{"as_of":"2026-08-16T13:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8806ee3a0eccc8330adf19d5590a6b27611c4a844bbc780a4c79b7a73235ae5b","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T10:22:04.654983Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2509.04214/citation-record","integrity":"/paper/2509.04214/integrity","json":"/paper/2509.04214/citation-record.json","paper":"/paper/2509.04214"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:22:04.546361Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.546361Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:340ec0c32f23fe5ab6f2da26c9c5f680ac830d391856d7e06524ee547a6a9641","observation_id":"dee8f82e-d1ac-4324-8e9c-e18aa4cde941","resolution":{"observed_at":"2026-08-05T10:22:04.546361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06721","last_updated":"2024-08-13T08:26:32Z","snapshot_observed_at":"2026-08-16T13:26:48.101975Z","submitted_at":"2024-08-13T08:26:32Z","title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","version":1},"cited_work":{"arxiv_id":"2408.06721","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.06721","snapshot_observed_at":"2026-08-05T10:22:05.133073Z","title":"Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities","venue":"cs.CV","work_id":"b5100957-a1ae-43e9-ab6a-0ee27e2a5414","year":2024},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.552395Z"},"links":{"cited_paper":"/paper/2408.06721","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:bc223c5ca760c9a795dc00d7850d56dfcf8f367d1f7ce8d57761299188a17d9e","observation_id":"dfd22304-5831-47bf-9cde-f56d41ec539f","resolution":{"observed_at":"2026-08-05T10:22:05.138364Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2019.29387","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:22:05.108258Z","title":"An Attack-Based Evaluation Method for Differentially Private Learning Against Model Inversion Attack,","venue":null,"work_id":"4c88a13a-353e-4f22-be9d-19ebae71725f","year":2019},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.558430Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:0df8d017279b277b48eb797f0c13d3fd4ec920fc6811704b3cce3420be30e15e","observation_id":"27d54235-2105-4d19-8a70-444feacee751","resolution":{"observed_at":"2026-08-05T10:22:05.116325Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.359445Z","title":"Checkpoint for bart-large after being trained on the MultiNLI (MNLI) dataset","venue":null,"work_id":"c3f6c815-ee76-4af1-80ed-8feb4678c588","year":2025},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.563049Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:eb5e1af032fe08dcd6da0d8de3033dc4da9516e9e230728f1725453388f6b820","observation_id":"a011ff36-f718-4cee-8f32-d3992992c6c5","resolution":{"observed_at":"2026-08-05T10:22:05.365498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.344521Z","title":"Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield But Also a Catalyst for Model Inversion Attacks,","venue":null,"work_id":"2950e0a0-0911-41a0-a05d-70540caae2d5","year":2024},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.567953Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:9cede6a2ea6f4a2f6d4f4ffcfcfd2a141a6e6e3c4badf467d170abd93739c51a","observation_id":"4474a841-3519-4b9c-9f96-1f890d6ac544","resolution":{"observed_at":"2026-08-05T10:22:05.349362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:04.572589Z","title":"Rethinking the inception architecture for computer vision,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.572589Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:b8c1046a6af67604fde83e1b405cfebde01616764772611096f758dae8d118db","observation_id":"38aa8414-4486-469c-b624-2f71df08566b","resolution":{"observed_at":"2026-08-05T10:22:04.572589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-05T10:22:04.577919Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.577919Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:bc6e034cf483b054004e667fbf681e34834552e2b696f06db66d30a7fd4ada6b","observation_id":"92e63ea8-3138-47da-8570-ab7902a4de74","resolution":{"observed_at":"2026-08-05T10:22:04.577919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.04381","last_updated":"2019-03-21T19:44:34Z","snapshot_observed_at":"2026-08-14T19:55:28.045143Z","submitted_at":"2018-01-13T04:46:26Z","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04381","snapshot_observed_at":"2026-08-05T10:22:04.587059Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.587059Z"},"links":{"cited_paper":"/paper/1801.04381","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:348b97c73de825576e43dc5dc0dc0b723fb1e5887253baee26cf1b89bed7d370","observation_id":"bf784742-208e-4baf-9f60-1894ee7cabf9","resolution":{"observed_at":"2026-08-05T10:22:04.587059Z","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":"2026-08-05T10:22:05.328945Z","title":"Visualizing and understanding convolu- tional networks,","venue":null,"work_id":"9ef0c29e-6713-4437-8f4a-faf705cdfea2","year":2014},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.591364Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:afe5505fd4b812da6f3f05d8cd73d805be99e34cbbcd1d3a01fd82930f3ac9fe","observation_id":"10f53a16-4ada-496a-8f15-9c994589501d","resolution":{"observed_at":"2026-08-05T10:22:05.333944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.312910Z","title":"The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks,","venue":null,"work_id":"36c579a6-4e1b-4057-b794-b618b33c9601","year":2020},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.596412Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:06104eb9f410ee291a380c4c43881ec1e3e9fe3708319d19b79d1d349d462201","observation_id":"49b5e3c2-6287-41ba-acf5-0cc9fe047eb4","resolution":{"observed_at":"2026-08-05T10:22:05.317967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-05T10:22:04.601265Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.601265Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:264bd0a0321061a3e83fd4a8bf0b400a32a2b7713ad5805185c1994526971fbe","observation_id":"303366d1-df3b-4f2f-bab7-bfd0f377342a","resolution":{"observed_at":"2026-08-05T10:22:04.601265Z","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":"8408.36192","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:22:04.992062Z","title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models,","venue":null,"work_id":"0608ab7b-7056-47ce-ab66-5c63c422718f","year":2023},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.606265Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:49778d0baa868859747c00fec588c86986dd3cb6e6a8f0466298eef40b7a52f0","observation_id":"d1017104-3edf-43a1-91e9-5949eb23e962","resolution":{"observed_at":"2026-08-05T10:22:04.999648Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"6122.36682","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:22:04.903116Z","title":"InstructBLIP: