{"as_of":"2026-08-11T01:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:47cce7a88bd43c15fa5a8923e32c66bb545ac9d4ff942934efa1f835b4d345b7","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:37:06.505689Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2508.05677/citation-record","integrity":"/paper/2508.05677/integrity","json":"/paper/2508.05677/citation-record.json","paper":"/paper/2508.05677"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T04:37:13.358298Z","title":"National health interview survey,","venue":null,"work_id":"e4c0a5e0-8d3f-4149-b49e-d4bd0ec2e935","year":2022},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.122979Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:64e72e55ec9f2d4011702e01ebb1650be584722ff95be6118064ccd64e5ab04f","observation_id":"bb7ff99d-7ef7-49db-bbb1-3787136c11a8","resolution":{"observed_at":"2026-08-06T04:37:13.410423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:13.192977Z","title":"Learning to Ask Medical Questions using Reinforcement Learning,","venue":null,"work_id":"ad6aa2e9-185d-48ab-98ae-7fafe321d761","year":2020},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.170329Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:f5aef9844e1fbfdc83b6db6594ded71595d461bc065a76070afeb8432ba42fe5","observation_id":"7a997bd5-5e2d-482b-95f4-a2f559e29369","resolution":{"observed_at":"2026-08-06T04:37:13.259398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:13.100749Z","title":null,"venue":null,"work_id":"7f0ae16b-e788-449a-a3af-feb2b6584820","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.234502Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:158f660948b926efdbdab4a824ddc5073dd66daebe26ec045faa80d17b138ca3","observation_id":"c7aaa2fa-86fc-49ae-acf7-c354fb817920","resolution":{"observed_at":"2026-08-06T04:37:13.126072Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:12.987362Z","title":"A survey on deep learning in medical image analysis,","venue":null,"work_id":"4749fec1-ac48-40fc-a093-cf1857338703","year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.290646Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:8b517715253190cd4fe3b55d748fdbb24c2021520c211750831f923ed20c67c5","observation_id":"b933d628-b370-4222-add9-4a8797397fa4","resolution":{"observed_at":"2026-08-06T04:37:13.048106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:12.813542Z","title":"An overview of clinical decision support systems: benefits, risks, and strategies for success,","venue":null,"work_id":"ee60b0ca-c946-4b8b-b84e-92e88843ca25","year":2020},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.380989Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:69d1474661be0c0d314af3ebed33f089ef3f7e36779ecbad850925a63607d6a1","observation_id":"1f7d9c16-243c-4b21-8198-f5c4b6ac0c28","resolution":{"observed_at":"2026-08-06T04:37:12.894946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:12.644457Z","title":"An adaptive testing item selection strategy via a deep reinforcement learning approach,","venue":null,"work_id":"5ba00d66-642c-4e4b-b1ce-7fdb0ebba2f0","year":2024},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.457766Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:be3a578fb1dd88b33857a50e031435335c5d677b8271a410a4a0e2ce26057384","observation_id":"c201f2cb-22d6-4c08-a910-c028034dc0c8","resolution":{"observed_at":"2026-08-06T04:37:12.747514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:02.575484Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.575484Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:e45777da74e6759471d32547eee3d327bcc7a431fcab6618b15c644446438db0","observation_id":"2b2112ea-f56f-4f58-8fc8-bc24bbfa1398","resolution":{"observed_at":"2026-08-06T04:37:02.575484Z","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":"2026-08-06T04:37:12.483238Z","title":"Bellman,A Markovian decision