{"as_of":"2026-08-10T03:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9708c1afbaea80fe7b48ae63519f449f902a9da87ffe2a1104464d4ec7772697","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T14:56:11.099966Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2604.12307/citation-record","integrity":"/paper/2604.12307/integrity","json":"/paper/2604.12307/citation-record.json","paper":"/paper/2604.12307"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.14359","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T03:57:38.911959Z","title":"Dual data alignment makes ai- generated image detector easier generalizable","venue":null,"work_id":"a5b5a89f-bea7-4183-9d6e-fd5a1a14a366","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:ece84ca2790863343c5554886193d15663f4eb9c645c0f7bd781bb73f2233b80","observation_id":"5fab3815-269c-41ee-bf5b-b94802feb295","resolution":{"observed_at":"2026-05-11T11:26:01.857486Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fair deepfake detec- tors can generalize","venue":null,"work_id":"8fd150d7-b9f9-4084-a95e-72516152c7be","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:e485cdad47e0c1b2dac7725087740f92f179d8ce4632c9c37f8d49e2832ef24a","observation_id":"8caebc8c-6528-4249-99b5-da751949b449","resolution":{"observed_at":"2026-05-18T10:52:34.869008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22062","last_updated":"2025-08-01T06:40:13Z","snapshot_observed_at":"2026-08-09T05:04:47.864375Z","submitted_at":"2025-07-29T17:59:58Z","title":"Meta CLIP 2: A Worldwide Scaling Recipe","version":3},"cited_work":{"arxiv_id":"2507.22062","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.22062","snapshot_observed_at":"2026-07-04T13:39:50.777855Z","title":"Meta clip 2: A worldwide scaling recipe","venue":null,"work_id":"35c3d2a3-1b34-4131-b73a-976f4727f77f","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2507.22062","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:1a3dced11f273197fe0e58b9b0e66415f7ef8f31c2727ef7a246c54158d92669","observation_id":"2842cd12-81a7-4d8a-944c-a8efe8790ae3","resolution":{"observed_at":"2026-05-11T11:26:01.868275Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the detection of synthetic images generated by diffusion mod- els","venue":null,"work_id":"70a58cb6-b0cc-4da7-b9d3-c39a62e8e79d","year":2023},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:13e73d37d600ccdcccd4b6fc63beb98369bf561f38794da4dcf31dd555a943c6","observation_id":"dee82331-988e-496c-9a4d-03dd913b87c0","resolution":{"observed_at":"2026-05-18T10:52:34.824628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Forensics adapter: Adapting clip for generalizable face forgery detection","venue":null,"work_id":"25a8cce3-b680-4e98-b852-9c21eccb32f8","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:c7ce4692db7f9ceb83dfd123eb9803543aa14cba4ea60224f66d629e21348a71","observation_id":"3eac5ec2-f58c-4b27-a11d-92984ab6e14b","resolution":{"observed_at":"2026-05-18T10:52:34.799656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Think twice before detect- ing GAN-generated fake images from their spectral domain imprints","venue":null,"work_id":"d61522a2-0b5b-4311-87b4-548937dc0d37","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:786653c694109242fbda3ef2a655cff6bc07bcaa2da7a80f44876c340b5ebd7a","observation_id":"c4c213a1-6eba-4e06-bf8a-4612566a69de","resolution":{"observed_at":"2026-05-18T10:52:34.856129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Watch your up-convolution: Cnn based generative deep neural net- works are failing to reproduce spectral distributions","venue":null,"work_id":"5a13f4f3-4441-4073-9713-5f39ecb21f93","year":2020},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:2d1dd0cced1888abef8dab100e5ba8d83d0ec2597874118386f86217a32e1e9a","observation_id":"2fe6aa86-ae2f-4d3d-a552-dec5d2bcb0f1","resolution":{"observed_at":"2026-05-18T10:52:34.810324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leveraging fre- quency analysis for deep fake image