{"as_of":"2026-08-09T22:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5e50514a7d7779bd6f0d21166554f49dad07f7eaeb4331345e0920cae671f024","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:00:37.823524Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2506.04288/citation-record","integrity":"/paper/2506.04288/integrity","json":"/paper/2506.04288/citation-record.json","paper":"/paper/2506.04288"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.334877Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.334877Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:da965e5dbb4ef77f3b262369ba768d938a35c44f2d04886b7f1186249cc2bca5","observation_id":"40324eaf-c2c2-41ba-9ab6-12e40780552a","resolution":{"observed_at":"2026-08-07T11:00:37.334877Z","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":"2026-08-07T11:00:37.351184Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.351184Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:c53e6c91091a7546223e812c59f67ca89eb0271eb018617bbb3175f3be123aed","observation_id":"a6e6ef1e-62d9-4fd0-8427-67c488c99a48","resolution":{"observed_at":"2026-08-07T11:00:37.351184Z","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":"2026-08-07T11:00:37.359534Z","title":"The llama 3 herd of models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.359534Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:e7b1d820aa495fd7b9fc0c0e64f79dfe65b3ec272f51925f3d4f326597ccefb1","observation_id":"34df0948-2772-47ae-9519-9d41cddc3d44","resolution":{"observed_at":"2026-08-07T11:00:37.359534Z","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":"2026-08-07T11:00:37.367555Z","title":"Scalable diffusion models with transformers, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.367555Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:4ca99ef5f378002da25b60cb4045f816d95b99d69be71b45f50835895bd2c122","observation_id":"ce37613c-5d40-45ae-ada7-dcbb3bab2468","resolution":{"observed_at":"2026-08-07T11:00:37.367555Z","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":"2026-08-07T11:00:39.512713Z","title":"Fast high-resolution image synthesis with latent adversarial diffusion distillation, 2024","venue":null,"work_id":"101a2d29-3529-4f00-9587-155d59d0943a","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.376846Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:0fb997bbd1de62eb3fb1f8168403546385b4c0c6e02e9fdd890e90bbc75a9933","observation_id":"c9745ed4-52c9-4e99-bc2f-683e26b90f62","resolution":{"observed_at":"2026-08-07T11:00:39.528900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T11:00:37.385730Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.385730Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:dc27ec479712bee33630b621e4f83a20298867a6341a6a4fd22c1d70e029174c","observation_id":"78ab835c-24c5-44e7-9bf1-bd9c85d7e70a","resolution":{"observed_at":"2026-08-07T11:00:37.385730Z","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":"2026-08-07T11:00:37.395653Z","title":"Qlora: Efficient finetuning of quantized llms, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.395653Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:37d99211f0326b7553deebfb96c891d69890a8df0b7a4fec52b7a16f79950823","observation_id":"fd86769b-cdaa-43b7-b096-d6efd51f2f86","resolution":{"observed_at":"2026-08-07T11:00:37.395653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09353","last_updated":"2024-07-09T05:59:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-14T17:59:34Z","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09353","snapshot_observed_at":"2026-08-07T11:00:37.403079Z","title":"Dora: Weight-decomposed low-rank adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.403079Z"},"links":{"cited_paper":"/paper/2402.09353","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:19fbd228f04cde7b1ddf830432accae2b58c77ef797a6f7e99cebe025f3ee02f","observation_id":"781c31e8-4d6c-460f-be63-d4a9b0ee319d","resolution":{"observed_at":"2026-08-07T11:00:37.403079Z","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":"2026-08-07T11:00:37.412259Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.412259Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:ed65e08cc3f762346a16d5f18da29afa873e41e36c40175d097b6aae1d0e346e","observation_id":"c9ff7912-25c2-4262-8fba-32bf3945bdb5","resolution":{"observed_at":"2026-08-07T11:00:37.412259Z","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":"2026-08-07T11:00:37.421040Z","title":"Bermano, Gal