{"as_of":"2026-08-14T11:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:08f5a23dad132ec45a4af115823b68e71d8c40ba98e44a5fcf689972fd2e47c8","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:47:34.282348Z","state":"measured"},{"denominator":74,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":74,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T21:14:48.430536Z","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":"2026-07-02T17:27:14.947625Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":"2506.07077","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.07077","snapshot_observed_at":"2026-07-02T17:27:14.947625Z","title":"Dual-priv pruning : Efficient differential private fine-tuning in multimodal large language models, 2025","venue":null,"work_id":"e078d6aa-108e-4dc3-999d-be9950793f6a","year":2025},"citing_paper":{"arxiv_id":"2606.07171","last_updated":"2026-06-05T11:40:03Z","snapshot_observed_at":"2026-08-02T22:25:34.082799Z","submitted_at":"2026-06-05T11:40:03Z","title":"When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T22:08:57.792229Z"},"links":{"cited_paper":"/paper/2506.07077","citing_paper":"/paper/2606.07171"},"observation_digest":"sha256:b95af05680196af5c09379615eed243732b3f2d1bcc2c5745fd9a41c85979718","observation_id":"046a90ea-9531-4b16-94ab-e5f017af8042","resolution":{"observed_at":"2026-07-02T17:07:13.125469Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":"2506.07077","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.07077","snapshot_observed_at":"2026-07-02T17:27:14.947625Z","title":"Dual-priv pruning : Efficient differential private fine-tuning in multimodal large language models, 2025","venue":null,"work_id":"e078d6aa-108e-4dc3-999d-be9950793f6a","year":2025},"citing_paper":{"arxiv_id":"2606.07175","last_updated":"2026-06-05T11:41:39Z","snapshot_observed_at":"2026-08-01T09:18:30.921777Z","submitted_at":"2026-06-05T11:41:39Z","title":"Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-27T22:03:49.204596Z"},"links":{"cited_paper":"/paper/2506.07077","citing_paper":"/paper/2606.07175"},"observation_digest":"sha256:55db48f568c6cc83c1450acaa9c2995665c06abc5e5db62b56426469e3349693","observation_id":"0b22ccf6-4d7c-4e82-8806-24f460a1bfe6","resolution":{"observed_at":"2026-07-02T17:27:14.949694Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.07077","snapshot_observed_at":"2026-08-01T21:14:48.430536Z","title":"Available: https://arxiv.org/abs/2506.07077","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22695","last_updated":"2026-07-17T17:23:39Z","snapshot_observed_at":"2026-08-11T19:22:40.581910Z","submitted_at":"2026-07-17T17:23:39Z","title":"PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T21:14:48.430536Z"},"links":{"cited_paper":"/paper/2506.07077","citing_paper":"/paper/2607.22695"},"observation_digest":"sha256:38be8d4f43140d00997aaa57e604aa17fab43503f9b4356f8cf7afdc88520d09","observation_id":"ad8ef6b5-f439-4f8c-ab85-e5b16c72a09a","resolution":{"observed_at":"2026-08-01T21:14:48.430536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.07077/citation-record","integrity":"/paper/2506.07077/integrity","json":"/paper/2506.07077/citation-record.json","paper":"/paper/2506.07077"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:47:28.517772Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.517772Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:3e4ca3d669f0fb99a50637e52264c911b1eb1c8087bba4c7f840523175efc90a","observation_id":"a9bb2b7d-690a-4b6c-8c4f-83a34c826b36","resolution":{"observed_at":"2026-08-07T05:47:28.517772Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-08-10T14:07:02.234322Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-07T05:47:28.586725Z","title":"Phi-3 technical report: A highly capable language model locally on your phone","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.586725Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:b2c84a6f62d73e313566fdd3d37df467d86d94d9b297fd288cdd10a254b9d4c0","observation_id":"bc731327-723a-40e4-90bb-a44c68cbaf28","resolution":{"observed_at":"2026-08-07T05:47:28.586725Z","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":"2026-08-07T05:47:28.633686Z","title":"Flamingo: a visual language model for few-shot learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.633686Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:a0e63ea6dfd0acfcadfff081de9f5a3e1619c39b55e23768908cc66dfec8c798","observation_id":"dbe472b5-1225-4b3d-bc10-56e9671d71b3","resolution":{"observed_at":"2026-08-07T05:47:28.633686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12966","last_updated":"2023-10-13T02:41:28Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-24T17:59:17Z","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12966","snapshot_observed_at":"2026-08-07T05:47:28.684671Z","title":"Qwen-vl: A frontier large vision-language model with versatile