{"as_of":"2026-08-19T01:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1534a20071893d038718fbeca77d5515d3d06fc535fd9a951e68aa3ff6a5bece","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T12:34:22.755810Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2507.21705/citation-record","integrity":"/paper/2507.21705/integrity","json":"/paper/2507.21705/citation-record.json","paper":"/paper/2507.21705"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:34:23.367515Z","title":null,"venue":null,"work_id":"1f08b2b4-f6f6-4a53-95b4-b9138668f189","year":2012},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.593765Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:4d2dc05440aa2c21d63346960f51488ea2e102cf5c19ba870087d804d0b43956","observation_id":"10a6d9d1-943a-4453-8110-dee2ae674acf","resolution":{"observed_at":"2026-08-06T12:34:23.372092Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.353781Z","title":null,"venue":null,"work_id":"138d961f-36c4-474b-a10b-18a9d06480e8","year":2014},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.598971Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:a611d0e5a1f6d45b70b3c0f70b69cce6af4152a53daa4b78bd780dc9f13c9417","observation_id":"fb1dcf0a-9fda-4910-bfbb-450f791c8080","resolution":{"observed_at":"2026-08-06T12:34:23.358283Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.340492Z","title":"Bertsekas, Dynamic Programming and Optimal Control: Volume I , vol","venue":null,"work_id":"53d72bed-0d07-4fbb-8819-55b5d20f0485","year":2012},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.603598Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:b3067d55399da975076c30646a334da728ff34b3f6ab6ce03e33c008085327f8","observation_id":"9e576fa2-e173-45f8-bb9d-ca1944ee8a96","resolution":{"observed_at":"2026-08-06T12:34:23.344735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.327358Z","title":"Learning fast approximations of sparse coding,","venue":null,"work_id":"8bba1182-dd99-4d73-b352-4abda8703155","year":2010},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.607939Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:b763a9912dfc9af88ebf77ae1894364362aae37e7b54b7e5aeaacba6e5f14b1a","observation_id":"2fbdab44-6ce0-48ab-b5db-eae0f32e1453","resolution":{"observed_at":"2026-08-06T12:34:23.331419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.314081Z","title":"Graph unrolling networks: Interpretable neural networks for graph signal denoising,","venue":null,"work_id":"d2070577-9055-4ec6-8980-7d0192ab252d","year":2021},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.612131Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:bb4698aad865e738c2e8b7e3dfea27b4bdc035f07230fccee70228bed8eb542a","observation_id":"82908a22-533b-4590-8a74-5f105fdd7f77","resolution":{"observed_at":"2026-08-06T12:34:23.318212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.616240Z","title":"Graph signal processing: Overview, challenges, and ap- plications,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.616240Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:4c70a071fb6412181351842bc83e092f616f07b960f39af4f15c5121f57ad52c","observation_id":"b57a5406-0406-4273-bebe-1ab08eb210f8","resolution":{"observed_at":"2026-08-06T12:34:22.616240Z","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":"2026-08-06T12:34:23.291799Z","title":"Graph signal processing: History, development, impact, and outlook,","venue":null,"work_id":"9e5ff145-3e97-49e5-be6c-778abeaa800c","year":2023},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.621671Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:d2b9f0c24ca20551ad8256ff530b6b5988114e4266d142d3b0ee0da8a77c4ce1","observation_id":"0ae4a0f6-a269-43f8-a3da-bc2c789344cf","resolution":{"observed_at":"2026-08-06T12:34:23.297094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.278278Z","title":"Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing,","venue":null,"work_id":"54c14c5e-1d2b-426c-bae7-2be1c7b9031d","year":2021},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.626272Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:9d390ddcbb8552bf40705544051ae6b07396761914adb9a4c26a14ec6541891f","observation_id":"5f1ed770-f679-48ec-ae7f-b46ded330288","resolution":{"observed_at":"2026-08-06T12:34:23.282679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.264776Z","title":"Robust