recognition","venue":null,"work_id":"fa61c32d-5a45-4915-9283-5786aafb754c","year":2020},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:5d6f33d5124d16a09dea94c1713ed353cd8639552d2a015d369e9f663fb5544f","observation_id":"fe0daba2-bf5d-4b91-b58c-1152a4931d06","resolution":{"observed_at":"2026-05-18T10:52:34.807623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15035","last_updated":"2024-06-21T10:33:09Z","snapshot_observed_at":"2026-08-10T02:18:33.507472Z","submitted_at":"2024-06-21T10:33:09Z","title":"Improving Interpretability and Robustness for the Detection of AI-Generated Images","version":1},"cited_work":{"arxiv_id":"2406.15035","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.15035","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving interpretabil- ity and robustness for the detection of ai-generated images","venue":null,"work_id":"cac615d9-0457-48e1-9b47-af4bc4508980","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2406.15035","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:8e8e66d5818fd6741fbd7eab368fbe7dae5b1efbae352a47d3a2601aeb7f1327","observation_id":"0935c2d2-dda4-44ed-8ec3-84621cc3bddf","resolution":{"observed_at":"2026-05-11T11:26:01.812112Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild","venue":null,"work_id":"4e5740a9-d507-4c9e-b747-2defb3a0a63a","year":2026},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:ec151efcf476064e4b0722f85ebf5dd5a2bf8fec0dba529f8dacca0d1ade22e2","observation_id":"64c63c32-5555-45b8-9748-c47c12fcfc54","resolution":{"observed_at":"2026-05-18T10:52:34.881581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"68a3ffb5-ecd6-4fdb-8458-e2c07cbe17e3","year":2019},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:20786343044f599b554726710e843ec2a83e4a0b9363182fbe936cec134bcb4f","observation_id":"418b7cdb-a416-4883-b07d-b5497f82defd","resolution":{"observed_at":"2026-05-18T10:52:34.844415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"LoRA: Low-rank adaptation of large language mod- els","venue":null,"work_id":"4be1cda6-e79b-46cc-a91e-8cd295ed021f","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:2a2794508d1e1e4bf6cc9c09af50520ea1fffa4fe6bbad2b92f7e49102778f22","observation_id":"30dedbfe-532d-455d-b521-7b1c2c887d6c","resolution":{"observed_at":"2026-05-18T10:52:34.851230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18660","last_updated":"2026-07-31T15:32:37Z","snapshot_observed_at":"2026-08-09T09:24:36.237155Z","submitted_at":"2025-05-24T11:53:35Z","title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","version":5},"cited_work":{"arxiv_id":"2505.18660","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.18660","snapshot_observed_at":"2026-08-03T03:15:17.929242Z","title":"So-fake: Benchmarking and explain- ing social media image forgery detection","venue":null,"work_id":"fc6205cc-ee4b-4cc4-af94-3608fdb0514b","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2505.18660","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:cf3e90d12b5ebe9b2d0a40dcb794fc8211ab94a00943fd0426039b1f99c3e283","observation_id":"0e011906-24bf-4ca6-94b3-515c1663b51f","resolution":{"observed_at":"2026-08-03T03:15:17.929242Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling up visual and vision-language representa- tion learning with noisy text supervision","venue":null,"work_id":"647979ac-3e2a-40ff-9a70-d27180867670","year":2021},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:c7d9732595b32d2f1f5cae784f4c876849577175ac19d4bdc21038000886a544","observation_id":"50651ad7-54a9-44ce-b8d2-3ec263efa5b4","resolution":{"observed_at":"2026-05-18T10:52:34.804731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vi- sual prompt