abilities","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.684671Z"},"links":{"cited_paper":"/paper/2308.12966","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:f7487bef4e2e3a04231a1731f790e08d3df605c05011bbe5e7df470f2c8cabb7","observation_id":"0faa10cf-31c9-4dc5-9209-91548ae0ed9f","resolution":{"observed_at":"2026-08-07T05:47:28.684671Z","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":"2026-08-07T05:47:28.779704Z","title":"Training with noise is equivalent to tikhonov regularization","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.779704Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:a534f92af675f89a95f8089f1f51ededc91f24810e648bf336de5e3ea06bfcf7","observation_id":"3fa7581d-ea78-4d6a-a4bf-ae4df64800c9","resolution":{"observed_at":"2026-08-07T05:47:28.779704Z","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":"2026-08-07T05:47:28.850462Z","title":"An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.850462Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:b985826d257b2592d4ee205b9366f0ddf57097458cf409b7717ba6cd8266bcdc","observation_id":"5f2047cd-9391-405e-a12b-5faab9070547","resolution":{"observed_at":"2026-08-07T05:47:28.850462Z","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":"2026-08-07T05:47:28.937160Z","title":"Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:28.937160Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:7652eb4dd941e7201493b30703b24e0cb7ee9eb7002fc82d957296e950895e15","observation_id":"ad99cce9-fe23-446f-b2ac-14dbcc911d28","resolution":{"observed_at":"2026-08-07T05:47:28.937160Z","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":"2026-08-07T05:47:37.548541Z","title":"Security and privacy challenges of large language models: A survey","venue":null,"work_id":"0cef8acc-cdca-4da6-89d3-3261139d7f17","year":2025},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.036541Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:128d384eb4870b4d72020c9777196299b784291e2ff7c59de7fc5db229de460f","observation_id":"cdf3fb01-e97b-4a8b-841f-59ca5f440c63","resolution":{"observed_at":"2026-08-07T05:47:37.553756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:29.158234Z","title":"Differential privacy","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.158234Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:664d90999ac73bb877559d4ecad7d4123a748bdb766f1b0171e978624edeaa37","observation_id":"84350ce8-06bb-48f8-93d9-03147144d33c","resolution":{"observed_at":"2026-08-07T05:47:29.158234Z","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":"2026-08-07T05:47:37.523421Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"078637cf-986b-40ac-8479-fcf18709156b","year":2014},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.273399Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:a18de74f899584148a54393e6edb2df93241c321620a1fdbedfc5e39dbcd9d9e","observation_id":"579d8b04-1225-473d-b669-440588c1b0f3","resolution":{"observed_at":"2026-08-07T05:47:37.528648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18532","last_updated":"2025-03-20T09:58:49Z","snapshot_observed_at":"2026-08-10T02:10:09.533626Z","submitted_at":"2025-01-30T17:58:36Z","title":"Differentially Private Steering for Large Language Model Alignment","version":2},"cited_work":{"arxiv_id":"2501.18532","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.18532","snapshot_observed_at":"2026-08-07T05:47:35.208989Z","title":"Differentially Private Steering for Large Language Model Alignment","venue":"cs.CL","work_id":"4d7c8c71-9f22-43a5-9f48-f79dfe939975","year":2025},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.370583Z"},"links":{"cited_paper":"/paper/2501.18532","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:150b4f1d66b72ce2ff43907f43b15d7e2a18f3e4f2afe03497ba1aad4c95affe","observation_id":"ba73bc6b-a27c-4557-8f46-615cafa236ac","resolution":{"observed_at":"2026-08-07T05:47:35.261379Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.506804Z","title":"Which tokens to use? investigating token reduction in vision transformers","venue":null,"work_id":"9ace9cc6-5ae0-4bd4-a425-54be237fa370","year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.526657Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:4ac3193dbfbb1e3d02601ab47b478bba7d283fa79eddce10a3f1604d85a521cb","observation_id":"65395437-0670-4bca-a9c8-0316afae9457","resolution":{"observed_at":"2026-08-07T05:47:37.511851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.10286","last_updated":"2020-03-07T17:55:41Z","snapshot_observed_at":"2026-07-06T09:06:42.071993Z","submitted_at":"2020-03-07T17:55:41Z","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.10286","snapshot_observed_at":"2026-08-07T05:47:29.667469Z","title":"Pathvqa: 30000+ questions for medical visual question