process","venue":null,"work_id":"1a812c84-7884-4836-8078-527b638bdf69","year":1957},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.618893Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:c8bcb31c55578ade720ae0ca38fd09b4cca4dff2245d881cca9cfce76b650cfc","observation_id":"e04e5041-dbdf-488b-9a16-501a2d54eefc","resolution":{"observed_at":"2026-08-06T04:37:12.570591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:02.687249Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.687249Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:ccf653f9c4ef84fe2bd1e23e67e6c7e156b6f4122cda8e76d47831480f745bb0","observation_id":"af15bfe9-e176-47aa-8914-0caa0ce5e6aa","resolution":{"observed_at":"2026-08-06T04:37:02.687249Z","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":"2026-08-06T04:37:12.281542Z","title":"Adversarial attacks on medical machine learning,","venue":null,"work_id":"f67ad071-1eb6-4d2b-bc4a-8296996a934c","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.779605Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:8511fbce58ef2d570a78062490eead1c510ee11d81da6d088367781d236bc20e","observation_id":"4df0ee94-47fa-4ea5-a0e0-3c15520cdeb1","resolution":{"observed_at":"2026-08-06T04:37:12.369860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.01134","last_updated":"2018-11-03T00:25:50Z","snapshot_observed_at":"2026-07-06T07:12:23.549121Z","submitted_at":"2018-11-03T00:25:50Z","title":"A Marauder's Map of Security and Privacy in Machine Learning","version":1},"cited_work":{"arxiv_id":"1811.01134","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.01134","snapshot_observed_at":"2026-08-06T04:37:07.430309Z","title":"A Marauder's Map of Security and Privacy in Machine Learning","venue":"cs.CR","work_id":"b4968320-9575-449e-87ec-27002745a3d9","year":2018},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.869236Z"},"links":{"cited_paper":"/paper/1811.01134","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:3749a14ff5a8bc02d95f34d19d9fb39ae29b31ec3f89e23a8d57c75549a223e0","observation_id":"ce23a4b0-9be1-49a2-a687-c2c985621d77","resolution":{"observed_at":"2026-08-06T04:37:07.557164Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:12.103448Z","title":"Evasion attacks against machine learning at test time,","venue":null,"work_id":"2482d86b-59b3-4741-980b-359c2596157c","year":2013},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:02.959172Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:d2b94b93d4e447a88608700359e194702afd3c9c05916a1189776f4646750456","observation_id":"672cd86a-f3be-44a9-a3bf-72da94cf414b","resolution":{"observed_at":"2026-08-06T04:37:12.193831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:11.931213Z","title":"The security of machine learning,","venue":null,"work_id":"31174e19-2cfa-416c-a157-176bfc47bd53","year":2010},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.110277Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:9ab82d09b76470ecfa9a127e73ed335dc13a4a8d9cf015fd739ec82b8f3fd328","observation_id":"388f4614-9801-4fbb-ad67-99d36fd54c5b","resolution":{"observed_at":"2026-08-06T04:37:12.052475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06565","snapshot_observed_at":"2026-08-06T04:37:03.197842Z","title":"Concrete problems in ai safety,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.197842Z"},"links":{"cited_paper":"/paper/1606.06565","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:e4763a09cae14269229d35107e8b2b2b5102668c83eddc3f62270bf13c7af058","observation_id":"c718ceb4-5e88-4c59-bb19-683134e286fd","resolution":{"observed_at":"2026-08-06T04:37:03.197842Z","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":"2026-08-06T04:37:11.787828Z","title":"Russell,Human compatible: Artificial intelligence and the problem of control","venue":null,"work_id":"e038fdbe-47a4-4ebc-887a-a0f70e97c760","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.273455Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:25941822c68eb263d7ae94ca0b104d39a0dc6d70b5dd0390d082043730ca4334","observation_id":"a7e3f640-8f40-4d67-b1c9-2cdd0cc72bd0","resolution":{"observed_at":"2026-08-06T04:37:11.862991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:11.682657Z","title":"COM(2021) 206 final","venue":null,"work_id":"987bb2bf-34fe-4cca-85ce-122cf5e38a25","year":2021},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.399946Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:66a44058fd41af243e0b259f91f2b2e77e303e73655e1a6d216f01f60702aed3","observation_id":"bbb886cc-d285-4b5d-8fa9-d3c981aab7eb","resolution":{"observed_at":"2026-08-06T04:37:11.738892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:11.522993Z","title":"LOINC: Logical observation identifiers names and codes","venue":null,"work_id":"71528e0f-ee29-4450-a5aa-3f54348b0f23","year":null},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.461470Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:5b0890ff24dcc1159556bfb896e95c2c1072746d8dc4b617497f87238cae57eb","observation_id":"40472e55-c5c7-4aaa-9b66-39d586794101","resolution":{"observed_at":"2026-08-06T04:37:11.603011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:11.079723Z","title":"SNOMED CT: Systematized nomenclature of medicine clinical terms","venue":null,"work_id":"9ca21726-acc2-4e4b-a75b-beb0792a3b17","year":2024},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.598589Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:6a42e4203fd925c7dcff6d9857ba929d0880d7abe1e7fb52b4c52dbd8180d9e4","observation_id":"71fc4aad-50a0-43c4-b330-9b296b6c1848","resolution":{"observed_at":"2026-08-06T04:37:11.165427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:10.851170Z","title":"ICD-11: International classification of diseases 11th revision","venue":null,"work_id":"24a1e5c2-a3bc-4b25-a4b0-da1d2e77b3cc","year":2024},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.701251Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:02419af65b1cfbc3a564b3dc3b2f5b26b3ce8a5daa2c09705454aa1597e7e6c6","observation_id":"629828db-d9d9-416f-8f3e-38173be1f733","resolution":{"observed_at":"2026-08-06T04:37:10.963317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:10.645321Z","title":"Standards of care in diabetes-2025,","venue":null,"work_id":"d8eeb182-1c8d-48e6-94b8-2f45230cebdc","year":2025},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.812919Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:876d9ce372f1999a2de1f87084d32e80e4c124fbba02ed35d6cf17deac0bc017","observation_id":"3606a36b-18c4-40c2-a17e-1e489df5b4ec","resolution":{"observed_at":"2026-08-06T04:37:10.739644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:10.439527Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":"3f7fb246-3643-4b05-a696-b84fc6c3676b","year":2020},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.907329Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:56ee3f4f07d900c568801bf146a36fadb5527ec78fe598415e38e10b91caa44d","observation_id":"68b37a9c-a575-49fa-a205-561e5a3f24aa","resolution":{"observed_at":"2026-08-06T04:37:10.553792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-06T04:37:03.988151Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.988151Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:260101fa119e2e7e88b90eca4730882b76f7c320b9dd5166a3deaaa139576cb5","observation_id":"62b12bee-72a8-48fb-bfc8-b0419072519a","resolution":{"observed_at":"2026-08-06T04:37:03.988151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-07-06T04:04:16.777653Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-06T04:37:04.179364Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.179364Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:7b18b782609ac03d0112110a43b1acc217e58f7caa8433f7796e3a94dcdbdefa","observation_id":"1dd1f138-fe81-497d-a8bd-a9d9c5141297","resolution":{"observed_at":"2026-08-06T04:37:04.179364Z","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":"2026-08-06T04:37:04.311017Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.311017Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:102c72d7e7380998fb084e9ea9e419c86e051bb83f43178a71512a3853fc5a49","observation_id":"7e352d38-2a1f-42fc-9f92-bc02ab9df3af","resolution":{"observed_at":"2026-08-06T04:37:04.311017Z","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":"2026-08-06T04:37:10.220039Z","title":"Practical black-box attacks against machine learning,","venue":null,"work_id":"9c520f99-7a2e-4587-a681-aabb7a51cf2c","year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.420096Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:93e3b1d279eee353f49cd830ab3c6abf16de522ee30d13388b4410387a25a763","observation_id":"0aa46a69-a147-4295-b496-bcb71fc42142","resolution":{"observed_at":"2026-08-06T04:37:10.309950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:10.046971Z","title":"Delving into transferable adversarial examples and black-box