{"as_of":"2026-08-10T07:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5da7afaaf493698bfec123f5f9940d8b856fb7683b8fc0fdb04cc385c18a8d84","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T04:58:41.837117Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"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/2607.22399/citation-record","integrity":"/paper/2607.22399/integrity","json":"/paper/2607.22399/citation-record.json","paper":"/paper/2607.22399"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T04:58:39.520881Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:39.520881Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:708de1cec8d702f03870285da807b194cb44ed646b8f1f6b59949b377a45887c","observation_id":"4f2c8fda-df62-4efb-b653-ec77a8f2fdac","resolution":{"observed_at":"2026-08-01T04:58:39.520881Z","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":"2026-08-01T04:58:39.848581Z","title":"Fischer, S","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:39.848581Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:07f79c37c5205e214946cf5cdb90717b9ee1bfc565cfe7e92b3cfce69550cda2","observation_id":"b84fdc2d-ac38-4fa9-9432-61fbdf59f305","resolution":{"observed_at":"2026-08-01T04:58:39.848581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1206.4655","last_updated":"2012-06-18T15:25:58Z","snapshot_observed_at":"2026-08-03T00:57:54.703694Z","submitted_at":"2012-06-18T15:25:58Z","title":"Modelling transition dynamics in MDPs with RKHS embeddings","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.4655","snapshot_observed_at":"2026-08-01T04:58:39.920954Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:39.920954Z"},"links":{"cited_paper":"/paper/1206.4655","citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:074d3cdea31cc8d0bea95dfcd7872d9472b81b69eb4ba06ed314677e6a37d429","observation_id":"528dee93-de8b-4147-92b1-4be93fda8070","resolution":{"observed_at":"2026-08-01T04:58:39.920954Z","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":"2026-08-01T04:58:40.758807Z","title":"If the conditional probabilities in(85) do not depend ont, the process is calledtime-homogeneous","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.758807Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:8e68af2dd72fae44e60ffe76c690bf9205e1d68246a52f299872db3864bf991d","observation_id":"4b9bd2bb-d8f4-481b-8fd6-8683d465d371","resolution":{"observed_at":"2026-08-01T04:58:40.758807Z","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":"2026-08-01T04:58:40.949041Z","title":"are mutually independent, then P-almost everyω∈Ωdetermines a sequence xt =X t(ω), η t =N t(ω), satisfying (87)","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.949041Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:2b92485560dd4e7936621655e47578a449de14cf62ee46085cd53156aea734aa","observation_id":"7d3b0829-b6e2-4f9a-84cf-ead1e6d4af04","resolution":{"observed_at":"2026-08-01T04:58:40.949041Z","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":"2026-08-01T04:58:41.064500Z","title":"are mutually independent,X0 has law(ξ0)#PX, and eachNt has lawξη #PN","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.064500Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:5f2626e8d6ad8f2fc9c217e512e809d745820430989e2166291c03974e3fa7de","observation_id":"70d47e31-a97b-40de-a7a9-7dc6ed7c1ece","resolution":{"observed_at":"2026-08-01T04:58:41.064500Z","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":"2026-08-01T04:58:41.221891Z","title":"(90) Let Gt = { σ(X0), t= 0, σ(X0,N 0,...,N t−1), t≥1","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.221891Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:372704ca4d9ac2427862514f09429a0f41c8c886cc59cf82902112ce8bd93a01","observation_id":"ed73a524-b073-4be4-9d3a-7bf6be70a301","resolution":{"observed_at":"2026-08-01T04:58:41.221891Z","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":"2026-08-01T04:58:41.318042Z","title":"SinceT is a measurable isomorphism onto its image˜Y, equality holds","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.318042Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:e658204427d2640e6e94e7ed55567a9cb3dd73e0692868d3e81a3f6dcf64a6b7","observation_id":"3d311b8e-c31c-4abf-894b-3cee6acc963c","resolution":{"observed_at":"2026-08-01T04:58:41.318042Z","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":"2026-08-01T04:58:41.468921Z","title":"P(x,A) = ∫ A 1 (2πσ 2)d/2 exp ( −∥x′−b(x)∥ 2 X 2σ2 )    p(x,x′) dx′, x∈X,A∈B(X)","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.468921Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:5f7a8701e7f65b52db60dd8d459a5a783469756cff4d8667d43dd8a9e1b96ba8","observation_id":"05ee6a04-f27f-4ad6-92d9-4b26f2df890c","resolution":{"observed_at":"2026-08-01T04:58:41.468921Z","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":"2026-08-01T04:58:41.551854Z","title":"It is positive since for allf∈H ⟨Σρf,f⟩H = ∫ |⟨f,Φ(x)⟩H|2ρ(dx)≥0","venue":null,"work_id":null,"year":1969},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.551854Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:88fa44da60183ee1f547f748443ae635879c066035aada6b379d376a9b48dde0","observation_id":"4a961c54-7b21-40d6-bbfc-68d4a8774b6b","resolution":{"observed_at":"2026-08-01T04:58:41.551854Z","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":"2026-08-01T04:58:41.719065Z","title":"See, e.g., Douc et al","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.719065Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:7db3a3d945a0719c80ac9b35bb4c6cac6e0bae099cbe36fc9297e1d974b89643","observation_id":"821f9e7a-03bb-447f-bdcc-68a5e940def1","resolution":{"observed_at":"2026-08-01T04:58:41.719065Z","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":"2026-08-01T04:58:41.837117Z","title":"Consequently,MT is a martingale inHwith