answering","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.667469Z"},"links":{"cited_paper":"/paper/2003.10286","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:20a0ab7d6dbe21e51598777329ae6b64a2c2aa05761bc3dbb4122855c98b4867","observation_id":"566cc5f3-6c34-42e7-ae01-d5c72acc1532","resolution":{"observed_at":"2026-08-07T05:47:29.667469Z","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":"2026-08-07T05:47:29.778173Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.778173Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:77330366c41649ea40bf5c1d33330a77bb90248a39b571e47e309aa1d7c827be","observation_id":"5a968413-87a9-4672-af60-a2682e90566f","resolution":{"observed_at":"2026-08-07T05:47:29.778173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08173","last_updated":"2024-03-01T04:24:04Z","snapshot_observed_at":"2026-08-13T11:17:48.993057Z","submitted_at":"2023-06-13T23:32:09Z","title":"Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08173","snapshot_observed_at":"2026-08-07T05:47:29.878452Z","title":"Safeguard- ing data in multimodal ai: A differentially private approach to clip training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.878452Z"},"links":{"cited_paper":"/paper/2306.08173","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:2aac74b2b1d34fc81cdb719dc8320950f72955080c51ce9d083fd178bec38569","observation_id":"fb32c6a1-87e3-443c-9f3f-38ba4225d358","resolution":{"observed_at":"2026-08-07T05:47:29.878452Z","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":"2026-08-07T05:47:29.949896Z","title":"Gqa: A new dataset for real-world visual reasoning and compositional question answering","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:29.949896Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:b58a1c72bd4e2f1e7f2e904422b1111024d6547a8581f937e22becc0d9de27d7","observation_id":"df28eeb7-af0f-4ff9-a7dd-f1a00fd1d656","resolution":{"observed_at":"2026-08-07T05:47:29.949896Z","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":"2026-08-07T05:47:37.470003Z","title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","venue":null,"work_id":"831bb54f-58b2-459b-bd4c-6123904fbff0","year":2021},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.018751Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:94b882d9436b8ea0e718c2f8870265dc2ad9a22260f37ba865f53c087f0071fb","observation_id":"bbf1d460-63e5-40dd-b2af-ecedbab055a3","resolution":{"observed_at":"2026-08-07T05:47:37.475193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.05886","last_updated":"2020-10-26T16:04:43Z","snapshot_observed_at":"2026-08-06T11:41:52.448290Z","submitted_at":"2020-09-13T00:50:44Z","title":"Differentially Private Language Models Benefit from Public Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.05886","snapshot_observed_at":"2026-08-07T05:47:30.110883Z","title":"Differentially private language models benefit from public pre-training","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.110883Z"},"links":{"cited_paper":"/paper/2009.05886","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:32231e2f17de262721a4b520a097394d9b8bb1e311d65029e37411a2789f9790","observation_id":"378320bf-f8dc-4ac5-b82d-1f2ef7c8f3f2","resolution":{"observed_at":"2026-08-07T05:47:30.110883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T05:47:30.206986Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.206986Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:bc69c5363fda4bae10fe43bea2c316d827556a7974fc684b600bdf7588751c52","observation_id":"eea46335-f6ac-46c6-826b-7c5fc7d14902","resolution":{"observed_at":"2026-08-07T05:47:30.206986Z","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":"2026-08-07T05:47:37.454071Z","title":"Spvit: Enabling faster vision transformers via latency- aware soft token pruning","venue":null,"work_id":"ae4f1511-226a-4517-876f-a2db1976c1f2","year":2022},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.265719Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:2ef4708c54e12c144f60ac7ffa99dec38cace01aa5d0916a4e6544923570f39c","observation_id":"758a44d4-419e-4b49-8e9f-41735cf74084","resolution":{"observed_at":"2026-08-07T05:47:37.459221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:30.336425Z","title":"A dataset of clinically generated visual questions and answers about radiology images","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.336425Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:1cb4da12b586bcc993a3d325b0c82e89acc4cf115325b203f22bc239a05078c9","observation_id":"32a03ccd-4b49-4603-a19b-a56f93f3c00d","resolution":{"observed_at":"2026-08-07T05:47:30.336425Z","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":"2026-08-07T05:47:30.404953Z","title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.404953Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:376de9a54795daa85dec3f02c5523b0e0d0104315f00cee472814c1ee78aa775","observation_id":"fec59502-7814-4b25-8c17-4c2bfd16c7a9","resolution":{"observed_at":"2026-08-07T05:47:30.404953Z","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":"2026-08-07T05:47:30.477101Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.477101Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:76844f838899f487bed6f1165579f83c6add70ab90ababffca789515c9bd1025","observation_id":"bea30493-c320-4dd2-9826-374a3fc7a60f","resolution":{"observed_at":"2026-08-07T05:47:30.477101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02912","last_updated":"2024-10-03T19:02:50Z","snapshot_observed_at":"2026-08-12T22:31:18.067802Z","submitted_at":"2024-10-03T19:02:50Z","title":"Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02912","snapshot_observed_at":"2026-08-07T05:47:30.547245Z","title":"Fine-tuning