attacks,","venue":null,"work_id":"b8dff020-9ed0-4a2f-84a2-31bf8bd81761","year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.521380Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:b85eb9a1626fd34144f625d9d25d837e9455b858cfdcb4a4d961d7560cd7763c","observation_id":"1daaa96d-c3c4-4f49-8581-97fe808039ab","resolution":{"observed_at":"2026-08-06T04:37:10.138753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:09.829115Z","title":"Black-box adversarial attacks with limited queries and information,","venue":null,"work_id":"2cadf24d-a051-4dba-8639-1648b77480a1","year":2018},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.596178Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:159fdfe8c4f09d12424a661b01f715e8d80885084f4169953ca90c7a6ef8e1ce","observation_id":"6a60fa5f-13d5-4f12-8922-9d2774cb10a4","resolution":{"observed_at":"2026-08-06T04:37:09.923582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:09.643878Z","title":"Autozoom: autoencoder-based zeroth order optimization method for attacking black-box neural networks,","venue":null,"work_id":"0acc05e7-2807-4c39-93cd-5893680ad4e7","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.695778Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:fb006933100c7abf565e11f26b79b1ba921d5a32720aac0ed48eef329f662aea","observation_id":"81ecf6ad-7048-4ba1-8917-d5336587734e","resolution":{"observed_at":"2026-08-06T04:37:09.737755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:09.477756Z","title":"Zoo: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models,","venue":null,"work_id":"88cfa9cf-e7e5-45fc-93a8-93d965fc758f","year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:04.872260Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:a54e2c13fbfaa14e1d26b60af213d24cb9621c98bffe8063b61fc7fc673c79da","observation_id":"3b4c045e-743b-4b6b-94bf-5493a80a9f41","resolution":{"observed_at":"2026-08-06T04:37:09.567046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.02284","last_updated":"2017-02-08T04:33:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-02-08T04:33:55Z","title":"Adversarial Attacks on Neural Network Policies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.02284","snapshot_observed_at":"2026-08-06T04:37:05.035760Z","title":"Adversarial attacks on neural network policies,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.035760Z"},"links":{"cited_paper":"/paper/1702.02284","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:ed6aad60a00c1b114b8b68559ee6f1b5cc92309db5ee9133625fc11e3b88e728","observation_id":"303f28b5-2625-4cd4-8e8a-29baf3be5227","resolution":{"observed_at":"2026-08-06T04:37:05.035760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.06748","last_updated":"2019-11-13T01:24:00Z","snapshot_observed_at":"2026-08-08T02:27:11.507759Z","submitted_at":"2017-03-08T04:39:34Z","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.06748","snapshot_observed_at":"2026-08-06T04:37:05.207213Z","title":"Tactics of adversarial attack on deep reinforcement learning agents,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.207213Z"},"links":{"cited_paper":"/paper/1703.06748","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:83a258268dc568d799a0ae4fcc5fc9054d5c3a9fb2e097dddfff46a9fdab1ce2","observation_id":"babecf3e-e3f9-4818-8682-b7b87f483782","resolution":{"observed_at":"2026-08-06T04:37:05.207213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10615","last_updated":"2021-01-17T19:25:56Z","snapshot_observed_at":"2026-08-04T07:21:33.793111Z","submitted_at":"2019-05-25T15:23:19Z","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10615","snapshot_observed_at":"2026-08-06T04:37:05.320640Z","title":"Adversarial policies: Attacking deep reinforcement