{"as_of":"2026-08-07T10:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:31a8708ba02d92ad55202434a0300436995ec8fe23fb60aceec597965557aa70","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T09:50:24.075860Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2607.16251/citation-record","integrity":"/paper/2607.16251/integrity","json":"/paper/2607.16251/citation-record.json","paper":"/paper/2607.16251"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:50:17.881019Z","title":"Foundation models for spatio-temporal data science: A tutorial and survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:17.881019Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:5364b9094c9e9c588b6d698d15656a0240af0bb5efe83e49a6c07fafe86183a2","observation_id":"d4a3b574-a596-415e-81e8-0da526f51a1c","resolution":{"observed_at":"2026-08-02T09:50:17.881019Z","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":"2026-08-02T09:50:17.995492Z","title":"Unraveling spatio-temporal foundation models via the pipeline lens: A comprehensive review,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:17.995492Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:906efa2354535301779f2172a89f1d3aa803373f1fe5d4eecd8a45822e181d33","observation_id":"783d94f3-fa53-42e4-be45-2514aadc8a74","resolution":{"observed_at":"2026-08-02T09:50:17.995492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09045","last_updated":"2025-02-07T02:39:32Z","snapshot_observed_at":"2026-07-06T20:21:37.540432Z","submitted_at":"2025-01-15T08:52:28Z","title":"Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09045","snapshot_observed_at":"2026-08-02T09:50:18.159385Z","title":"Spatio-temporal foundation models: Vision, challenges, and opportunities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.159385Z"},"links":{"cited_paper":"/paper/2501.09045","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:5545d4eb85176c610229397a625284ab0b57fb43b04427f625115961cbad6923","observation_id":"e7750401-664a-44b5-83ef-538ed6e15f6c","resolution":{"observed_at":"2026-08-02T09:50:18.159385Z","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":"2026-08-02T09:50:18.277191Z","title":"Spatio-temporal graph neural networks for predictive learning in urban computing: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.277191Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:68c88badbd6d422767c8cbd56e80c9dc9eea3a092a9bbcc1644438f56eecfd91","observation_id":"c37e2aa2-0aee-41ee-babb-0d5def629625","resolution":{"observed_at":"2026-08-02T09:50:18.277191Z","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":"2026-08-02T09:50:18.480445Z","title":"Flownet: Modeling dynamic spatio-temporal systems via flow propagation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.480445Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:cc4347ef2b1bd40261c2905746c9fbedba1bd14b5c97e4a913361ced04c2349c","observation_id":"2dfa3785-9fab-4463-b1a6-8674bc901e93","resolution":{"observed_at":"2026-08-02T09:50:18.480445Z","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":"2026-08-02T09:50:18.671708Z","title":"Representation learning for spatiotemporal physical systems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.671708Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:1d4a324e8a7ba6a1e919ef25dd33efb28281b0be30328249ca99c2061b25cad8","observation_id":"011faa7a-7418-4254-8de6-13edfa22de49","resolution":{"observed_at":"2026-08-02T09:50:18.671708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.03208","last_updated":"2026-06-16T20:46:31Z","snapshot_observed_at":"2026-07-13T13:29:04.173053Z","submitted_at":"2026-04-03T17:32:36Z","title":"Hierarchical Planning with Latent World Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.03208","snapshot_observed_at":"2026-08-02T09:50:18.760889Z","title":"Hierarchical planning with latent world models,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.760889Z"},"links":{"cited_paper":"/paper/2604.03208","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:5c5f92e81c88a98ab402fc2cd8226ab8ce873c53050c9c5dbfd259c7ff1fc21a","observation_id":"7701f4d9-de50-4de3-b274-bd0fa528b494","resolution":{"observed_at":"2026-08-02T09:50:18.760889Z","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":"2026-08-02T09:50:18.944330Z","title":"An observed value consistent diffusion model for imputing missing values in multivariate time