lan- guage models with differential privacy through adaptive noise allocation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.547245Z"},"links":{"cited_paper":"/paper/2410.02912","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:dd95de30c3a69d16c1532b71f8fe1489f972f80c64df610443fad1378f0c0559","observation_id":"7bb86e9d-62bb-49fc-bc34-853a12dacb3d","resolution":{"observed_at":"2026-08-07T05:47:30.547245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.05679","last_updated":"2022-11-10T18:42:34Z","snapshot_observed_at":"2026-08-13T17:54:58.734783Z","submitted_at":"2021-10-12T01:45:27Z","title":"Large Language Models Can Be Strong Differentially Private Learners","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.05679","snapshot_observed_at":"2026-08-07T05:47:30.616876Z","title":"Large language models can be strong differentially private learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.616876Z"},"links":{"cited_paper":"/paper/2110.05679","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:49caa4dce1dad64d7075452bf7465fd521d434950cea0cf058fcdd531c788979","observation_id":"382b8d0a-7c39-420c-bdab-553eb70cf307","resolution":{"observed_at":"2026-08-07T05:47:30.616876Z","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":"2026-08-07T05:47:30.670329Z","title":"Membership inference attacks against large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.670329Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:fe736fca6cf80e57a491f364cbe405c358dd55750112059fb549000dc12c9482","observation_id":"576a3d5a-4e3d-452c-9639-62ff25c085ef","resolution":{"observed_at":"2026-08-07T05:47:30.670329Z","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":"2026-08-07T05:47:30.763753Z","title":"Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.763753Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:e8a3eaf7038e9036d60e11d5ad4fb851a3391dea5d93ece519bbd4ebef1f117d","observation_id":"d42a091e-0dec-4f74-90ca-5d8be6704bf2","resolution":{"observed_at":"2026-08-07T05:47:30.763753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07818","last_updated":"2025-03-10T06:52:03Z","snapshot_observed_at":"2026-08-13T04:20:26.804693Z","submitted_at":"2024-02-12T17:24:15Z","title":"Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07818","snapshot_observed_at":"2026-08-07T05:47:30.826841Z","title":"Differentially private zeroth-order methods for scalable large language model finetuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.826841Z"},"links":{"cited_paper":"/paper/2402.07818","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:1abf3c427f4c356fb9be9a74a95e2138b9ae2e6f3ce8632ec0cecbde0cad49e9","observation_id":"a1e3d07f-04ec-498d-9942-b5481f5b2e23","resolution":{"observed_at":"2026-08-07T05:47:30.826841Z","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":"2026-08-07T05:47:37.387931Z","title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","venue":null,"work_id":"a9d46149-52b6-4db0-9655-e220b401e533","year":2022},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.897295Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:1556a087b376af8107478065061e54c1892ad9a15ec9222015ac080e04cd37e9","observation_id":"43953c4c-3458-409a-8b7c-9d2a32644ecf","resolution":{"observed_at":"2026-08-07T05:47:37.393248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01054","last_updated":"2023-07-19T14:50:27Z","snapshot_observed_at":"2026-08-13T11:26:56.370871Z","submitted_at":"2023-06-01T18:00:40Z","title":"Unveiling a universal relationship between the f(R) parameter and neutron star properties","version":2},"cited_work":{"arxiv_id":"2306.01054","doi":null,"metadata_source":"pith","pith_arxiv_id":"2306.01054","snapshot_observed_at":"2026-08-07T05:47:34.911270Z","title":"Unveiling a universal relationship between the f(R) parameter and neutron star properties","venue":"gr-qc","work_id":"184422be-ea9a-4780-b223-35b8c77ec85d","year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:30.967231Z"},"links":{"cited_paper":"/paper/2306.01054","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:3ddc044ebb0cb6e15bd1f2b9e8ffa51f6a4a3ff0f306417f7d2c944023eea672","observation_id":"103c3e27-f7ef-4b64-bcd5-3c80f5d62aaf","resolution":{"observed_at":"2026-08-07T05:47:35.003649Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-10T06:02:31.713188Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-07T05:47:31.039463Z","title":"Learning differentially private recurrent language models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.039463Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:4a7dac96546e77aa8cdfd168cb0b530485da2b7682b78930f0f328783976a389","observation_id":"cefdda7f-7b51-4ca3-91ca-b7f7af2f1283","resolution":{"observed_at":"2026-08-07T05:47:31.039463Z","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":"2026-08-07T05:47:37.371099Z","title":"The impact of multimodal large language