learning,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.320640Z"},"links":{"cited_paper":"/paper/1905.10615","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:958fcbc64103e1875a012063c9860c08e479c31c4f658b3550a2f67adde23ec1","observation_id":"0a3643ad-4f4c-4b8e-8535-4ef9a2443076","resolution":{"observed_at":"2026-08-06T04:37:05.320640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02918","last_updated":"2019-11-21T19:07:45Z","snapshot_observed_at":"2026-07-06T08:19:42.994042Z","submitted_at":"2019-09-06T14:06:21Z","title":"Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information","version":2},"cited_work":{"arxiv_id":"1909.02918","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.02918","snapshot_observed_at":"2026-08-06T04:37:07.153758Z","title":"Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Information","venue":"cs.LG","work_id":"5a284ce5-f156-4b66-8d43-16f6cefac67b","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.483236Z"},"links":{"cited_paper":"/paper/1909.02918","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:e14ce684bd9b0ddfd1af8cf5d64b82057d6c01d9d93f18d58b658f42372fff71","observation_id":"76db0e6c-d426-451c-8f4f-7ef7ea3e0e69","resolution":{"observed_at":"2026-08-06T04:37:07.244651Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:09.280165Z","title":"Robust reinforcement learning via adversarial training with langevin dynamics,","venue":null,"work_id":"2665d1d9-af85-47fd-9313-a9155232a838","year":2020},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.612844Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:ff9ef01a59910b7926baff4ca6d705a2a4afbc9ab92dc3d8707384d7f7044eaa","observation_id":"a869f06c-b7ad-4480-94a1-937fddda9a3e","resolution":{"observed_at":"2026-08-06T04:37:09.379211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:09.123320Z","title":"Bayesian learning via stochastic gradient langevin dynamics,","venue":null,"work_id":"b34e190f-23eb-43d5-a571-643fbd67f886","year":2011},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.699013Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:d20dcc0658b4efad2280432a07d05a85070925c2fff7866606059a5922c40f67","observation_id":"29a05f6b-fdb4-4ec6-bbd8-6d254d009a57","resolution":{"observed_at":"2026-08-06T04:37:09.223045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.934212Z","title":"Understanding deep learning requires rethinking generalization,","venue":null,"work_id":"5273a202-6f3b-4342-91fd-4f8e4c50371b","year":2021},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.741499Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:faf1d9ef7c7eb221ecd71dba1118b567cc33e44fa41cafa65e8a33b2b50fad03","observation_id":"2622b74e-3a78-470c-a311-93a3094c09eb","resolution":{"observed_at":"2026-08-06T04:37:09.015107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.776679Z","title":"Understanding adversarial attacks on deep learning based medical image analysis systems,","venue":null,"work_id":"6aaaa78e-f201-47d4-ae75-4c158974a728","year":2020},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.895467Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:6d19f54f0534608b3beaae0c03fcf9e65566b1a90d3d5d756835e9753fc5b621","observation_id":"49de23b7-457b-41a1-96b9-4ea03ad353fa","resolution":{"observed_at":"2026-08-06T04:37:08.847605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.587888Z","title":"Impact of adversarial examples on deep learning models for biomedical image segmentation,","venue":null,"work_id":"bcf51413-6c59-4330-92ed-6a3ffaf1d985","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:05.966079Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:b5234843e4fc119773dcd6fe5252a7ea85f353eecd6834fac939a8bf80235d67","observation_id":"7d2ada32-f789-49b6-9523-4ec96b67767e","resolution":{"observed_at":"2026-08-06T04:37:08.685054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.449157Z","title":"A hierarchical feature constraint to camouflage medical adversarial attacks,","venue":null,"work_id":"cace9387-3140-44dc-836c-0755cb62ef92","year":2021},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.043223Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:84204b06bd24f7d7f9194d6486f830ecdd5a455c327c0104f1f2a0dbbae5e540","observation_id":"c2801781-06ae-48df-9201-91d70c71f993","resolution":{"observed_at":"2026-08-06T04:37:08.514920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.09531","last_updated":"2021-03-17T09:32:13Z","snapshot_observed_at":"2026-08-09T14:30:49.613106Z","submitted_at":"2021-03-17T09:32:13Z","title":"The power spectrum and structure function of the Gamma Ray emission from the Large Magellanic Cloud","version":1},"cited_work":{"arxiv_id":"2103.09531","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.09531","snapshot_observed_at":"2026-08-06T04:37:06.903553Z","title":"The power spectrum and structure function of the Gamma Ray emission from the