Chechik, and Daniel Cohen-Or","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.421040Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:0241a35147bf67e53923a4159f8a830d05fc9a5147daecd9929805e5dad6f677","observation_id":"8d2d40aa-df9c-471d-bf7d-0e926a5d950d","resolution":{"observed_at":"2026-08-07T11:00:37.421040Z","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":"2026-08-07T11:00:39.428574Z","title":"Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models, 2023","venue":null,"work_id":"7d46bcbc-ec5e-4559-821c-412c44dc742b","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.428445Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:243df03b8540802ae9f1bf2ff8ea8ada84a691f8fbb233136e73a586ef0e63c2","observation_id":"d62428e3-af4a-4ec2-b345-5920a06b4572","resolution":{"observed_at":"2026-08-07T11:00:39.436361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.388377Z","title":"Enhancing dreambooth with lora for generating unlimited characters with stable diffusion, 06 2024","venue":null,"work_id":"d200965f-4ce4-4b88-86ba-0a8dc2c79a58","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.436321Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:68dbb1fde7c7218a5b0c54ceffc2e5a632fb0d02ab963c456fd7c533ecf8dec5","observation_id":"37c11b2f-3fc5-4f69-b6d2-3044dda01215","resolution":{"observed_at":"2026-08-07T11:00:39.396239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.355016Z","title":"Overfitting mechanism and avoidance in deep neural networks, 2019","venue":null,"work_id":"214a24da-c46e-437c-b43c-dd3fa975c6bd","year":2019},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.443791Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:55d1cc3b894a73cbe2adf4c821286f87e6b11cbd744440884de9b197188f09c0","observation_id":"3494773c-6ff7-4ae5-ace9-8570f2afdba8","resolution":{"observed_at":"2026-08-07T11:00:39.362777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.323619Z","title":"White, and Sujay Kumar Jauhar","venue":null,"work_id":"38fc39de-8939-41fd-b02e-96a9dcb83b36","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.454044Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:98d6fd0f26267a17e62dad18e2a080a77769cd05c39cd4e82631a2cd9785806f","observation_id":"e6382f9e-0e3b-4015-a0d3-bceeadcca439","resolution":{"observed_at":"2026-08-07T11:00:39.333017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.289067Z","title":"Nlp evaluation in trouble: On the need to measure llm data contamination for each benchmark, 2023","venue":null,"work_id":"20e27672-afd6-4c37-9764-4880e16be255","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.461131Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:4e32aea07c05feaa336b3422f0782fcc7eb740dc7d3da384074e79e145c574ed","observation_id":"6c756180-e64d-4b86-a38f-668e8c2b60fc","resolution":{"observed_at":"2026-08-07T11:00:39.297394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.257918Z","title":"Does synthetic data make large language models more efficient?, 2023","venue":null,"work_id":"1bdd14f4-c5a0-4be1-a7ec-78a32941a84f","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.467086Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:c4510983b088941edd27b69fb340b6de1254548fceac05615eef5315a7462714","observation_id":"a67a2a0a-d6dd-456f-a964-de3a11b6d73e","resolution":{"observed_at":"2026-08-07T11:00:39.266975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09368","last_updated":"2025-08-11T11:28:39Z","snapshot_observed_at":"2026-07-06T20:21:50.886212Z","submitted_at":"2025-01-16T08:27:40Z","title":"Aligning Instruction Tuning with Pre-training","version":4},"cited_work":{"arxiv_id":"2501.09368","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.09368","snapshot_observed_at":"2026-08-07T11:00:38.340484Z","title":"Aligning Instruction Tuning with