models on health care’s future","venue":null,"work_id":"2d1c9a45-3005-4629-af20-ae2dee7157fc","year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.136052Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:0e415516bc968649c67659fe52b57c91f3d7bbc95ba9e38ec07da532d84bb0e4","observation_id":"e40e413f-c0aa-41c6-a58c-2f531de2116d","resolution":{"observed_at":"2026-08-07T05:47:37.376981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:31.202224Z","title":"Rényi differential privacy","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.202224Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:cc1e56d6e7ddf84d552f82592579d3f555ae16364fd29b340c9bb4ac54285080","observation_id":"6eccc5c5-6f18-49d1-8cc9-ca0bacab1616","resolution":{"observed_at":"2026-08-07T05:47:31.202224Z","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":"2026-08-07T05:47:37.353723Z","title":"Regularizing deep neu- ral networks by noise: Its interpretation and optimization","venue":null,"work_id":"5390fdfc-55b9-43f5-b36e-fd0672fad958","year":2017},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.269284Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:930e68ef1b8b949a64257fb141a745937978accf0d8846a1f6e042d3087ef9e3","observation_id":"a0e7abcc-0ffd-4f84-8e0b-de79efb054f0","resolution":{"observed_at":"2026-08-07T05:47:37.359899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:31.355013Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.355013Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:1e319e915b6905901e515bca8d6581e1a7b44382150ed55852e257449b27bba7","observation_id":"9ad27907-e473-4248-84df-8c6c2cca50a2","resolution":{"observed_at":"2026-08-07T05:47:31.355013Z","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":"2026-08-07T05:47:31.417921Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.417921Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:42667343e6126d4534272611c62e6fe7037ef53e8a5bc1bd5750340ddcbdb8e3","observation_id":"52a16c27-7510-4c89-8265-700d1539e048","resolution":{"observed_at":"2026-08-07T05:47:31.417921Z","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":"2026-08-07T05:47:31.474290Z","title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.474290Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:8b45f34691aa17ee4ffce9f0a8b4a8d74ea011db07a77ae0bb5a5c6b86797886","observation_id":"e3b2b608-a864-48a7-8123-4a574813c17c","resolution":{"observed_at":"2026-08-07T05:47:31.474290Z","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":"2026-08-07T05:47:37.307434Z","title":"Seco de Herrera, et al","venue":null,"work_id":"a638447a-5681-4d5a-abf6-ccf4cc4d8a1d","year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.560429Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:ac0d25cc43011c7ccda41b69e1a5e4949ed717faf9549dfcafe15b89355f330b","observation_id":"f09af41f-e664-441e-9def-97d51fca9297","resolution":{"observed_at":"2026-08-07T05:47:37.312518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:31.638762Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.638762Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:613795925ce1a09e1e984d0668f300d261008d177317e8c62e4d904c19623eb0","observation_id":"32f4e6e6-ece9-42e8-9929-fee91fb03fea","resolution":{"observed_at":"2026-08-07T05:47:31.638762Z","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":"2026-08-07T05:47:31.730216Z","title":"Towards vqa models that can read","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.730216Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:f42a183040d7166ec889aeff21761508b07cb2efbdea26cada05e52702f8697d","observation_id":"4adc5666-0f86-43f2-a7ff-a0ea23ae2df7","resolution":{"observed_at":"2026-08-07T05:47:31.730216Z","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":"2301.12707","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:47:34.730021Z","title":"Differentially private image classification by learning priors from random processes","venue":null,"work_id":"46fcd3e1-73ee-460e-a915-7fd5685acf93","year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.828510Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:b286602c575bd53bd6d60e127d1e573ada7a081fa95587ddd94ffdf13ce34625","observation_id":"aec7e3d0-9ed4-4d03-a6d0-ab21969bb975","resolution":{"observed_at":"2026-08-07T05:47:34.773292Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04343","last_updated":"2025-01-31T02:33:07Z","snapshot_observed_at":"2026-08-13T04:46:51.653341Z","submitted_at":"2024-01-09T03:53:59Z","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04343","snapshot_observed_at":"2026-08-07T05:47:31.952969Z","title":"Pri- vate fine-tuning of large language models with zeroth-order optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:31.952969Z"},"links":{"cited_paper":"/paper/2401.04343","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:ee1c74df5e64c4dc0c0f490223b08201c474bf05650cb185875b7bf71dc6ef6f","observation_id":"78c5b743-d256-4814-b1be-04a752662912","resolution":{"observed_at":"2026-08-07T05:47:31.952969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T05:47:32.042603Z","title":"Llama: Open and efficient foundation language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.042603Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:81c8e58d8cfb2d63d0c4ba7114620c9869a0de8f0eba4f2d7f53b9145c734e06","observation_id":"be1a816c-192e-4b72-b860-4f4fa2c992ce","resolution":{"observed_at":"2026-08-07T05:47:32.042603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13303","last_updated":"2025-05-15T22:00:19Z","snapshot_observed_at":"2026-08-13T07:57:54.393510Z","submitted_at":"2024-12-17T20:09:55Z","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13303","snapshot_observed_at":"2026-08-07T05:47:32.126006Z","title":"Fastvlm: Efficient vision encoding for vision language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.126006Z"},"links":{"cited_paper":"/paper/2412.13303","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:63f1cd96e7db54829e8db0c75b5b7ecf6d57f3ed772e447ecf096982a657f0ff","observation_id":"c6000fa5-f4a4-403e-9b46-56ec7bf20067","resolution":{"observed_at":"2026-08-07T05:47:32.126006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12191","last_updated":"2024-10-03T15:54:49Z","snapshot_observed_at":"2026-08-06T05:35:29.109022Z","submitted_at":"2024-09-18T17:59:32Z","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12191","snapshot_observed_at":"2026-08-07T05:47:32.203358Z","title":"Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.203358Z"},"links":{"cited_paper":"/paper/2409.12191","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:769bf82d58236e5b22a4848ff7de88c3b0aa854547d38dd58b9cc6574cd20bb3","observation_id":"e7810090-a4c4-418c-bb66-f0d1405eb04d","resolution":{"observed_at":"2026-08-07T05:47:32.203358Z","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":"2026-08-07T05:47:37.271384Z","title":"Cogvlm: Visual expert for pretrained language models","venue":null,"work_id":"fc52dbd4-8379-4a25-8ece-e9d3920d1bb7","year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.253926Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:b04fff72e6c8c9acf0366ee7f4f1c5ced5e10214994c9192d86db532921c4ad1","observation_id":"3e989ec4-2b16-4122-a1eb-702df63ed0d8","resolution":{"observed_at":"2026-08-07T05:47:37.276458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.255610Z","title":"Joint token pruning and squeezing towards more aggressive compression of vision transformers","venue":null,"work_id":"679834a8-9759-4e14-a383-c64ed6de3732","year":2023},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.342254Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:9d5e422f23ebcfd5502978f2a47c3b3280dd66d1f5e4e471bf4021d9ba8d8ff2","observation_id":"e373d67e-061c-4794-8c4d-0df6c0f5e0c6","resolution":{"observed_at":"2026-08-07T05:47:37.261036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.240305Z","title":"Improving differentially-private deep learning with gradients index pruning,","venue":null,"work_id":"1a20df8a-0d8a-4b92-9e79-9be57a302433","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.412187Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:4372ecd1f0238cc934f5fb18f45a27cedb4569b8886a528735705ce7ff7a5566","observation_id":"0c229ab8-67ad-4164-89d4-c22b7b707e97","resolution":{"observed_at":"2026-08-07T05:47:37.245210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:32.566186Z","title":"Visionzip: Longer is better but not necessary in vision language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.566186Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:ae002800d274386466a6bc9d7d42c7587ea8af94a6cdd170ef3d5ad5655d1da1","observation_id":"b9649a70-ea0e-4728-a5d8-fa79fc68f371","resolution":{"observed_at":"2026-08-07T05:47:32.566186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-08-13T17:54:09.741380Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-08-07T05:47:32.651397Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.651397Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:3e93d1635d1a733199172baa1bc08efa1d6340be4cbdc369c807da4e9612eca5","observation_id":"25fa7251-23fe-422d-8680-caf89deb1404","resolution":{"observed_at":"2026-08-07T05:47:32.651397Z","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":"2026-08-07T05:47:37.210040Z","title":"Large scale private learning via low-rank reparametrization","venue":null,"work_id":"78c5be21-d436-48d6-8e43-555722ac5fbb","year":2021},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.731898Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:fedcea0e2f2f052a349f2caf7248463ed289ff55a6c5554531959b20abbe4447","observation_id":"b266d738-2622-4c8b-ba28-3685a65db844","resolution":{"observed_at":"2026-08-07T05:47:37.215258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-07T05:47:32.803460Z","title":"Opt: Open pre-trained transformer language