stochastically- descending unrolled networks,","venue":null,"work_id":"ed786239-a710-4721-8708-c6f17efb2885","year":2024},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.630120Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:aa0b9480ebf80c916b758adc1e0c2e62ff0e669b6b7abe87dbd8f7400704a585","observation_id":"f1f980ce-a503-4fe5-90de-3b0e9885ca09","resolution":{"observed_at":"2026-08-06T12:34:23.269278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.634507Z","title":"Graph filters for signal processing and machine learning on graphs,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.634507Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:6783891dcee265ea7fd59940b4619493d0af542e45d6fd5992d107f53fba0ec6","observation_id":"3e138b65-0e45-4e20-9f1e-023ebb594a77","resolution":{"observed_at":"2026-08-06T12:34:22.634507Z","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":"2026-08-06T12:34:23.242040Z","title":"Value iteration networks,","venue":null,"work_id":"f6317325-d831-4b05-8d8b-aa0285e22edc","year":2016},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.639252Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:13af153b1565751931a24d50cf779e63e7873cb4debcec152928b415d9fe0f94","observation_id":"08998098-27b6-4699-b0fe-c3b8f9374d40","resolution":{"observed_at":"2026-08-06T12:34:23.246107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.228811Z","title":"Generalized value iteration networks: Life beyond lattices,","venue":null,"work_id":"f3eed6b1-3197-4103-acf2-3023efda9802","year":2018},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.643197Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:decd0f9d11cf05111bd58e67be77580f89f93a7464c2285c81c78c770d1bbd58","observation_id":"db905d29-aa5c-42b7-ae60-5b9c5404c2c3","resolution":{"observed_at":"2026-08-06T12:34:23.233165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.12604","last_updated":"2020-09-26T14:09:16Z","snapshot_observed_at":"2026-08-05T18:53:11.077086Z","submitted_at":"2020-09-26T14:09:16Z","title":"Graph neural induction of value iteration","version":1},"cited_work":{"arxiv_id":"2009.12604","doi":null,"metadata_source":"pith","pith_arxiv_id":"2009.12604","snapshot_observed_at":"2026-08-06T12:34:22.924149Z","title":"Graph neural induction of value iteration","venue":"cs.LG","work_id":"47cd7fa3-3d08-49d4-b253-071cc6983899","year":2020},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.647167Z"},"links":{"cited_paper":"/paper/2009.12604","citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:ad39a5de31ccf719509680c6b931753da43fb3d3cad4a22c24069607a0c98fd0","observation_id":"7d560094-21cb-4d00-aeb7-af89b6fed9e0","resolution":{"observed_at":"2026-08-06T12:34:22.928958Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.215371Z","title":"On solving MDPs with large state space: Exploitation of policy structures and spectral properties,","venue":null,"work_id":"8011e587-97af-440e-a7ba-83c8d95fa17b","year":2019},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.651616Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:a181f6f50727a7b0d646511f4fc9be20f1f782f47d849e1cbd80d334209f49fd","observation_id":"8eda06f4-cd96-4d00-9bba-a4bdc8013939","resolution":{"observed_at":"2026-08-06T12:34:23.219724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.202202Z","title":"Policy sampling and interpolation for wireless networks: A graph signal processing approach,","venue":null,"work_id":"dbeb21a1-23ec-4f89-8839-5c77c13ffda5","year":2019},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.655416Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:a019c1fc22bd3f1cdc2e05f10c675e9e116206d2caeb95ab0713705a9c63b03d","observation_id":"3791a7aa-68a4-40af-9c11-10d281967bd2","resolution":{"observed_at":"2026-08-06T12:34:23.206498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.187887Z","title":"Reduced dimension policy iteration for wireless network control via multiscale analysis,","venue":null,"work_id":"70a7e3d8-0db0-4561-af85-70983a8e54b2","year":2012},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.659382Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:e9c3a9a291eaa76ec1f1a301dbe2299e07fa4b7ad38cfd912d17fce6478df941","observation_id":"8278c33b-29cf-42ae-a376-bafbc03f6691","resolution":{"observed_at":"2026-08-06T12:34:23.192769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.663413Z","title":"Stability