Pre-training","venue":"cs.AI","work_id":"08633103-dacc-40c5-b810-1da2d2293c54","year":2025},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.473100Z"},"links":{"cited_paper":"/paper/2501.09368","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:e2824677a34e556f2409970820b6293b343baf0cbff594ae1b84c981404ba6f2","observation_id":"4d1f0ebf-508c-4636-9f0b-64cf864e402d","resolution":{"observed_at":"2026-08-07T11:00:38.354138Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.225309Z","title":null,"venue":null,"work_id":"f3c04dc1-5943-4a18-b3db-7e8fe934aff0","year":2020},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.481241Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:ab70a225556d276df4a5e0f9f7cdcccfaeab8512454577ca712a92b6b0f0d49a","observation_id":"91fdfbfd-f53b-4cc8-a453-547a7d000825","resolution":{"observed_at":"2026-08-07T11:00:39.233101Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.199392Z","title":"Improved fine-tuning by better leveraging pre-training data, 2022","venue":null,"work_id":"d05c2d33-c670-4537-baa2-40172815f4cd","year":2022},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.494720Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:ab4b0333a2fc414f13f38674c9746082c9a79deec05d2394e6654465252a0e08","observation_id":"2b233980-64ff-4cab-baea-7867ec38bf2a","resolution":{"observed_at":"2026-08-07T11:00:39.207848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.172992Z","title":"Sdxl photorealistic lora tips: Reflections on training and releasing 10 different models, 2024","venue":null,"work_id":"704bebdc-f238-4842-83bd-bf467e62eb75","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.502098Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:ee5d81acc6302268a32d67bbcabb875514f5a0832962d5f98ac81a659db68a51","observation_id":"edf1eec3-dda0-4aed-92ca-3570a8a20aa2","resolution":{"observed_at":"2026-08-07T11:00:39.179420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.150509Z","title":null,"venue":null,"work_id":"9f9403d7-31e3-4709-a909-a8ea9dc1ade3","year":2020},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.509739Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:b4bbd8beccb2822d8c4e500bfebac6bd9c138323af05a9d0d09d71a93af74f32","observation_id":"e31b676f-693a-4160-a0c5-8dbed02e8b4d","resolution":{"observed_at":"2026-08-07T11:00:39.158416Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:39.127441Z","title":"Towards a statistical theory of data selection under weak supervision","venue":null,"work_id":"6d96d319-eb23-4e09-8105-d51e0b02b01a","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.518999Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:c3e774aea540e936c3821c12b7374e715c04161224571d467a6c9ce5f7b405bc","observation_id":"0a0128ea-f7e0-4475-8361-4088ecbd100e","resolution":{"observed_at":"2026-08-07T11:00:39.134773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.526236Z","title":"Datainf: Efficiently estimating data influence in lora-tuned llms and diffusion models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.526236Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:281c78ae4ef1f34be3b196d52cc0c061079646a43318aa0cb020d49272c9ac3f","observation_id":"8430fa28-29c3-4e79-8821-eb4833b54040","resolution":{"observed_at":"2026-08-07T11:00:37.526236Z","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":"2026-08-07T11:00:37.542373Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.542373Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:2f2e48de605b4fce4d7d2b4442249eea4384f0098c8d0770c60ec5e4ffd9f227","observation_id":"742c7441-6bb7-4f0d-a4e8-af840639e26d","resolution":{"observed_at":"2026-08-07T11:00:37.542373Z","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":"2026-07-06T10:29:18.734092Z","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":"2026-08-07T11:00:37.552688Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.552688Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:e0c0e6565a00b57e484b7e743f3d5a5ba5ed58e6f4634529d2c939b511167fde","observation_id":"5959c244-432a-4c6b-8ad9-178b38ef9598","resolution":{"observed_at":"2026-08-07T11:00:37.552688Z","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":"2026-08-07T11:00:37.564786Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.564786Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:b07c1fbf44d07b9b99af5eaadbe5ba6ac7a27ea93bfcf41fc5c43bdee4ece83f","observation_id":"e8ab632d-cae6-43e8-bb3d-e47060afe99d","resolution":{"observed_at":"2026-08-07T11:00:37.564786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07463","last_updated":"2021-06-09T14:39:17Z","snapshot_observed_at":"2026-08-08T10:12:13.760366Z","submitted_at":"2020-12-14T12:34:01Z","title":"Parameter-Efficient