series,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:18.944330Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:61113d0aa71de0584b6a7df9dd5ef003492f9dcf39caf4159be26b6c5e6edeb1","observation_id":"986c9a95-0f50-4738-80ae-6982ec8007c0","resolution":{"observed_at":"2026-08-02T09:50:18.944330Z","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":"2026-08-02T09:50:19.026674Z","title":"Foundation models for time series analysis: A tutorial and survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.026674Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:a17d015efe83c05c371e80c8c7bddb9acd01c35dc16d426bfb05b8ed650d31a3","observation_id":"22183c4b-5527-4f28-ae0a-7601fb825fc0","resolution":{"observed_at":"2026-08-02T09:50:19.026674Z","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":"2026-08-02T09:50:19.118170Z","title":"Deep learning for time series forecasting: Tutorial and literature survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.118170Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:6071c28606d4ded37049b621fcaecc63e43d3265fa79a2a80c8330a44415416d","observation_id":"c880734b-d037-4b9f-b13e-6c8cc751eb34","resolution":{"observed_at":"2026-08-02T09:50:19.118170Z","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":"2026-08-02T09:50:19.161624Z","title":"Time-series forecasting with deep learning: a survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.161624Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:e03c77f2e98bc2bedc9d111facca2d900a369fc5d71ba29583716cec5e63d78e","observation_id":"a9deb03e-ae92-4e07-8fc4-35f48f90093f","resolution":{"observed_at":"2026-08-02T09:50:19.161624Z","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":"2026-08-02T09:50:19.239577Z","title":"A survey on diffusion models for time series and spatio-temporal data,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.239577Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:c3e651dd55a5d9ceb0cd89f58e82a6b12d1660f0aa6050189341e85f704488f6","observation_id":"7dd170b1-1438-43fc-bd53-92068e0afffc","resolution":{"observed_at":"2026-08-02T09:50:19.239577Z","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":"2026-08-02T09:50:19.345121Z","title":"A survey on diffusion models for time series and spatio-temporal data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.345121Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:77ddb730a125f84f78e389af5892de64ebab03f076eee053bacbf469ffe5e79f","observation_id":"ad185695-fa46-4226-ac7f-cf91c9a14cba","resolution":{"observed_at":"2026-08-02T09:50:19.345121Z","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":"2026-08-02T09:50:19.405841Z","title":"Diffstg: Probabilistic spatio-temporal graph forecasting with denoising diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.405841Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:24667db15b18c8aea912d6312e34b83fb8f717b8fc965a4384edde9c90d4e377","observation_id":"eeed1baa-0557-4341-8618-18640f9649a9","resolution":{"observed_at":"2026-08-02T09:50:19.405841Z","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":"2026-08-02T09:50:19.508552Z","title":"Towards unifying diffusion models for probabilistic spatio-temporal graph learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.508552Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:76d65d5cf86a192d2643e805785f6f29c83ac015c93690a5d9ebc57fea3efc7e","observation_id":"a1d20111-b362-43f5-8f9c-9456babec75f","resolution":{"observed_at":"2026-08-02T09:50:19.508552Z","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":"2026-08-02T09:50:19.586246Z","title":"A comprehensive survey of regression-based loss functions for time series forecasting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.586246Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:73b8bffa4032f9c352b170634141240a842b7d100269d83f6dbf1b9e02c83fdf","observation_id":"2dbbde89-0b06-42fe-85ff-74b1394fb650","resolution":{"observed_at":"2026-08-02T09:50:19.586246Z","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":"2026-08-02T09:50:19.661488Z","title":"Soft-dtw: a differentiable loss function for time-series,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.661488Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:759a3b4797c5daab98c09d019b36284a56872605941e5f43111ca776d65ad2b6","observation_id":"83cc21ef-dc57-4280-8fe5-a562556ff0a0","resolution":{"observed_at":"2026-08-02T09:50:19.661488Z","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":"2026-08-02T09:50:19.735002Z","title":"Shape