Large Magellanic Cloud","venue":"astro-ph.GA","work_id":"e6e6cbe3-46a8-476f-8df4-49c16f2bcee1","year":2021},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.111052Z"},"links":{"cited_paper":"/paper/2103.09531","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:f3272559fc2a4f6e0ec0adcf093603b8b5d53ceca514acc576f3f03f6762420f","observation_id":"f926b9bc-a427-46c1-a779-8dfba63d018b","resolution":{"observed_at":"2026-08-06T04:37:07.045639Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.289719Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":"7e198661-4f2d-4e76-9d46-2e2a5a88176f","year":2017},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.194606Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:06a7ee833f55d49b4fb40ce944eaca5bce2cc5d798ea740cf949f6269aba8167","observation_id":"3cfb78d9-6b52-4c3c-a640-75bb8b7d012b","resolution":{"observed_at":"2026-08-06T04:37:08.354115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:08.180998Z","title":"Human-level control through deep reinforcement learning,","venue":null,"work_id":"e2b821ce-cd5b-474a-b49d-0b330d416088","year":2015},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.260934Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:fb364f726c369fb642110ba35df0373e2eecb88aa05bcafe1def5da2acb750c1","observation_id":"2d77a4f8-d24a-4b74-be14-3d28177f4377","resolution":{"observed_at":"2026-08-06T04:37:08.236275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:07.970107Z","title":"Self-improving reactive agents based on reinforcement learning, planning and teaching,","venue":null,"work_id":"98177ce4-d65f-42fb-9c52-c54e7d41d365","year":1992},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.290561Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:c88b7f77858f0234484a73b96633c5850b8300fc8a7a99b9602245d5e6761a3c","observation_id":"6a23aa29-8572-416a-ac1d-6128517be420","resolution":{"observed_at":"2026-08-06T04:37:08.057841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:07.700867Z","title":"Understanding the difficulty of training deep feedforward neural networks,","venue":null,"work_id":"0383ae4f-a48e-439f-abe3-91a56cba42db","year":2010},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.398517Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:cb428965430c247f783cf2080b847644d496f5099cae4cf1247d6c77c2f588b9","observation_id":"ad573df7-6696-4a19-b923-4d9150081eb4","resolution":{"observed_at":"2026-08-06T04:37:07.826680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.03493","last_updated":"2019-05-09T09:01:08Z","snapshot_observed_at":"2026-08-07T06:14:16.201139Z","submitted_at":"2019-05-09T09:01:08Z","title":"Limits of Deepfake Detection: A Robust Estimation Viewpoint","version":1},"cited_work":{"arxiv_id":"1905.03493","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.03493","snapshot_observed_at":"2026-08-06T04:37:06.629305Z","title":"Limits of Deepfake Detection: A Robust Estimation Viewpoint","venue":"cs.LG","work_id":"a1fcf56d-4d55-4d06-b0f3-14a677f11a6f","year":2019},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:06.505689Z"},"links":{"cited_paper":"/paper/1905.03493","citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:b37818a2d1f2fac527ce87962b40303fe7234c140b0f534cadd237a0f4318cac","observation_id":"7561827b-15e0-4478-ae5b-371c0bc03a63","resolution":{"observed_at":"2026-08-06T04:37:06.741360Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T04:37:11.299668Z","title":null,"venue":null,"work_id":"666a04dc-1dff-469c-abeb-32046202a61e","year":null},"citing_paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T04:37:03.541199Z"},"links":{"citing_paper":"/paper/2508.05677"},"observation_digest":"sha256:88fae5efce641206ca05a85955e8fbb89efaa70065954bcf71dfe212549c14cb","observation_id":"2ee305a0-09b1-42d2-ab48-41d9b810d86f","resolution":{"observed_at":"2026-08-06T04:37:11.387092Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.05677","last_updated":"2025-08-05T11:10:49Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T07:39:03.079584Z","submitted_at":"2025-08-05T11:10:49Z","title":"Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":11,"verified_exact":2,"verified_fuzzy":31},"total_outbound_references":46},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2508.05677."}