Transfer Learning with Diff Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07463","snapshot_observed_at":"2026-08-07T11:00:37.575291Z","title":"Parameter-efficient transfer learning with diff pruning","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.575291Z"},"links":{"cited_paper":"/paper/2012.07463","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:93ff350fec202e7286495db9cc896fbc6a26a16058d0e696f653af65a7da9f06","observation_id":"46f6bfb8-6ffa-4506-819c-2d0eeb4b8831","resolution":{"observed_at":"2026-08-07T11:00:37.575291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13255","last_updated":"2020-12-22T07:42:30Z","snapshot_observed_at":"2026-08-08T07:37:46.709970Z","submitted_at":"2020-12-22T07:42:30Z","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13255","snapshot_observed_at":"2026-08-07T11:00:37.585028Z","title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.585028Z"},"links":{"cited_paper":"/paper/2012.13255","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:471fa2e94b8c8f0b7744a55d96915b0086c89dd32a635445f0e61a0947a9fe8d","observation_id":"a017da4f-df26-49d9-aa76-4beeda337956","resolution":{"observed_at":"2026-08-07T11:00:37.585028Z","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":"2026-08-07T11:00:39.042678Z","title":"Compacter: Efficient low-rank hypercomplex adapter layers","venue":null,"work_id":"2ab0e921-8057-4081-94da-c564ce7ef89f","year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.593334Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:318b1ea91d6cdffa5d796d597dea786a1e3fdf6368a7f13142558c2e1a0ae421","observation_id":"8cfcc974-9e6e-4786-935b-e11c77bbcbd0","resolution":{"observed_at":"2026-08-07T11:00:39.053557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.599761Z","title":"Denoising diffusion implicit models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.599761Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:212370b9ca02da347e6e1a1657791ed45666416179f8ffa8424bd71a1144dbcd","observation_id":"9eaad9e4-c9ec-48d7-91f2-d5e49d1f371c","resolution":{"observed_at":"2026-08-07T11:00:37.599761Z","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":"2026-08-07T11:00:37.619334Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.619334Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:58414bbeafca79a159c0047dd6b48aeb4c6f855be917c1cc9fc01ba0e772f9bd","observation_id":"6dcbd591-0c16-4954-a8a6-32e4e45bf1cc","resolution":{"observed_at":"2026-08-07T11:00:37.619334Z","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":"2026-08-07T11:00:38.966114Z","title":"Navigating text-to-image customization: From lycoris fine-tuning to model evaluation","venue":null,"work_id":"39a05870-90dc-4d9a-b7d9-ae932e2b1eda","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.626437Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:dbbca8c57c6fdf6479ed8ae9a2bbad37898c4ce2c70b6384a7bb83928f353013","observation_id":"26230c85-e9bb-40ee-9a39-2b1a82b8efb3","resolution":{"observed_at":"2026-08-07T11:00:38.973183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.928037Z","title":null,"venue":null,"work_id":"5cc0db24-ff11-401d-ade8-e2a294f31756","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.644729Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:9263e6ca7f3bb0c3337f0945903976be4687ee6965b61b92ade389d691e77985","observation_id":"c59d58fc-b80f-45a6-85a6-3fd31d44489f","resolution":{"observed_at":"2026-08-07T11:00:38.936953Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.907158Z","title":"Infobatch: Lossless training speed up by unbiased dynamic data pruning","venue":null,"work_id":"231922ce-da76-4849-b77e-3c90d6003d98","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.654728Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:fe4df6209ccd0e6523f01452543a371e41597c2788de6bff499ad4d86b482f35","observation_id":"b647bf99-b2b9-4181-86b8-adab112c4491","resolution":{"observed_at":"2026-08-07T11:00:38.913808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.887991Z","title":"Wang, Tianji