respect toF","venue":null,"work_id":null,"year":1969},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:41.837117Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:a356c234fe5e5c65ef0f7322afa4af3f759735fd5e668a77858267c4fedc0c08","observation_id":"55685388-ac81-46a5-b177-070aa6c00751","resolution":{"observed_at":"2026-08-01T04:58:41.837117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02995","last_updated":"2025-04-03T19:35:38Z","snapshot_observed_at":"2026-08-07T16:10:28.399301Z","submitted_at":"2025-04-03T19:35:38Z","title":"Online Learning for Nonlinear Dynamical Systems without the I.I.D. Condition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02995","snapshot_observed_at":"2026-08-01T04:58:40.666452Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.666452Z"},"links":{"cited_paper":"/paper/2504.02995","citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:4d612dee6a67115146be72e90b6d63db349c2593caf24939cf2ff607bffaae59","observation_id":"ed960f61-cbbe-417b-8187-7782fa242d92","resolution":{"observed_at":"2026-08-01T04:58:40.666452Z","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":"2026-08-01T04:58:40.418121Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.418121Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:71072e4337c169232cb1790eddfa1ebdaf6c1b659cb946b5ddd78a90df069aa4","observation_id":"3865352a-c52f-4702-860e-4e84bfcfc66a","resolution":{"observed_at":"2026-08-01T04:58:40.418121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.12086","last_updated":"2021-10-29T21:12:18Z","snapshot_observed_at":"2026-08-09T23:16:49.570980Z","submitted_at":"2021-02-24T06:18:16Z","title":"Modern Koopman Theory for Dynamical Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.12086","snapshot_observed_at":"2026-08-01T04:58:39.684574Z","title":"Brockwell, P","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:39.684574Z"},"links":{"cited_paper":"/paper/2102.12086","citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:bfddb0cacf7eba54957c1ca960fc1eb49272a795e9bf3a38ec9c6aada52cf35f","observation_id":"c95a0974-c644-4873-a3cb-e82e967e771e","resolution":{"observed_at":"2026-08-01T04:58:39.684574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06101","last_updated":"2024-06-10T08:35:01Z","snapshot_observed_at":"2026-08-05T21:54:13.293686Z","submitted_at":"2024-06-10T08:35:01Z","title":"On the Consistency of Kernel Methods with Dependent Observations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06101","snapshot_observed_at":"2026-08-01T04:58:40.155834Z","title":"Li, Y., Zhang, T., Das, S., Shamma, J., and Li, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":107,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.155834Z"},"links":{"cited_paper":"/paper/2406.06101","citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:81812d7f01eeecf1330fca098bb70e619fe795b97b1e99230dd72931b6f56e45","observation_id":"52012ad6-465d-46b8-aaae-eb349c0feb7b","resolution":{"observed_at":"2026-08-01T04:58:40.155834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05814","last_updated":"2018-03-15T15:37:40Z","snapshot_observed_at":"2026-07-06T06:28:28.104983Z","submitted_at":"2018-03-15T15:37:40Z","title":"Theory and Algorithms for Forecasting Time Series","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05814","snapshot_observed_at":"2026-08-01T04:58:39.989678Z","title":"Kloeckner, B","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":156,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:39.989678Z"},"links":{"cited_paper":"/paper/1803.05814","citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:1ee8537108732bc8e05532985e311a8c164e09fc57db402a327dd5d492c3bab7","observation_id":"b5f3dd56-c483-47db-a6a9-5c105799b79f","resolution":{"observed_at":"2026-08-01T04:58:39.989678Z","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":"2026-08-01T04:58:40.301376Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":204,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.301376Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:f52df38e765a8eeab60e22195a8c79bb27e3785d68aad6f9836bb1f9af13ca22","observation_id":"6a8b3416-0d4f-4d16-857b-10a4b8596780","resolution":{"observed_at":"2026-08-01T04:58:40.301376Z","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":"2026-08-01T04:58:40.532557Z","title":"I., and Recht, B","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":423,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.532557Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:e07aba8a884572fc4a39dce42b16d42a04b7519c9e617d3d928f96eb7b092b1d","observation_id":"89039fa2-85cd-4641-acfa-cabca907443f","resolution":{"observed_at":"2026-08-01T04:58:40.532557Z","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":"2026-08-01T04:58:40.856185Z","title":"Thus the pair(µ0,P )determines the law of the processuniquely, although the process may admit many realizations on different probability spaces","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory","version":1},"reference_index":2002,"source":"pdf_text","source_observed_at":"2026-08-01T04:58:40.856185Z"},"links":{"citing_paper":"/paper/2607.22399"},"observation_digest":"sha256:c5b698ae20b386acb8005a4cfdfab1725bb59bd777813cc55ff64c2b9bf40ebd","observation_id":"156e6100-1d19-4ce0-9a05-f74608a14a11","resolution":{"observed_at":"2026-08-01T04:58:40.856185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.22399","last_updated":"2026-07-24T15:21:51Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-09T18:21:01.666099Z","submitted_at":"2026-07-24T15:21:51Z","title":"Learning Ergodic Dynamical Systems from a Finite Trajectory"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":20},"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 10 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2607.22399."}