{"as_of":"2026-08-09T11:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:482338c61e5b4c7a4f9b88bf8b012ba7680aaeff8f28dc489b55b1e1e7fdbfb7","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:21:29.820285Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.02016/citation-record","integrity":"/paper/2506.02016/integrity","json":"/paper/2506.02016/citation-record.json","paper":"/paper/2506.02016"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:31.120843Z","title":"Intriguing properties of neural networks.Computer Science, 2013","venue":null,"work_id":"7cc78f7e-0513-4c49-b700-ef3fb1a9e1a1","year":2013},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:28.631259Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:be1cd08d7ad15fc1ed37cd89a86511eb91d29dca036390d3eeaedc37dfe948c6","observation_id":"2014eeb4-9857-43c4-ab57-fe167d140803","resolution":{"observed_at":"2026-08-07T13:21:31.166120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:28.689593Z","title":"Univer- sal adversarial perturbations","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:28.689593Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:afc19f35b6fc4d6b71f8f5f987970c4d93f91ebe51a1344a722f0ae90efe5626","observation_id":"ac5ab3d2-783e-430d-9a3e-8d605eb61f9c","resolution":{"observed_at":"2026-08-07T13:21:28.689593Z","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":"2026-08-07T13:21:30.984321Z","title":"Goodfellow, Jonathon Shlens, and Christian Szegedy","venue":null,"work_id":"f4f11030-48a1-4127-87ef-633a99b27816","year":2014},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:28.802455Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:bd1d94b2fabf9acb1c971f7e9ad1b489e574c0ad5b8ee3c4bff79f37bc5fd51f","observation_id":"aeeed728-7855-44e2-89b6-8acb571d6151","resolution":{"observed_at":"2026-08-07T13:21:31.041909Z","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":"1705.07204","last_updated":"2020-04-26T22:20:25Z","snapshot_observed_at":"2026-07-06T05:43:27.961693Z","submitted_at":"2017-05-19T21:56:43Z","title":"Ensemble Adversarial Training: Attacks and Defenses","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07204","snapshot_observed_at":"2026-08-07T13:21:28.922969Z","title":"Ensemble adversarial training: Attacks and defenses.arXiv preprint arXiv:1705.07204, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:28.922969Z"},"links":{"cited_paper":"/paper/1705.07204","citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:36acb2fda27ec69a650f09820453954acf1ffee3171e5ae4b5e6ed15f7fa3120","observation_id":"ea67c754-cc8b-4734-bb88-873643d07d82","resolution":{"observed_at":"2026-08-07T13:21:28.922969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-07T13:21:29.017286Z","title":"Towards deep learning models resistant to adversarial attacks.arXiv preprint arXiv:1706.06083, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.017286Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:6e802a7b112b25c025ac492db162d81cde391e22e2139a1fa012701ff1ba57e5","observation_id":"d76a82c5-75c2-4a00-b5b9-af1c7d913e9b","resolution":{"observed_at":"2026-08-07T13:21:29.017286Z","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":"2026-08-07T13:21:29.076882Z","title":"Towards evaluating the robustness of neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.076882Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:dcacbfe50ac890193783ded6295372d5c48674d4c4b8d7a32afe437b8da60cac","observation_id":"3598dc6b-8e97-4531-abbe-345ccb2d06b0","resolution":{"observed_at":"2026-08-07T13:21:29.076882Z","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":"2026-08-07T13:21:30.846733Z","title":"Distillation as a defense to adversarial perturbations against deep neural networks","venue":null,"work_id":"1b308820-aa77-43fd-b3fd-8e495f6a7b18","year":2016},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.173028Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:5e09b083b0e2685af75340093fb2309343fe5e02a083ceb4773fabfdab57317c","observation_id":"74f84cc6-8289-43e1-a5fc-ec6cff4a4e25","resolution":{"observed_at":"2026-08-07T13:21:30.908959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:29.291023Z","title":"Deepfool: a simple and accurate method to fool deep neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.291023Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:f8109a956711bfbd26f6900dbba6add8626fdcef50041ff0725681d45c8b3a0d","observation_id":"baf6b9f1-8d8c-440c-b611-db526453d148","resolution":{"observed_at":"2026-08-07T13:21:29.291023Z","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":"2026-08-07T13:21:30.652431Z","title":"Adversarial