tuning","venue":null,"work_id":"b3261a5f-7c31-4fc3-a2cc-652653ea9480","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:522de96cf8af37791c09c8a076f80e2164cbc5f0724fd430b7f49bc8eaf4cb01","observation_id":"f2087ffc-d67c-49a6-9c50-f8b7b3a77438","resolution":{"observed_at":"2026-05-18T10:52:34.838404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"0ad645b9-1552-4a13-b62b-dbc5b569ee3d","year":2019},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:0f0c79dbc298adc50b5b9391eef661a02ad56c088c6e74f45b97377ce2cbc2cc","observation_id":"15806984-9785-4056-a3e9-ca2430cd7751","resolution":{"observed_at":"2026-05-18T10:52:34.878803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.10236","last_updated":"2026-05-15T17:35:28Z","snapshot_observed_at":"2026-07-06T21:56:49.263374Z","submitted_at":"2025-07-14T12:56:55Z","title":"Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?","version":2},"cited_work":{"arxiv_id":"2507.10236","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.10236","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Navigating the challenges of ai- generated image detection in the wild: What truly matters?","venue":null,"work_id":"ca2fd6ae-48c7-47b7-8481-4f6e157a6d33","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2507.10236","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:5709de3f243433cd5493f317b890977f610cb31fa75b30a6ca5c2f60406d6255","observation_id":"5c416c74-54f8-4be4-8ef1-f20e77f82b21","resolution":{"observed_at":"2026-05-20T00:01:34.726456Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leveraging rep- resentations from intermediate encoder-blocks for synthetic image detection","venue":null,"work_id":"f17d25f8-b24e-4075-90d3-763f32511ec8","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:5d197a58ec743d9cddd1e6ae02455b109763d59656b1ab2280d6aaac278fbf98","observation_id":"d1c57c36-aa68-44fd-95f4-3a45f2823517","resolution":{"observed_at":"2026-05-18T10:52:34.846658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning real facial concepts for independent deepfake detection","venue":null,"work_id":"89c41a4a-91bb-4028-b67b-c5fe637c3efa","year":null},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:c43473ab93282adc1f6951f8e850be613a83597aa5a842963431097c5b130c4b","observation_id":"fbd41d37-5b2e-48a7-bed3-b55fb86c526b","resolution":{"observed_at":"2026-05-18T10:52:34.798471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":"1608.03983","doi":"10.21203/rs.3.rs-7055642/v1","metadata_source":"pith","pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","venue":"cs.LG","work_id":"ad476478-c5ea-495b-a454-168c504bbfcc","year":2016},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:63bb73459b352bc685fa6d1267951d477394d588b6d24fe929d9b5716402a18b","observation_id":"e3c410d9-28a6-495a-a02f-5ac9b78a0c51","resolution":{"observed_at":"2026-05-11T11:26:01.793642Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":"1711.05101","doi":"10.1137/1.9781611972825.47","metadata_source":"pith","pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Decoupled Weight Decay Regularization","venue":"cs.LG","work_id":"07ef7360-d385-4033-83f7-8384a6325204","year":2017},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:febc28b84da4aff6f42f8b00a44d190b32f158a3187979812a7ed6da601903f4","observation_id":"0f5a8c50-b050-4dd7-b3b7-e7fc487af8c4","resolution":{"observed_at":"2026-05-11T11:26:01.826347Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Detecting gan-generated images by orthogo- nal training of multiple cnns","venue":null,"work_id":"d13e1c2f-f10b-4b47-b159-1eb4e2ed1f02","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:547e52d2a79a753c5e4220dc1da478ea970d44c99669071312f789614b64847a","observation_id":"2d7b80f0-68bd-4061-8ecf-4b43c24e4b39","resolution":{"observed_at":"2026-05-18T10:52:34.830668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.11842","last_updated":"2018-12-31T15:32:33Z","snapshot_observed_at":"2026-08-09T11:08:56.256545Z","submitted_at":"2018-12-31T15:32:33Z","title":"Do GANs leave artificial fingerprints?","version":1},"cited_work":{"arxiv_id":"1812.11842","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1812.11842","snapshot_observed_at":"2026-07-04T23:18:05.990488Z","title":"Do GANs leave artificial