towards general- purpose vision-language models with instruction tuning,","venue":null,"work_id":"9ef71c7b-f956-4096-ba86-e1d90317e2c7","year":2023},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.610773Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:da87234a98c1e16c4b96978c35d0450e7192edc343f1e867f8ce020c5ccf44e6","observation_id":"8be9f290-1d57-4ba1-89bd-98610f7cb82a","resolution":{"observed_at":"2026-08-05T10:22:04.912481Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.296574Z","title":"An analysis of single-layer networks in unsupervised feature learning,","venue":null,"work_id":"a9c15778-9dd5-4fb8-8f48-19d81ea3b277","year":2011},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.615456Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:b81f5910b8f07713e6c159dfe461ef7073504cc94e87a66bb05f9faaee6858eb","observation_id":"be0e850c-1257-4598-8665-be5e0a9ffab8","resolution":{"observed_at":"2026-08-05T10:22:05.302066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.279768Z","title":"ImageNet: A Large-Scale Hierarchical Image Database,","venue":null,"work_id":"8ffc82cf-596d-46b9-ab0f-2cf95d9fe880","year":2009},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.620061Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:a261176b7b9352843837ea303a153a026e9f612090c8db3be268c4c8a27e2423","observation_id":"3c7fe559-8bb3-4261-b636-88d446e43db2","resolution":{"observed_at":"2026-08-05T10:22:05.284683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.263663Z","title":"Military Vehicles Dataset,","venue":null,"work_id":"5029de02-f56f-4b79-9bf3-a880777d05cd","year":2023},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.625275Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:bec038169cb4ac9d626eb0a1046d524f507691af09822d48db9234ee7b89efc0","observation_id":"9780af76-3f6e-44aa-a15e-71b91a7416d5","resolution":{"observed_at":"2026-08-05T10:22:05.268694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.247124Z","title":"Lucid library adapted for PyTorch,","venue":null,"work_id":"047c56d8-909d-43d2-9ee2-7de62b48e14c","year":2021},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.629691Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:d76facd6a10763857abcf01f31b5b19e63b79de4b4d3c1104c5e9fec1d734d94","observation_id":"05525132-8f0a-4d4c-b81c-73e0a3276eb7","resolution":{"observed_at":"2026-08-05T10:22:05.252021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:04.634061Z","title":"Error detection and constraint recovery in hierarchical multi-label classification without prior knowledge,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.634061Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:14674a569545832b14333226076e42d2d33baee1d349e62f8f220a8b27d22780","observation_id":"dd7ad561-4a66-4246-aa62-6049cdfbcefc","resolution":{"observed_at":"2026-08-05T10:22:04.634061Z","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":"2026-08-05T10:22:05.231982Z","title":"kNN Approach to Unbalanced Data Distributions: A Case Study involving Information Extraction,","venue":null,"work_id":"ee0c384a-5227-49f2-a253-9f428f730787","year":2003},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.638779Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:776e1767e3b7f458f992ae4f6c6e576e8361b775456631f1f1fd3aed0c503309","observation_id":"597d34da-2f91-4abb-b3c4-0e33e1436208","resolution":{"observed_at":"2026-08-05T10:22:05.236987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-05T10:22:04.644522Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.644522Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:03adf01ca7f483da5444147093f0d5a1642783e15435e68decfff9ba72a86f87","observation_id":"e6adde99-1718-4fea-b410-af030537c131","resolution":{"observed_at":"2026-08-05T10:22:04.644522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.03519","last_updated":"2026-05-14T04:50:49Z","snapshot_observed_at":"2026-07-06T21:19:44.737182Z","submitted_at":"2025-05-06T13:32:12Z","title":"Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment","version":7},"cited_work":{"arxiv_id":"2505.03519","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.03519","snapshot_observed_at":"2026-08-05T10:22:04.705311Z","title":"Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment","venue":"cs.LG","work_id":"12acf03a-c9da-4a30-9e7e-3999063efbf5","year":2025},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.649869Z"},"links":{"cited_paper":"/paper/2505.03519","citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:57aa3dafd63a1032f325035d69c5f2c174625285d0cbb1f04878fe3a1fae217a","observation_id":"c6012169-eb45-4798-ae80-ad87d796567b","resolution":{"observed_at":"2026-08-05T10:22:04.714348Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T10:22:05.216312Z","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation,","venue":null,"work_id":"62b3d7ea-b5c6-429f-bb5b-fb19ff3dfca2","year":2022},"citing_paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T10:22:04.654983Z"},"links":{"citing_paper":"/paper/2509.04214"},"observation_digest":"sha256:560256ea3349e673a8128076379673444ab5572b6997bd73dd7927b50b8cb7cf","observation_id":"51f33b01-8c00-40df-8534-4995a923c24f","resolution":{"observed_at":"2026-08-05T10:22:05.221261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.04214","last_updated":"2025-09-04T13:39:37Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-14T07:31:33.590104Z","submitted_at":"2025-09-04T13:39:37Z","title":"An Automated, Scalable Machine Learning Model Inversion Assessment Pipeline"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":3,"parse_uncertain":0,"unresolved":7,"verified_exact":2,"verified_fuzzy":10},"total_outbound_references":22},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2509.04214."}