examples are not bugs, they are features","venue":null,"work_id":"de6aa70a-dc47-4b6f-bc39-5362378f1abc","year":2019},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.379321Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:bcb7f07069f80eb79a659eb087bb37f2be87a47367a3e7cb05ceb8c357c16814","observation_id":"598088fc-9c10-491d-a3b9-2b377d4fe6de","resolution":{"observed_at":"2026-08-07T13:21:30.742916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:30.514416Z","title":"Adversarial sample detection through neural network transport dynamics","venue":null,"work_id":"9946b4d4-ba59-4ea6-afae-21398035080d","year":2023},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.446803Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:62f5c0d1afb6176a97f456c96090e5322e218a06b7ea4693be7fe007bfc32765","observation_id":"609347f9-949e-4493-9e78-6d9a1eaafc8e","resolution":{"observed_at":"2026-08-07T13:21:30.588139Z","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":"2405.00985","last_updated":"2024-05-02T03:48:08Z","snapshot_observed_at":"2026-08-09T04:36:38.560964Z","submitted_at":"2024-05-02T03:48:08Z","title":"Progressive Feedforward Collapse of ResNet Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00985","snapshot_observed_at":"2026-08-07T13:21:29.521845Z","title":"Progressive feedforward collapse of resnet training","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.521845Z"},"links":{"cited_paper":"/paper/2405.00985","citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:e68694d46fe37d38070b3f838e08aff39362619b6f5812a7e6e4d6d0d36a4355","observation_id":"e53f8521-c75b-4a20-b999-47d4d604c670","resolution":{"observed_at":"2026-08-07T13:21:29.521845Z","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":"2026-08-07T13:21:30.334433Z","title":"Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 2020","venue":null,"work_id":"65b1409b-0d1e-4d9d-9fb3-cdc3569ab4eb","year":2020},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.584880Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:f77f4d08e9ebe38d3318c937424e04bfe0ae1232d089772c42e56b1d2423cb69","observation_id":"e52c5d04-7885-43c5-9c25-431680726646","resolution":{"observed_at":"2026-08-07T13:21:30.380635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:30.242976Z","title":"A law of data separation in deep learning.Proceedings of the National Academy of Sciences, 120(36):e2221704120, 2023","venue":null,"work_id":"79b8ef24-4a64-41ab-96a2-35e590ade642","year":2023},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.647925Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:84b906f1bb5f995bc7afccdcf05b1d6ad1641ff59f5704884ec5adefdafd8940","observation_id":"e35dd667-9f32-4250-b8e2-a8572b450d95","resolution":{"observed_at":"2026-08-07T13:21:30.290808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:30.108831Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":"481965da-48be-4c8a-a60d-1c08b0400d1f","year":2020},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.731995Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:73a8dd639640450c6ae502f7428dc5f205fc11d5827f726043e306111d642af1","observation_id":"81a99a67-1d96-4df7-ae12-11085efd5fb0","resolution":{"observed_at":"2026-08-07T13:21:30.175116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:21:29.939290Z","title":"A threshold selection method from gray-level histograms.IEEE Transactions on Systems Man & Cybernetics, 9(1):62–66, 2007","venue":null,"work_id":"73e2f403-423b-4704-9dd9-d33309c48dca","year":2007},"citing_paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:29.820285Z"},"links":{"citing_paper":"/paper/2506.02016"},"observation_digest":"sha256:7dd1a2a7c63df95626e8f8eca44f4108958a9d8db51f0f83b9e1e3a1f171c16b","observation_id":"4df51198-b8b6-4119-89e0-4bc182444f25","resolution":{"observed_at":"2026-08-07T13:21:29.992401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.02016","last_updated":"2025-05-28T06:58:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T07:12:13.626087Z","submitted_at":"2025-05-28T06:58:05Z","title":"Are classical deep neural networks weakly adversarially robust?"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":9},"total_outbound_references":15},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2506.02016."}