and time distortion loss for training deep time series forecasting models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.735002Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:cdf875529919f984adb46ea1c7d340e6537ef2795d58e882b8dba728112ebcce","observation_id":"0afe3aaa-0f83-4cff-82e3-8232bd08b0c5","resolution":{"observed_at":"2026-08-02T09:50:19.735002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10196","last_updated":"2026-06-08T01:28:46Z","snapshot_observed_at":"2026-07-06T16:33:34.184498Z","submitted_at":"2023-10-16T09:06:00Z","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10196","snapshot_observed_at":"2026-08-02T09:50:19.817465Z","title":"Large models for time series and spatio-temporal data: A survey and outlook,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.817465Z"},"links":{"cited_paper":"/paper/2310.10196","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:78dd31c0abe1a24a12045a75c3ebd30693eff56d7a653f4c1f7acd55aed03918","observation_id":"0515b1e9-92e8-4514-a898-132385855f1c","resolution":{"observed_at":"2026-08-02T09:50:19.817465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.03248","last_updated":"2026-04-22T22:13:36Z","snapshot_observed_at":"2026-07-06T22:40:51.136169Z","submitted_at":"2026-01-06T18:46:12Z","title":"STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.03248","snapshot_observed_at":"2026-08-02T09:50:19.880661Z","title":"Streasoner: Empowering llms for spatio- temporal reasoning in time series via spatial-aware reinforcement learning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.880661Z"},"links":{"cited_paper":"/paper/2601.03248","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:0c7d66b4a4efaa3a4a15181fc2616c4e414f5be0abff235c03eaa403ecba4738","observation_id":"d79bf737-730d-412e-8743-745768402dc6","resolution":{"observed_at":"2026-08-02T09:50:19.880661Z","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":"2026-08-02T09:50:19.976422Z","title":"A decoder-only foundation model for time-series forecasting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:19.976422Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:ae3d67cd94cd5aa0d93cd57d9ed2e87df5e1a451c480ccbc0e4bafac177ce2a1","observation_id":"089cc842-e3b7-4d63-99bb-697fcf20b245","resolution":{"observed_at":"2026-08-02T09:50:19.976422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07815","last_updated":"2024-11-04T17:42:45Z","snapshot_observed_at":"2026-07-06T17:43:27.034067Z","submitted_at":"2024-03-12T16:53:54Z","title":"Chronos: Learning the Language of Time Series","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07815","snapshot_observed_at":"2026-08-02T09:50:20.115724Z","title":"Chronos: Learning the language of time series,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.115724Z"},"links":{"cited_paper":"/paper/2403.07815","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:cd483772944f135a1d8392360fba01b8d500f8c12fe1e40df5d1172ee73774d2","observation_id":"bec39383-eb80-4069-be6a-1bf58f226340","resolution":{"observed_at":"2026-08-02T09:50:20.115724Z","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":"2026-08-02T09:50:20.225245Z","title":"Unified training of universal time series forecasting transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.225245Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:0517220d2c5122c59306cbf815e9f3365d02f887427d05bbfc2adaffbf389b2e","observation_id":"aebe517e-a15e-48d0-b1de-7981a696afaf","resolution":{"observed_at":"2026-08-02T09:50:20.225245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10469","last_updated":"2024-10-14T13:01:11Z","snapshot_observed_at":"2026-07-06T19:33:04.265295Z","submitted_at":"2024-10-14T13:01:11Z","title":"Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10469","snapshot_observed_at":"2026-08-02T09:50:20.337617Z","title":"Moirai-moe: Empowering time series foundation models with sparse mixture of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.337617Z"},"links":{"cited_paper":"/paper/2410.10469","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:03b7fb67b4782617e532fd6bfe502f54c883623938b5d965b73a04bb668f2bfb","observation_id":"37f2d32e-bb80-4992-9a22-4426a607e890","resolution":{"observed_at":"2026-08-02T09:50:20.337617Z","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":"2026-08-02T09:50:20.408769Z","title":"Moirai 2.0: When less is more for time series