{"as_of":"2026-08-08T09:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b39c7e4450fe3532b4ae6e7d6804c3cb99adb0fb74cdc0db870f6485621ecd17","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T01:06:22.022074Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:14:59.466122Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T18:15:01.374851Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"cited_work":{"arxiv_id":"2506.12203","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.12203","snapshot_observed_at":"2026-08-06T18:15:01.374851Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","venue":"cs.LG","work_id":"abd77a35-fdeb-4e4f-adc6-dc00f364010c","year":2025},"citing_paper":{"arxiv_id":"2507.09151","last_updated":"2025-07-12T05:54:54Z","snapshot_observed_at":"2026-08-08T03:41:42.073125Z","submitted_at":"2025-07-12T05:54:54Z","title":"Convergence Rate of the Solution of Multi-marginal Schrodinger Bridge Problem with Marginal Constraints from SDEs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:14:59.466122Z"},"links":{"cited_paper":"/paper/2506.12203","citing_paper":"/paper/2507.09151"},"observation_digest":"sha256:3f383187f84525e6e05aef9bcf6b92d563a69b6eeb9a5e99a7ae9814c317f21e","observation_id":"fc621c3a-ad11-4b8b-886b-20038d2d57d7","resolution":{"observed_at":"2026-08-06T18:15:01.422693Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.12203/citation-record","integrity":"/paper/2506.12203/integrity","json":"/paper/2506.12203/citation-record.json","paper":"/paper/2506.12203"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.17823","last_updated":"2024-07-29T14:12:50Z","snapshot_observed_at":"2026-07-06T17:23:05.927644Z","submitted_at":"2024-01-31T13:28:07Z","title":"Privacy-preserving data release leveraging optimal transport and particle gradient descent","version":3},"cited_work":{"arxiv_id":"2401.17823","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.17823","snapshot_observed_at":"2026-08-07T01:06:22.160127Z","title":"Privacy-preserving data release leveraging optimal transport and particle gradient descent","venue":"cs.LG","work_id":"61ac5529-a2bb-430d-a555-f845b8c0245a","year":2024},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.985802Z"},"links":{"cited_paper":"/paper/2401.17823","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:a426bbea21adbf97dc9fb4050c97e9d0c0aadbdfa24e8c7f260fd0150b0d83df","observation_id":"ef6933e6-4928-43c4-a3e6-b6c4685ed76f","resolution":{"observed_at":"2026-08-07T01:06:22.163760Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19941","last_updated":"2024-10-25T19:32:58Z","snapshot_observed_at":"2026-08-07T02:08:23.501873Z","submitted_at":"2024-10-25T19:32:58Z","title":"Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training","version":1},"cited_work":{"arxiv_id":"2410.19941","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.19941","snapshot_observed_at":"2026-08-07T01:06:22.120669Z","title":"Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training","venue":"cs.LG","work_id":"f8df001b-c6dd-471a-9ce7-041d2a609e46","year":2024},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.996376Z"},"links":{"cited_paper":"/paper/2410.19941","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:deceddae6a8c077f91721572d78b4201a249f23927b8b4ca7d1ad8ac3e2285f7","observation_id":"6de9c176-b2b7-4658-9b1a-799b5ce04817","resolution":{"observed_at":"2026-08-07T01:06:22.126346Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T01:06:22.182803Z","title":"From the Schr ¨odinger problem to the MongeKantorovich problem","venue":null,"work_id":"05a85332-5e7e-40b6-9591-d1cf19bce710","year":1920},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.004401Z"},"links":{"citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:2a3c815b0a8c90bf52d5a1948f80a48fa23fc0bd463e1d393a892969be47374d","observation_id":"93eae83b-fbe9-4ecd-9c1d-43e4ad18d7da","resolution":{"observed_at":"2026-08-07T01:06:22.186512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03672","last_updated":"2024-03-11T14:42:58Z","snapshot_observed_at":"2026-07-06T15:51:31.792957Z","submitted_at":"2023-07-07T15:42:35Z","title":"Simulation-free Schr\\\"odinger bridges via score and flow matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03672","snapshot_observed_at":"2026-08-07T01:06:22.014837Z","title":"Simulation-free schr\\” odinger bridges via score and flow matching.arXiv preprint arXiv:2307.03672,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.014837Z"},"links":{"cited_paper":"/paper/2307.03672","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:430b0cd29b79141161a096a16f23106f59fc4605c0083381a68236d9bcaf5254","observation_id":"6cb0fb18-0b66-492b-bca9-9cb984ad797f","resolution":{"observed_at":"2026-08-07T01:06:22.014837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06739","last_updated":"2018-02-19T18:05:33Z","snapshot_observed_at":"2026-07-06T06:24:12.439943Z","submitted_at":"2018-02-19T18:05:33Z","title":"Differentially Private Generative Adversarial Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06739","snapshot_observed_at":"2026-08-07T01:06:22.018174Z","title":"Differentially private generative adversarial network.arXiv preprint arXiv:1802.06739,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.018174Z"},"links":{"cited_paper":"/paper/1802.06739","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:63345b2cc071283638753ea6e4e89741027c8f5dfd4257f8306f5ef1a5029c9d","observation_id":"a4227976-cc00-45e7-9ae5-78bc51d28a66","resolution":{"observed_at":"2026-08-07T01:06:22.018174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.17738","last_updated":"2025-02-25T00:17:42Z","snapshot_observed_at":"2026-08-07T17:51:38.762569Z","submitted_at":"2025-02-25T00:17:42Z","title":"Learning Density Evolution from Snapshot Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.17738","snapshot_observed_at":"2026-08-07T01:06:22.022074Z","title":"Learning density evolu- tion from snapshot data.arXiv preprint arXiv:2502.17738,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.022074Z"},"links":{"cited_paper":"/paper/2502.17738","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:379d6863f161c93607f4fafde59d0c2b73a897282339a7009c5e7251d9975ae2","observation_id":"f9637748-2e27-4f19-b23b-8dc4377668b4","resolution":{"observed_at":"2026-08-07T01:06:22.022074Z","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":"2026-08-07T01:06:22.193533Z","title":"Deep learning with gaussian differential privacy.Harvard data science review, 2020(23):10–1162,","venue":null,"work_id":"dbd55727-41e7-42c3-b260-9f29ad766fd0","year":2020},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.978592Z"},"links":{"citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:284d914c856361a757a0199de2e87dd17087868f1be1bb0657dd229fcf212b49","observation_id":"8561303b-8abf-4848-a5eb-e313eeb34f71","resolution":{"observed_at":"2026-08-07T01:06:22.196715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T01:06:22.203884Z","title":"Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang","venue":null,"work_id":"bf77b067-3302-4450-96c5-bb5fdff95fa3","year":2016},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.975006Z"},"links":{"citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:15a475551eb5d5161040a01dd5648e6282f94f766376b9f53d0422889c314d3b","observation_id":"d27bfcb1-6bbe-444e-bc30-2fa48a7cebbb","resolution":{"observed_at":"2026-08-07T01:06:22.207522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05839","last_updated":"2020-11-16T18:08:01Z","snapshot_observed_at":"2026-08-07T23:09:10.111717Z","submitted_at":"2020-02-14T01:41:30Z","title":"LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05839","snapshot_observed_at":"2026-08-07T01:06:22.008050Z","title":"Linkedin’s audience engagements API: A privacy preserving data analytics system at scale.arXiv preprint arXiv:2002.05839,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.008050Z"},"links":{"cited_paper":"/paper/2002.05839","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:29a80530fb4a40b89da74b7ea0b2a03d743703bf8c03a0cd5fd447f93ffad6a7","observation_id":"d53352eb-9e65-4040-9290-c3b487617d0d","resolution":{"observed_at":"2026-08-07T01:06:22.008050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.06277","last_updated":"2025-04-03T20:49:52Z","snapshot_observed_at":"2026-07-06T18:59:43.564435Z","submitted_at":"2024-08-12T16:39:18Z","title":"Multi-marginal Schr\\\"odinger Bridges with Iterative Reference