models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.803460Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:df2840a4948f8281c6227c9d3ffbda2543ed3a3a4b4c93395becfdbd1904c8a2","observation_id":"29bc9a3a-8af8-435f-9a57-1517c0775cba","resolution":{"observed_at":"2026-08-07T05:47:32.803460Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13257","last_updated":"2025-02-05T08:44:02Z","snapshot_observed_at":"2026-08-13T00:35:03.634903Z","submitted_at":"2024-08-23T17:59:51Z","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13257","snapshot_observed_at":"2026-08-07T05:47:32.902897Z","title":"Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenarios that are difficult for humans? arXiv preprint arXiv:2408.13257, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.902897Z"},"links":{"cited_paper":"/paper/2408.13257","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:4f4cc24abc53bb6350102507da5a1be826dae3f83a6674c50b5dc052a9a96e8b","observation_id":"33d5db1f-8095-427d-b945-8d6152a1c6f3","resolution":{"observed_at":"2026-08-07T05:47:32.902897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-08-11T04:34:07.318549Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-07T05:47:32.960834Z","title":"one record","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.960834Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:2e9110be5288c871c8c510647c157ade2d1407e419ab7564115792d6d31ad784","observation_id":"c2f6fd31-86bc-41fb-b679-c91f8208a5ab","resolution":{"observed_at":"2026-08-07T05:47:32.960834Z","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":"2026-08-07T05:47:37.194187Z","title":"Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper","venue":null,"work_id":"753dcbdb-d39d-4536-a6c4-4e83006053ba","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.085401Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:af5e02cdc75f65be21593d0e84540aada3b1b2aae735de90997a4ba95a83b61a","observation_id":"e88c0e69-e830-4527-8951-2c1f412f2536","resolution":{"observed_at":"2026-08-07T05:47:37.199352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.178767Z","title":"Limitations","venue":null,"work_id":"3764f199-7e8d-4194-8656-100c4bbaaf0a","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.124493Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:d78078b28021aee2a935fc7621189a172d0d97b3154c10088abdeba9d7a531f6","observation_id":"fe51645e-5431-47a7-bb65-28c678c203af","resolution":{"observed_at":"2026-08-07T05:47:37.183692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.162528Z","title":"• All the theorems, formulas, and proofs in the paper should be numbered and cross- referenced","venue":null,"work_id":"57d86ee6-5845-4bbc-bad3-acc0ef7b55d9","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.229415Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:359376cf4054ee82741525c0312ed199d289c0060a4a3d3f340ee3891de3b84a","observation_id":"9b76857f-ce68-412f-8266-3dbffc7f95c9","resolution":{"observed_at":"2026-08-07T05:47:37.167606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.147338Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"6d16ca99-5470-4618-811c-fc0a3219a5d6","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.285985Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:22c041406170aa076298832c7e218132bb37393dcdcd798f718e56203e5b9bb4","observation_id":"2041c9f5-f7fb-4a71-bd4f-ffdc3953d360","resolution":{"observed_at":"2026-08-07T05:47:37.151911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.131215Z","title":"Guidelines: • The answer NA means that paper does not include experiments requiring code","venue":null,"work_id":"9d89c8e7-f7b7-42fe-b838-4ac6f0786b9b","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.360579Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:20707e0f8396cb27b35916445cf8f4700cb32e1017e346b90726a16b3820da9f","observation_id":"28a40c2c-841f-4f3b-a21b-0b9a0026df12","resolution":{"observed_at":"2026-08-07T05:47:37.136783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.115408Z","title":"• The experimental setting should be presented in the core of the paper to a level of detail that is necessary to appreciate the results and make sense of them","venue":null,"work_id":"3c1d414f-68de-4e70-a58b-2b2cb2795e78","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.424351Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:f229b5a8a2ea0a60a20e17b8ff9fa0fbc176811cb495f27810b952d6f1b7a358","observation_id":"19d0eb18-724b-4487-99b8-7beb427fa779","resolution":{"observed_at":"2026-08-07T05:47:37.119911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.101024Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"a10bd450-eeec-48fe-a3be-0462a01bbec5","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.534608Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:aca9f9d79100b590bfa9409ce54f048a2d2600820f3e5d16241d91ba1b1a1113","observation_id":"0d7cfbe5-3caa-4cff-8316-7ca5a73b0c6c","resolution":{"observed_at":"2026-08-07T05:47:37.105347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:36.934275Z","title":"• The paper should indicate the type of compute workers CPU or GPU, internal cluster, or cloud provider, including relevant memory and