fingerprints?","venue":null,"work_id":"dd9ac661-637d-4bcb-856a-3fe8e02ad8c8","year":2019},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/1812.11842","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:9ef7639865160d87cf3ffe28d27964fa7ebde291e6ace9f9a5c241629cb14893","observation_id":"78da3e06-ac63-49f2-9dc9-7077b560b334","resolution":{"observed_at":"2026-07-04T23:18:05.990488Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards uni- versal fake image detectors that generalize across generative models","venue":null,"work_id":"9649b167-b9e3-4b47-ab1e-c77c782e53d1","year":2023},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:2b8dbf15f4d1dc05d959aedd35a108a9ea0d07a75cda68b9f6b4ced2d0489cb6","observation_id":"5e996b9a-92ad-4395-a989-9abb4fd9d675","resolution":{"observed_at":"2026-05-18T10:52:34.859058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T05:14:35.715460Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"292e4202-5927-473f-b73e-1d6883498f14","year":null},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:b69dc3ae638824134c14a4249b887cea7ff65f2e46d0d0c938851391df2616e3","observation_id":"f6c75790-1864-4621-90f0-fa7fec12c621","resolution":{"observed_at":"2026-05-18T10:52:34.872670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"83c0cb2b-3bb6-4449-b9e1-7b5d66f66f0d","year":2021},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:dcffa434e2fcd3da89c7f5efe28a8f815c91c2f6ea297a56ef1863a656329d0f","observation_id":"d9a5386a-08c5-42db-b9d2-25ea107f298a","resolution":{"observed_at":"2026-05-18T10:52:34.841193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Im- proving robustness against common corruptions with fre- quency biased models","venue":null,"work_id":"1e229a29-f04c-4ef8-9926-5e5d55e6aced","year":2021},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:7233fa7af7650f0cb53f2c8a6a05d23d5fe928944bb9c829ed93eee49b607c3c","observation_id":"963b6fb3-0cc3-4d09-9bcc-907d850a1014","resolution":{"observed_at":"2026-05-18T10:52:34.835869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shield: An evaluation benchmark for face spoofing and forgery detection with multimodal large lan- guage models.Visual Intelligence, 3(1):9","venue":null,"work_id":"8481bbe6-6886-41d9-8472-a91c0aeabfda","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:fc54cae6d9d46a370d8906bb1ceb936d4236f3e94238ba29c09cb71a133ad43c","observation_id":"ca64eb8d-3806-4e17-b844-37b3c86cda1f","resolution":{"observed_at":"2026-05-18T10:52:34.818066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Flava: A foundational language and vision alignment model","venue":null,"work_id":"8ae64a84-62c2-402c-8902-c33af9cb4d17","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:2acd8d9888b8d6c3932c6217fc7ad87c7dd652d3e232f4e390b902a375923372","observation_id":"977ee17f-386f-448b-b76b-08b2970ac303","resolution":{"observed_at":"2026-05-18T10:52:34.875764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-07-06T10:01:50.133383Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":"2010.02502","doi":"10.48550/arxiv.2010.02502","metadata_source":"pith","pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Denoising Diffusion Implicit Models","venue":"cs.LG","work_id":"8fa2128b-d18c-405c-ac92-0e669cf89ac0","year":2020},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:8de2de5722b4d47b06dc2fb93f557ef470b3ce019af49f461528b921cd9475fa","observation_id":"3dd9980b-50d6-4f14-bb11-150e184afd38","resolution":{"observed_at":"2026-05-11T11:26:01.875564Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-07-12T13:49:41.147667+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T13:49:41.147667+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards general visual-linguistic face forgery