Refinement","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.06277","snapshot_observed_at":"2026-08-07T01:06:22.011497Z","title":"Multi-marginal schr\\” odinger bridges with iterative reference refinement.arXiv preprint arXiv:2408.06277,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.011497Z"},"links":{"cited_paper":"/paper/2408.06277","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:0997cf7a3e97829d8d21ff2418e83cbf8b4e6c1fd1d893f3b55aff4f66bbe45d","observation_id":"3ab93f0c-565e-4c26-a5be-9aa4fcd44fbc","resolution":{"observed_at":"2026-08-07T01:06:22.011497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.10440","last_updated":"2024-09-16T16:19:55Z","snapshot_observed_at":"2026-07-06T19:16:10.416481Z","submitted_at":"2024-09-16T16:19:55Z","title":"Uniform-in-$N$ log-Sobolev inequality for the mean-field Langevin dynamics with convex energy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.10440","snapshot_observed_at":"2026-08-07T01:06:21.982207Z","title":"Uniform-in-nlog-sobolev in- equality for the mean-field langevin dynamics with convex energy.arXiv preprint arXiv:2409.10440,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.982207Z"},"links":{"cited_paper":"/paper/2409.10440","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:8ee17a24db2221d53c824c0b699c713bd97bb10b0c54d1e61c5d832ddcfd4238","observation_id":"19fcb994-ce9b-4025-aaba-413f4b133fdb","resolution":{"observed_at":"2026-08-07T01:06:21.982207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.06180","last_updated":"2023-10-13T13:57:54Z","snapshot_observed_at":"2026-08-05T04:17:42.540484Z","submitted_at":"2023-02-13T08:28:49Z","title":"LDPTrace: Locally Differentially Private Trajectory Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.06180","snapshot_observed_at":"2026-08-07T01:06:21.989017Z","title":"Ldptrace: Locally differentially private trajectory synthesis.arXiv preprint arXiv:2302.06180,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.989017Z"},"links":{"cited_paper":"/paper/2302.06180","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:99e845bb132e88ee1da285f6e855fddd22e7483e90548aae5b27f9b784af376b","observation_id":"895c84d0-2b94-473e-ba75-36925f275f4b","resolution":{"observed_at":"2026-08-07T01:06:21.989017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00267","last_updated":"2025-02-25T20:31:22Z","snapshot_observed_at":"2026-08-05T17:00:32.828234Z","submitted_at":"2024-05-01T01:20:25Z","title":"Differentially Private Release of Israel's National Registry of Live Births","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00267","snapshot_observed_at":"2026-08-07T01:06:22.000079Z","title":"Differentially private release of Israel’s national registry of live births.arXiv preprint arXiv:2405.00267,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:22.000079Z"},"links":{"cited_paper":"/paper/2405.00267","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:e92d66cff5852e01c9f8681bce07e860196cf0206b835c5f554fb4bdbcc94e00","observation_id":"65ac214e-6ecf-4974-a679-d4a593bd89e9","resolution":{"observed_at":"2026-08-07T01:06:22.000079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02621","last_updated":"2026-05-18T08:19:15Z","snapshot_observed_at":"2026-08-01T16:22:24.701488Z","submitted_at":"2025-05-05T12:49:42Z","title":"Mirror Mean-Field Langevin Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02621","snapshot_observed_at":"2026-08-07T01:06:21.992796Z","title":"Mirror mean-field langevin dynamics.arXiv preprint arXiv:2505.02621,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T01:06:21.992796Z"},"links":{"cited_paper":"/paper/2505.02621","citing_paper":"/paper/2506.12203"},"observation_digest":"sha256:9e4cebbb310a31d8b0e79812c79408bf0f0e58fda638353f769ca427a3b0d961","observation_id":"4cc00b5d-3352-483b-927e-035afa777661","resolution":{"observed_at":"2026-08-07T01:06:21.992796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.12203","last_updated":"2025-06-13T20:13:37Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T00:53:38.309767Z","submitted_at":"2025-06-13T20:13:37Z","title":"Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":3},"total_outbound_references":14},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2506.12203."}