forecasting,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.408769Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:53f7db01df161744167db8897be23698ef334ddbef368475419f154268f64117","observation_id":"08ba469b-7e7b-46fe-9ad6-4c5b35e1b261","resolution":{"observed_at":"2026-08-02T09:50:20.408769Z","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":"2026-08-02T09:50:20.483331Z","title":"Unitime: A language- empowered unified model for cross-domain time series forecasting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.483331Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:b5b6382b76c693389edb3e44510a79be3d0d28aa42e5f09623c4abe0c5662134","observation_id":"63d251fc-8aa2-4f2a-8214-d2785827efb8","resolution":{"observed_at":"2026-08-02T09:50:20.483331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03885","last_updated":"2024-10-10T15:37:45Z","snapshot_observed_at":"2026-08-05T08:29:54.807725Z","submitted_at":"2024-02-06T10:48:46Z","title":"MOMENT: A Family of Open Time-series Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03885","snapshot_observed_at":"2026-08-02T09:50:20.556896Z","title":"Moment: A family of open time-series foundation models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.556896Z"},"links":{"cited_paper":"/paper/2402.03885","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:5ccbbaad274f9b7c8d793a0fcfdd70cd72db6745c49efa070adde9495c1afc83","observation_id":"781535af-56fc-491c-a310-cd2058bb3d00","resolution":{"observed_at":"2026-08-02T09:50:20.556896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16040","last_updated":"2025-02-27T05:38:14Z","snapshot_observed_at":"2026-08-07T04:23:22.512255Z","submitted_at":"2024-09-24T12:42:18Z","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16040","snapshot_observed_at":"2026-08-02T09:50:20.667752Z","title":"Time-moe: Billion-scale time series foundation models with mixture of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.667752Z"},"links":{"cited_paper":"/paper/2409.16040","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:d34060468930b580081b0aeb04503927d33d5539e012bc96df8ef47248d95329","observation_id":"bf2dbf65-8e63-4a51-b02b-6821e28bef31","resolution":{"observed_at":"2026-08-02T09:50:20.667752Z","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":"2026-08-02T09:50:20.773611Z","title":"Opencity: Open spatio-temporal foundation models for traffic prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.773611Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:28c71c8ea7294f2dd57522823002f32bd3283b0b4b882e02f535f0cb6faa4d2e","observation_id":"95f8e91f-17e4-4f5f-a967-6f368cd4413a","resolution":{"observed_at":"2026-08-02T09:50:20.773611Z","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":"2026-08-02T09:50:20.871606Z","title":"Unist: A prompt-empowered universal model for urban spatio-temporal prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.871606Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:c757d728ecf468a28973da116153e5cb6b0e1c6b695115ad09c8472beda4d844","observation_id":"65540759-a174-418e-b9e3-7163108b154b","resolution":{"observed_at":"2026-08-02T09:50:20.871606Z","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":"2026-08-02T09:50:20.938195Z","title":"Urbangpt: Spatio-temporal large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:20.938195Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:fb942d3b091be3e1c9986e281e6cf4b028e3366cd55a6e6f1e0abe3952b1d853","observation_id":"b2602dde-28e3-48a5-a630-7c6c8fd8c437","resolution":{"observed_at":"2026-08-02T09:50:20.938195Z","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":"2026-08-02T09:50:21.030649Z","title":"Airformer: Predicting nationwide air quality in china with transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.030649Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:46060c5a80e88dc423ebba82a9458d51c8626b28b823e69d8139e2859e533724","observation_id":"99d5ccb8-b2b1-48f7-8467-099251eae204","resolution":{"observed_at":"2026-08-02T09:50:21.030649Z","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":"10.24963/ijcai.2024/803","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Spatio-temporal field neural networks for air quality inference,","venue":null,"work_id":"4243ff40-628e-4b07-9ab2-38aeae15789c","year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.128502Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:44db9c7a22056a7256a04cc3a64e9401da83c23890e078ea45fdfe25ef98aba2","observation_id":"bf4f30ab-c2a8-4944-988c-9cb0f9cbd0b6","resolution":{"observed_at":"2026-08-02T09:53:27.419444Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-02T09:50:21.221881Z","title":"Accurate