detection","venue":null,"work_id":"9a8b5748-adb0-4de6-a720-ec8e66dab565","year":null},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:dced981738c29420374b927e4a650c18852ab3720e0ec9efcc464c27b104002c","observation_id":"aad6fa68-1cde-451c-af16-909cfbf725cf","resolution":{"observed_at":"2026-05-18T10:52:34.862059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15389","last_updated":"2023-03-27T17:02:21Z","snapshot_observed_at":"2026-07-06T15:08:34.018146Z","submitted_at":"2023-03-27T17:02:21Z","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","version":1},"cited_work":{"arxiv_id":"2303.15389","doi":"10.48550/arxiv.2303.15389","metadata_source":"pith","pith_arxiv_id":"2303.15389","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","venue":"cs.CV","work_id":"0c16c250-fd0f-446a-bbb0-ea8dd0ba5ccd","year":2023},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2303.15389","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:e95e647cbdca4f838a04a453001f06eb2a4c5394ea3edd3ac0249d7c983dafe1","observation_id":"6b520045-579d-42f9-a8ca-fe98c2fbca43","resolution":{"observed_at":"2026-05-13T01:54:22.133331Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking the up-sampling op- erations in cnn-based generative network for generalizable deepfake detection","venue":null,"work_id":"a3d81a7b-2cd7-463e-b7e8-e35ed013abaf","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:8e13880110d4d7e6660c28890447805ba762873b3dc94f5bfb0bfa4fd472fe8f","observation_id":"aeeb1650-bdeb-469f-a1a2-810a1ea4d124","resolution":{"observed_at":"2026-05-18T10:52:34.812964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.10231","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Seman- tic visual anomaly detection and reasoning in ai-generated images","venue":null,"work_id":"a0b5085f-4178-40b8-b314-26a6361a807b","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:99d208dd38f3e46c659b3a42cfefb2729958af01a4f5ce65bf1563d1ad5a4c52","observation_id":"a0753c61-9e16-45ea-802f-1768df53a3fe","resolution":{"observed_at":"2026-05-11T11:26:01.882229Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Oddn: Addressing unpaired data challenges in open-world deepfake detection on online social networks","venue":null,"work_id":"3f85ec01-22d2-4386-b60f-0fc5b9a12e01","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:b244ccc76ad26983a66be8bfd7056a9d8ecdf3e81dc5880e455cf39cca0c2b86","observation_id":"6c7da4dc-b917-42c9-9638-8c5735155a67","resolution":{"observed_at":"2026-05-18T10:52:34.820686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving robustness to corruptions with multiplica- tive weight perturbations.Advances in Neural Information Processing Systems, 37:35492–35516","venue":null,"work_id":"1f785ec0-872b-40ae-b26f-afc102620f3d","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:cdde2df514ad76e5c48750f91af11fe8f04b1b3a0ed199d4c7ea94b19bad0585","observation_id":"76549f38-3bde-4417-ab92-cc80109e028f","resolution":{"observed_at":"2026-05-18T10:52:34.865361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cnn-generated images are surprisingly easy to spot","venue":null,"work_id":"fc88885e-dcd7-4df8-9ef6-0767d2e34b38","year":2020},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:831beb7159714202a6ca1c3846a5e328e5fe93d5d2a046863cc368eaa2783461","observation_id":"88fe80ce-a450-41c6-949d-07fa657f0159","resolution":{"observed_at":"2026-05-18T10:52:34.849052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19435","last_updated":"2025-02-15T16:01:36Z","snapshot_observed_at":"2026-08-06T05:38:31.927956Z","submitted_at":"2024-06-27T17:59:49Z","title":"A Sanity Check for AI-generated Image Detection","version":3},"cited_work":{"arxiv_id":"2406.19435","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.19435","snapshot_observed_at":"2026-07-08T12:04:50.442080Z","title":"A sanity check for ai-generated image detection","venue":"cs.CV","work_id":"8b1627f4-5434-49ca-9cf6-3496ae1c191d","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2406.19435","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:23f6a95ed3b278e184da4e4d3aca0d9c1b51b664f4f387003e2f232281fe97f2","observation_id":"5fb2f1c1-fbc2-446a-b4b3-94bc5707bcb3","resolution":{"observed_at":"2026-05-11T11:26:01.837635Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15633","last_updated":"2025-05-20T12:06:56Z","snapshot_observed_at":"2026-08-06T14:53:33.853203Z","submitted_at":"2024-11-23T19:10:32Z","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","