properties of graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.663413Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:19c3a132d48752a18dbea3b5453b950d04a25513b9ae219c8936781a6fe497da","observation_id":"a4c86262-56f5-4eff-8046-c9bc51edbc2f","resolution":{"observed_at":"2026-08-06T12:34:22.663413Z","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":"2026-08-06T12:34:22.667515Z","title":"Graph neural networks: Architec- tures, stability, and transferability,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.667515Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:c6fb4fbe25c72a6356f41ca17e9e8f915f2ee18778745e1a851d17a100e98e2f","observation_id":"c5d6315c-082a-4166-92ad-1dc71cdcff77","resolution":{"observed_at":"2026-08-06T12:34:22.667515Z","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":"2026-08-06T12:34:22.671618Z","title":"Trans- ferability of spectral graph convolutional neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.671618Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:38d17cd7db3cc86ada82e1d8cd355056f4e7ef280bbcdbc5686bc2de3f474b12","observation_id":"10cf6142-f21c-4fde-b019-a45a48913596","resolution":{"observed_at":"2026-08-06T12:34:22.671618Z","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":"2026-08-06T12:34:23.146236Z","title":"Learning by transference: Training graph neural networks on growing graphs,","venue":null,"work_id":"785a4ca2-f07a-4d9e-9b5d-cdd8b0b1d4c1","year":2023},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.675405Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:a192e7f6fbeb40e9bbbf6f572b67b0de827c150bc35e88b1d9ce5f311dbb9010","observation_id":"8a15d84e-183e-41f6-a07f-eae1b33e5211","resolution":{"observed_at":"2026-08-06T12:34:23.151296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.132713Z","title":"Re- designing graph filter-based GNNs to relax the homophily assumption,","venue":null,"work_id":"837ac5df-e6d0-4073-a62b-d9c336034b31","year":2025},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.679646Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:7bf261e57d54a6b165d4af37b284ea3c9f20fd071e82f1702d29cef19e8fe1ac","observation_id":"890057bd-be24-4da9-b83a-6a6df5b56eda","resolution":{"observed_at":"2026-08-06T12:34:23.137247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.118963Z","title":"A manifold perspective on the statistical generalization of graph neural networks,","venue":null,"work_id":"53f1151f-17db-4d94-abf1-0ba931657e7b","year":2025},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.683804Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:044922ca1636b02341dfe3b585c882903190f522234838b65016e7fa71457456","observation_id":"a0e824fc-d847-46f8-b72c-ae8d289195ef","resolution":{"observed_at":"2026-08-06T12:34:23.123441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.687774Z","title":"Dynamic programming,","venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.687774Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:ba77050216ae32c79908f74905be0a22e92bc852e782d99a4cfe82f3236c56ff","observation_id":"db6debb3-664b-489d-ac53-2b269f0210b9","resolution":{"observed_at":"2026-08-06T12:34:22.687774Z","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":"2026-08-06T12:34:23.096080Z","title":"Robust graph filter identification and graph denoising from signal observations,","venue":null,"work_id":"5ffdb444-ce90-4181-ae8b-859d238f6715","year":2023},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.691750Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:57d457f65f08566cb66f95be694a1fed72b612095704b1b21f41d189b73e9850","observation_id":"e3d03c19-0312-4447-a419-1da8f0fae226","resolution":{"observed_at":"2026-08-06T12:34:23.101429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.081844Z","title":"Optimal graph-filter design and applications to distributed linear network operators,","venue":null,"work_id":"988a741b-9ec1-44d4-b9f2-28c1a52e442b","year":2017},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.695833Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:00471fab3769c8c64920258a5bc54764ddbac259946bbf66880a77dd2146a00a","observation_id":"8c827364-ecec-4473-8c1f-6baa7de9870b","resolution":{"observed_at":"2026-08-06T12:34:23.086800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.067750Z","title":"Least-squares