medium-range global weather forecasting with 3d neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.221881Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:20a23567777bf0a513cc82bbd924c0bdeee00c255b1d1c93afebb918f92fbf45","observation_id":"5ec18af9-6dc3-4510-a418-6bc957c405cf","resolution":{"observed_at":"2026-08-02T09:50:21.221881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.10343","last_updated":"2023-12-18T18:16:12Z","snapshot_observed_at":"2026-08-07T07:30:31.438078Z","submitted_at":"2023-01-24T23:19:01Z","title":"ClimaX: A foundation model for weather and climate","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.10343","snapshot_observed_at":"2026-08-02T09:50:21.303098Z","title":"Climax: A foundation model for weather and climate,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.303098Z"},"links":{"cited_paper":"/paper/2301.10343","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:fe5fb88837833eb55b1745d9de1276b9d8330a4415cbb1b16f25897e1af9d502","observation_id":"5ed764a5-cb3e-4273-9338-859544f83fab","resolution":{"observed_at":"2026-08-02T09:50:21.303098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19606","last_updated":"2025-03-18T10:12:54Z","snapshot_observed_at":"2026-07-06T19:24:03.133851Z","submitted_at":"2024-09-29T07:57:07Z","title":"Hyper-Connections","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19606","snapshot_observed_at":"2026-08-02T09:50:21.394076Z","title":"Hyper- connections,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.394076Z"},"links":{"cited_paper":"/paper/2409.19606","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:b298ac015365cb107a3f1ce3966b52c2fd32d9567bf5cc29ecca01bd382bfc23","observation_id":"16759ec6-d259-40cf-9ac3-32277ccf8461","resolution":{"observed_at":"2026-08-02T09:50:21.394076Z","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":"2026-08-02T09:50:21.487431Z","title":"Reversible instance normalization for accurate time-series forecasting against distribution shift,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.487431Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:722e6b0a28932b80d2532e85d5ffc52c2e1e092893b399a7d0f24b9dfe50a273","observation_id":"15548eac-0ca5-4d11-809f-b4040dcf1bd0","resolution":{"observed_at":"2026-08-02T09:50:21.487431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.06708","last_updated":"2025-05-10T17:15:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-10T17:15:49Z","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.06708","snapshot_observed_at":"2026-08-02T09:50:21.593887Z","title":"Gated attention for large language models: Non-linearity, sparsity, and attention-sink-free,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.593887Z"},"links":{"cited_paper":"/paper/2505.06708","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:c2a819ba5a4b0957f0b6a86db2352471bf929789b4f3325457482bb2f8b68972","observation_id":"5bfcc3a3-82c9-46ae-a547-06add249eac1","resolution":{"observed_at":"2026-08-02T09:50:21.593887Z","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":"2026-08-02T09:50:21.682533Z","title":"Roformer: Enhanced transformer with rotary position embedding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.682533Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:4195cc108d449797345e86cbf75747fe992889d3a674eb89de103651b0ec2045","observation_id":"a91c7fef-4e0c-4a61-93fe-6bb11e766310","resolution":{"observed_at":"2026-08-02T09:50:21.682533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.07659","last_updated":"2016-12-22T15:53:57Z","snapshot_observed_at":"2026-08-02T01:46:27.642002Z","submitted_at":"2016-12-22T15:53:57Z","title":"Structured Sequence Modeling with Graph Convolutional Recurrent Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.07659","snapshot_observed_at":"2026-08-02T09:50:21.753108Z","title":"Structured sequence modeling with graph convolutional recurrent networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.753108Z"},"links":{"cited_paper":"/paper/1612.07659","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:3a245ae214b6168ddd869efc0b2e78dec6f786fb1aa318f0d75bdabe9c7b589f","observation_id":"b0175e1f-8815-48a3-acda-75ba53069b72","resolution":{"observed_at":"2026-08-02T09:50:21.753108Z","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":"2026-08-02T09:50:21.842470Z","title":"Principal