Yang, James Zou, Yongchan Kwon, and Ruoxi Jia","venue":null,"work_id":"f522a69c-6f96-40a5-8aa9-836106c4b0d6","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.664794Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:eb13d96d0bd09927022e504e94b7284e5263ae54cfffeafc0a392a56a89ce72d","observation_id":"4fc43f46-dc60-4dba-b759-8af94fd38eef","resolution":{"observed_at":"2026-08-07T11:00:38.893533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.868084Z","title":"Optimal sub-sampling with influence functions, 2017","venue":null,"work_id":"28cced2f-b32c-4c88-93d7-f4627c480b39","year":2017},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.673976Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:24f18d4624fff012f88bd4a0e01c9207a07125b11dc78aaa5adbe8bf28677cde","observation_id":"aa5d424e-6939-44c0-9412-4c9e87721658","resolution":{"observed_at":"2026-08-07T11:00:38.873397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.832552Z","title":"Less is better: Unweighted data subsampling via influence function, 2021","venue":null,"work_id":"ac7a6704-63bd-4f5d-8d32-1bc6343ae0fe","year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.681099Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:f2d4c8ca16b7b38388674fad74bb676871863e87368be4c4812a8c046dd38fe4","observation_id":"cfa7bba5-c4c0-4eec-91de-eb6d9c186f5e","resolution":{"observed_at":"2026-08-07T11:00:38.843411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.805852Z","title":"A statistical perspective on algorithmic leveraging","venue":null,"work_id":"4f3f686f-4a4c-4e5f-a826-40abe7df060b","year":2014},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.687408Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:b05adf6a9cfc2e638a4878a759431b2e6a9bd1f2629119c0662b8f5c6d0e272a","observation_id":"6a224867-1bcb-4620-a228-27a80094b9ab","resolution":{"observed_at":"2026-08-07T11:00:38.814065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.693610Z","title":"New insights and perspectives on the natural gradient method","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.693610Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:c89d8600d3f3cc207dcde3d07ca54fb812e72151e8a41e30e8f72e2d94cedc80","observation_id":"d839e327-7312-4963-844d-2d4498cbdc22","resolution":{"observed_at":"2026-08-07T11:00:37.693610Z","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":"2026-08-07T11:00:38.695667Z","title":null,"venue":null,"work_id":"0dd4899e-237a-4793-821e-3c8f65670af1","year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.706858Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:d3b0c0a76fd5ca183a352165a49832deb6678821884b6cdaf2ea136266ff933e","observation_id":"9b63de6e-3738-4a40-ba48-f054c98f85c4","resolution":{"observed_at":"2026-08-07T11:00:38.745195Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T11:00:38.641157Z","title":"Optimal subsampling algorithms for big data regressions","venue":null,"work_id":"45b58627-6cbc-40b1-8dd4-b531495a25ff","year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.716034Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:69c383ca6010f92de4f439ff16702046fc162a67105ba9096073c126453ec4c3","observation_id":"a294163b-4213-42ad-a0d6-7ffb67d7ffe6","resolution":{"observed_at":"2026-08-07T11:00:38.658703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.723912Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.723912Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:8b2a10e0df667434c317d6f8175945b91e5493e707a3fc706a8a73d5b5e57d67","observation_id":"f9962425-8db2-4dc9-9734-72df0951b153","resolution":{"observed_at":"2026-08-07T11:00:37.723912Z","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":"2026-08-07T11:00:38.577423Z","title":"The star wars dataverse, 