policy iteration,","venue":null,"work_id":"eae3d32d-dfdc-4474-9078-fe27398ea510","year":2003},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.699571Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:4fae7846e034994d3cd9cde3c5435a87baa0b8006685b6bd18b24b9f1bb2a0c6","observation_id":"66963567-4a9f-4874-a7ea-0dfd613e8eaa","resolution":{"observed_at":"2026-08-06T12:34:23.072185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.054186Z","title":"A tutorial on linear function approximators for dynamic programming and reinforcement learning,","venue":null,"work_id":"82b7ec30-5c59-4500-97dd-e5c37d3e88cf","year":2013},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.703212Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:9b676a4a1afdd13745ae5865d96c831350babc1a92d6a16550562ff5d69060e5","observation_id":"de3b0fa4-2112-4dd6-bbd7-b9d4744a5873","resolution":{"observed_at":"2026-08-06T12:34:23.058596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.040785Z","title":"FLAMBE: Structural complexity and representation learning of low rank MDPs,","venue":null,"work_id":"5a17ca17-af06-414f-95d2-40c4e67ce879","year":2020},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.707170Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:61ea536ea448b2bf61b56e8ebe7452b2d4d1cc30fbd373d7998b03a358bd107b","observation_id":"44686289-3b59-44af-bfac-5512128ae7ca","resolution":{"observed_at":"2026-08-06T12:34:23.045153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.027240Z","title":"Tensor and matrix low- rank value-function approximation in reinforcement learning,","venue":null,"work_id":"65630605-3899-4b53-89fe-40d67793c191","year":2024},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.711362Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:d3b42a7766fab24610b7f05f3ec4c1945766b91d12b0b0ccf4c4eb3a527ec872","observation_id":"2de5668f-bf81-4826-82cd-b3b869fe46ac","resolution":{"observed_at":"2026-08-06T12:34:23.032022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.10598","last_updated":"2026-05-13T13:08:50Z","snapshot_observed_at":"2026-07-06T20:22:45.422714Z","submitted_at":"2025-01-17T23:10:50Z","title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","version":3},"cited_work":{"arxiv_id":"2501.10598","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.10598","snapshot_observed_at":"2026-08-06T12:34:22.905969Z","title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","venue":"cs.LG","work_id":"d9f56534-6713-47ea-a4af-1236aa91671e","year":2025},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.715172Z"},"links":{"cited_paper":"/paper/2501.10598","citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:084808add2f0fcb10c580a5aa7bac734f85f877d446b3d7caf7438a5972bd02c","observation_id":"19700877-a78c-4093-bafd-44b6dca8198a","resolution":{"observed_at":"2026-08-06T12:34:22.910770Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:23.013500Z","title":"Kernel-based reinforcement learning,","venue":null,"work_id":"14fd5ab4-57a7-4191-9e53-fb220a474e89","year":2002},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.719448Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:ccb8ac9710cf268ebb3adee94fb1a52159267b1f29961f1a6bb38dc223798c45","observation_id":"fce02d6f-2d25-4b0c-891b-ce8855720469","resolution":{"observed_at":"2026-08-06T12:34:23.018509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.16192","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:34:22.882689Z","title":"Nonparametric Bellman mappings for value iteration in distributed reinforcement