storage","venue":null,"work_id":"e399a931-28db-44c7-9267-241999260c8f","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.597282Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:2e6077f6eeb3c1a3aec6a31a72a8c6b544080305eb739e5a93723a67b2056cf7","observation_id":"2867b894-b8b7-4a14-957c-b97906cd2a2e","resolution":{"observed_at":"2026-08-07T05:47:37.031135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:36.625848Z","title":"Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics","venue":null,"work_id":"ad7b834c-4474-4073-9466-8f9d0984bf4d","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.728136Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:7ff5f5d1141bc3eef43a3e059a53630a34449b7b8757216d662cea8ce8f69ebf","observation_id":"c9713667-8ea8-4a0c-8c95-3267a41d3d24","resolution":{"observed_at":"2026-08-07T05:47:36.775217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:36.357499Z","title":"• If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact","venue":null,"work_id":"f8befa46-4f91-424c-9cf4-9f86823b4fb9","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.788202Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:ea451be503901ae2ae0df8ebacacfaea0f23a0885e12759c6077941066b86fae","observation_id":"4a236b3b-7372-4c14-948f-ae79215ec0c4","resolution":{"observed_at":"2026-08-07T05:47:36.512506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:33.875218Z","title":"Guidelines: • The answer NA means that the paper poses no such risks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.875218Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:ebacac9d84b379e68148f9ecbc0a198d7dd1691edaa50c073e1662c54a8af097","observation_id":"448099dd-b1ff-4bc3-89ab-068fca5ff9b2","resolution":{"observed_at":"2026-08-07T05:47:33.875218Z","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":"2026-08-07T05:47:36.047554Z","title":"Guidelines: • The answer NA means that the paper does not use existing assets","venue":null,"work_id":"9512aa0d-45f7-400b-8d9c-a88058d40a22","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:33.965650Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:f095f3540069860eb2ff6453f111c931cdf8699552a27e76c4c9f79e408218e0","observation_id":"2bf4c08d-3f3e-44db-a123-f837cf3e7e44","resolution":{"observed_at":"2026-08-07T05:47:36.155251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:35.850891Z","title":null,"venue":null,"work_id":"dbd41a0c-fd15-4b91-8cd6-9f98af6359e4","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:34.042383Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:2f88e94b2de4de009a9ef6173e12a4bc9e601521445612656414da1bc696e010","observation_id":"4c380288-8a9b-46ba-a9ad-713424ffdce1","resolution":{"observed_at":"2026-08-07T05:47:35.959418Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:35.752824Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"0c52db30-055a-45c2-9473-80daa5d5238b","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:34.118635Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:4bfd4637706e5411a7198d1a90bb4aa2eb138454643c30c6ea4ccc8826e6b2ec","observation_id":"3c4bdef4-4f4b-4253-bb4c-27e2a4857bb7","resolution":{"observed_at":"2026-08-07T05:47:35.774144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:35.626028Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"752bfe94-8628-43a2-8fdd-93aa5b8dfd6e","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:34.209769Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:09e43291e726b1d49fb2c9918e7aff806cbbb7b66e43617e0d77bfb9f2949c2e","observation_id":"6a7035cd-7642-41df-80d1-b8e26c797ec4","resolution":{"observed_at":"2026-08-07T05:47:35.671899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:35.431791Z","title":"28 Answer: [Yes] Justification: The core methodology of this research is centered on the differential private fine-tuning of Multimodal Large Language Models (MLLMs)","venue":null,"work_id":"d9bf7958-f2d2-4562-af75-5c6632c3a1de","year":2025},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:34.282348Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:41e4737116fcfc32a03bbcb0f38cd75f8f6cc91344c7b4c8c61772ab562bc4d4","observation_id":"01785de6-590c-40b1-9a63-a60484acabc8","resolution":{"observed_at":"2026-08-07T05:47:35.520788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-07T05:47:37.225338Z","title":"net/forum","venue":null,"work_id":"7f91a470-2a97-479b-88b7-9307b8a23742","year":null},"citing_paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T05:47:32.490931Z"},"links":{"citing_paper":"/paper/2506.07077"},"observation_digest":"sha256:91728fd7f856d6464b5306949b54a876ea83d1bfdd1cad364aacef155bdda244","observation_id":"ce7c417a-74dc-4cf8-a02f-7e74ee352a08","resolution":{"observed_at":"2026-08-07T05:47:37.229881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.07077","last_updated":"2025-06-08T10:33:01Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-13T18:30:16.506609Z","submitted_at":"2025-06-08T10:33:01Z","title":"Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":40,"verified_exact":2,"verified_fuzzy":28},"total_outbound_references":71},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 3 inbound Pith citation observations for arXiv:2506.07077."}