2024","venue":null,"work_id":"1389dc4e-b2a6-4855-a1ad-a4dc35cff77f","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.732102Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:115b3709d98e0365bce3211782ed63bd856358c5d528d09cf2e3ac9a9144891e","observation_id":"91943324-c534-4c71-ab06-348421ab8aee","resolution":{"observed_at":"2026-08-07T11:00:38.584971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T11:00:37.740309Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.740309Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:6d036af3935bfd90814b68536b6aa0a28d7fb63ef677c66554092623f1009fc9","observation_id":"9716aea4-2da3-40c5-8439-2d45ad2225e5","resolution":{"observed_at":"2026-08-07T11:00:37.740309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-07-31T00:09:56.948833Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-07T11:00:37.761689Z","title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.761689Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:aab49b3f2cd5bb15b928a93a42972af488e7502fef94bc94680f457c5491fc0b","observation_id":"1f2b07d0-5be7-4481-9c1d-4c86de187799","resolution":{"observed_at":"2026-08-07T11:00:37.761689Z","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":"2026-08-07T11:00:37.769288Z","title":"An introduction to measure theory, volume 126","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.769288Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:bb0e20f593bfe464f4d05799e4ee13d5a0c5717fb9655d98fe3cc1596f11b95c","observation_id":"97a1e227-6586-4e98-85a6-d2d35165fb69","resolution":{"observed_at":"2026-08-07T11:00:37.769288Z","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":"2026-08-07T11:00:37.774125Z","title":"Hashimoto","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.774125Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:694af50b786cb9d3a91370cb9cd036a0942e7465138801335ff0fa1e1b5f744a","observation_id":"77f0f1ce-8db9-45d4-b7d9-fbca49a89205","resolution":{"observed_at":"2026-08-07T11:00:37.774125Z","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":"2026-08-07T11:00:38.497921Z","title":"A question-entailment approach to question answering","venue":null,"work_id":"048fb5cc-59b4-4bfd-92f1-38715d8c5fae","year":2019},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.780690Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:44d2caf5bdf7b07ba4c904e2d555730a98414cbe74fcbee517b12329cc273811","observation_id":"312feaf1-f51c-45e9-82cf-c9b813660e6a","resolution":{"observed_at":"2026-08-07T11:00:38.513853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:00:37.788411Z","title":"Winogrande: An adversarial winograd schema challenge at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.788411Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:92938fd9a65ccaee895624da45c5a8baec4a0370a6b7f4c84dfb4daec721fce2","observation_id":"4d32b1a5-d1d2-488d-b522-7b01020dabc5","resolution":{"observed_at":"2026-08-07T11:00:37.788411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.08745","last_updated":"2018-08-27T09:08:18Z","snapshot_observed_at":"2026-07-06T06:57:36.335954Z","submitted_at":"2018-08-27T09:08:18Z","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.08745","snapshot_observed_at":"2026-08-07T11:00:37.811226Z","title":"Cohen, and Mirella Lapata","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.811226Z"},"links":{"cited_paper":"/paper/1808.08745","citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:a2c06aea4331b29d89864a767294e5f18c08cca0ac440dfa68c875ef5f62aeb7","observation_id":"6469e1c7-ef28-461d-9435-b60520271b68","resolution":{"observed_at":"2026-08-07T11:00:37.811226Z","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":"2026-08-07T11:00:38.450431Z","title":"Star Wars","venue":null,"work_id":"17551fa9-0c49-4d6c-89e0-88198e8295ce","year":2024},"citing_paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:37.823524Z"},"links":{"citing_paper":"/paper/2506.04288"},"observation_digest":"sha256:06ab1b373a0752fb455a8c744869d92c1faa432096e9a8b2afc148c7440bb6bb","observation_id":"d1f179e5-0a15-4ec0-af71-727be8ed1dc1","resolution":{"observed_at":"2026-08-07T11:00:38.458099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04288","last_updated":"2025-06-04T10:09:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:47:16.858870Z","submitted_at":"2025-06-04T10:09:33Z","title":"Backbone Augmented Training for Adaptations"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":21},"total_outbound_references":51},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2506.04288."}