version":4},"cited_work":{"arxiv_id":"2411.15633","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15633","snapshot_observed_at":"2026-07-09T17:16:23.136828Z","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","venue":"cs.CV","work_id":"3ee10805-5d15-48ba-955d-528468dc1f6f","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/2411.15633","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:94cbd5f1c058f785ad751d5c827e3aa854a1457203ab2e9b527dd3e8457479d0","observation_id":"4f9a683e-8b74-4fa3-a96c-e4ac206f6a02","resolution":{"observed_at":"2026-05-17T23:25:48.212043Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Attributing fake im- ages to GANs: Learning and analyzing GAN fingerprints","venue":null,"work_id":"8385c397-0049-4256-9aea-3e9d389476c7","year":2019},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:a4af97807e3839f212030b31847791990c6556af4198b1dc3daf20c5242d706f","observation_id":"db8fd7bb-1e5d-40d1-aab3-9b6354822e9c","resolution":{"observed_at":"2026-05-18T10:52:34.801733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mlep: Multi-granularity local entropy patterns for generalized ai-generated image detection","venue":null,"work_id":"ba55fdbf-74fd-4545-963b-55195a68b63d","year":2025},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:8fdfeafb93169f3ce80c9bafae131ad641c66ac1a6dfab65a4418aef2c5511b8","observation_id":"7897b558-0268-42e6-933e-6b2b01b7e664","resolution":{"observed_at":"2026-05-18T10:52:34.815441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lit: Zero-shot transfer with locked-image text tuning","venue":null,"work_id":"ede358c1-f53f-44f1-9211-d6796dd4aae1","year":2022},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:7e9966aa5174444d0975009432dbb8a6dc1cb58714af7f87279e6d3b74776fbd","observation_id":"c8c1d7ec-78de-4cb0-9e9a-2c2899033b91","resolution":{"observed_at":"2026-05-18T10:52:34.853549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adalora: Adap- tive budget allocation for parameter-efficient fine-tuning","venue":null,"work_id":"b0a7d77c-c54d-43ba-b3c1-fb114fd599b5","year":2023},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:ebd78bab3b21bba0c92b973e9663ac7e3ba20eda3606ac58bdbcfcf7e17ba412","observation_id":"cdbd60a8-1044-451d-9dbc-5615ae7904a8","resolution":{"observed_at":"2026-05-18T10:52:34.827556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.06515","last_updated":"2019-10-15T22:53:46Z","snapshot_observed_at":"2026-07-06T08:07:47.943239Z","submitted_at":"2019-07-15T14:22:34Z","title":"Detecting and Simulating Artifacts in GAN Fake Images","version":2},"cited_work":{"arxiv_id":"1907.06515","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1907.06515","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:1907.06515 , year=","venue":null,"work_id":"0d218ad4-8eae-4499-802f-3dfbaaaa4d4a","year":1907},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"cited_paper":"/paper/1907.06515","citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:7f6f16b416f083ffeaa2abc8833764b4f8a67783d64a432e2e8dcd828779a05e","observation_id":"2f7e2977-55cb-4539-82df-a645bf368700","resolution":{"observed_at":"2026-05-11T11:26:01.784164Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Breaking semantic artifacts for gener- alized ai-generated image detection","venue":null,"work_id":"d3ba9fb0-dbf5-49fb-bb4d-a8a42d696f40","year":2024},"citing_paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T14:56:11.099966Z"},"links":{"citing_paper":"/paper/2604.12307"},"observation_digest":"sha256:43547bdb4d98e6789140aaeaca7a68cfbb68d98969536544f4488ab1322d0064","observation_id":"104eef72-1dd7-4c3f-82c7-d5ab904eee86","resolution":{"observed_at":"2026-05-18T10:52:34.791950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.12307","last_updated":"2026-04-14T05:35:32Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T05:35:32Z","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":14,"verified_fuzzy":31},"total_outbound_references":45},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2604.12307."}