57-f419-46c8-bf5a-721bc54a3384","resolution":{"observed_at":"2026-08-15T20:38:54.571784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.12433","last_updated":"2025-05-18T14:12:40Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T10:49:35.217691Z","submitted_at":"2025-05-18T14:12:40Z","title":"SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":7},"total_outbound_references":18},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2505.12433."}