learning,","venue":null,"work_id":"e1a45917-3b0d-40c6-80ab-ca480d394d9c","year":2025},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.723275Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:5a8eae81c6ffa03ef87000a29c293f1124793980b923db77b09b87a868a3fda4","observation_id":"a5b0fab7-793c-4fe2-a540-c6a09f1fbcd7","resolution":{"observed_at":"2026-08-06T12:34:22.891330Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.727953Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.727953Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:29b607806982e91351a409300c10b8a73eb07ce8d32e9b0a16b30cfbdb12d6d8","observation_id":"1fd04253-d7b9-4bc1-a147-d9040a126298","resolution":{"observed_at":"2026-08-06T12:34:22.727953Z","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":"2026-08-06T12:34:22.991794Z","title":null,"venue":null,"work_id":"54519396-7f52-4e39-9fe4-7147f990eb0d","year":2018},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.731822Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:7a1179457f494aeecae88aad1dd904dc9ee0bf559b054320fabdecd8ee079f8b","observation_id":"e4be266b-666e-4fac-be1b-7baf8f6f707c","resolution":{"observed_at":"2026-08-06T12:34:22.996422Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.978400Z","title":"Algorithmic survey of parametric value function approximation,","venue":null,"work_id":"f4578b64-7d13-4bf9-b3c1-68f8b17c6be9","year":2013},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.735554Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:db1d4d4583726dad31a838e86e2da165116a97eb5856bd87d32cb380c2c79bfb","observation_id":"17c5f3d3-6866-4d4f-9cc3-0e1e9429c0bd","resolution":{"observed_at":"2026-08-06T12:34:22.982550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.963959Z","title":"A generalized Kalman filter for fixed point approximation and efficient temporal-difference learning,","venue":null,"work_id":"3b9932a9-297e-40ce-b666-f0087a7fe14f","year":2006},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.739542Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:7f1a57beff983dc08bb3a3a81b25fdd1e25f2af55e702462cb91dbb06dccc874","observation_id":"9cfa119b-3bb5-4eff-8e09-1cd3447f3e02","resolution":{"observed_at":"2026-08-06T12:34:22.968912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.950492Z","title":"TD convergence: An optimization perspective,","venue":null,"work_id":"16ae07de-b37e-475d-b602-b72c53f4c5e8","year":2023},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.743535Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:ffd96911d46b59d7b2bae7f0e9a6598f4b452320195b819f0d8606b123e3aa01","observation_id":"e6f3b6aa-1321-4c1d-8645-b3fa72fd7629","resolution":{"observed_at":"2026-08-06T12:34:22.954553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-06T12:34:22.937786Z","title":"Simplifying neural networks by soft weight-sharing,","venue":null,"work_id":"73c20a69-bdee-426a-9f8a-b34df2170447","year":1992},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.747347Z"},"links":{"citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:ce0cd93f6dab0afb73523df46697385d84331a9bbb6b106a0fb0de500906f05c","observation_id":"b5c1ba17-5320-4af0-bb90-04201519dd19","resolution":{"observed_at":"2026-08-06T12:34:22.941938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-08-13T12:26:05.192883Z","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01540","snapshot_observed_at":"2026-08-06T12:34:22.751607Z","title":"OpenAI Gym,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.751607Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:0eb8752a8083b0164633a6e175daab1fd2ef4791d33d52f9294ff68c9f5fee53","observation_id":"61b66cc5-1c62-4e8c-9101-cd7494f065db","resolution":{"observed_at":"2026-08-06T12:34:22.751607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17032","last_updated":"2025-11-02T13:42:19Z","snapshot_observed_at":"2026-08-13T22:24:37.672685Z","submitted_at":"2024-07-24T06:35:05Z","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17032","snapshot_observed_at":"2026-08-06T12:34:22.755810Z","title":"Gymnasium: A standard interface for reinforcement learning environments,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T12:34:22.755810Z"},"links":{"cited_paper":"/paper/2407.17032","citing_paper":"/paper/2507.21705"},"observation_digest":"sha256:b92a1db83e5b0ae9985ac75e40c06683f5fb904f1f98d38cba6ae6731e5051a9","observation_id":"299dbc52-df13-4fcb-94f7-c69bb6fc8b4c","resolution":{"observed_at":"2026-08-06T12:34:22.755810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.21705","last_updated":"2025-07-29T11:34:20Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T12:34:22.279980Z","submitted_at":"2025-07-29T11:34:20Z","title":"Unrolling Dynamic Programming via Graph Filters"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":3,"verified_fuzzy":25},"total_outbound_references":40},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2507.21705."}