component analysis,","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.842470Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:76096ead4c8d9dbf8beb635a6d9cea2db55565c770d4fd0a42f223de78fecea1","observation_id":"bdc171e4-6bc9-4aee-b837-02a8ae10b21c","resolution":{"observed_at":"2026-08-02T09:50:21.842470Z","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":"2026-08-02T09:50:21.910638Z","title":"Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.910638Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:504fa3aef1cdafbdb287f2f30cfe89dcf0ea5e1927967fe79ded7f9300988c4a","observation_id":"44435022-e170-4157-87af-2978f975a796","resolution":{"observed_at":"2026-08-02T09:50:21.910638Z","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":"2026-08-02T09:50:21.990583Z","title":"Diffusion convolutional recurrent neural network: Data- driven traffic forecasting,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:21.990583Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:ec78597de5a3c9498edc721f3c9216c5518efe137b47b373a17a5342e15d8749","observation_id":"b3be6d28-40b3-49c8-b823-5c010d7f3edb","resolution":{"observed_at":"2026-08-02T09:50:21.990583Z","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":"2026-08-02T09:50:22.051379Z","title":"Learning to factorize spatio-temporal foundation models,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.051379Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:f7a02af93ecc19fe0a169823be237cd11db1baab500a2d67ba2180954256df42","observation_id":"55f6d985-433e-4d00-b3d6-b260a69da40d","resolution":{"observed_at":"2026-08-02T09:50:22.051379Z","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":"2026-08-02T09:50:22.098041Z","title":"Rose: Register-assisted general time series forecasting with decomposed frequency learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.098041Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:62a14a466f9965cbf743dbe7200bc8bde69589a6424bc2c5d88f2a99cb973954","observation_id":"c240db4b-be45-4c0e-b43b-72e75cb9b985","resolution":{"observed_at":"2026-08-02T09:50:22.098041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-02T09:50:22.166864Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.166864Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:72fa184063171b22cd929915d64fb2677587e708020e8d966d7bab793e71aa7e","observation_id":"e1ce35f9-115c-4727-8fd8-15031b72ff02","resolution":{"observed_at":"2026-08-02T09:50:22.166864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11411","last_updated":"2025-03-14T13:53:46Z","snapshot_observed_at":"2026-07-06T20:52:45.934843Z","submitted_at":"2025-03-14T13:53:46Z","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.11411","snapshot_observed_at":"2026-08-02T09:50:22.243832Z","title":"Empowering time series analysis with synthetic data: A survey and outlook in the era of foundation models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.243832Z"},"links":{"cited_paper":"/paper/2503.11411","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:2707874658a946f9d22f0e253bfc248dd990364e8b19bb181cbf3e9d7675e00e","observation_id":"442c5cb9-0282-4654-add1-65f063243f8b","resolution":{"observed_at":"2026-08-02T09:50:22.243832Z","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":"2026-08-02T09:50:22.310046Z","title":"Largest: A benchmark dataset for large-scale traffic forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.310046Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:92c3708b0d2c2fd42eac46d48b3783f3680426cc261ef081c92a2419682f41f1","observation_id":"7dbcaa06-099a-42f5-9083-e6f573dc6c9f","resolution":{"observed_at":"2026-08-02T09:50:22.310046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18910","last_updated":"2024-05-29T09:11:51Z","snapshot_observed_at":"2026-07-06T18:21:52.950440Z","submitted_at":"2024-05-29T09:11:51Z","title":"Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18910","snapshot_observed_at":"2026-08-02T09:50:22.382020Z","title":"Predicting parking availability in singapore with cross-domain data: A new dataset and a data-driven approach,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.382020Z"},"links":{"cited_paper":"/paper/2405.18910","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:ef4641985a00ef5bdcbc1a1589cac652a6487cd199b031bf5c24f663cd713a96","observation_id":"05a813ca-e137-411c-bf8e-f9f707f8a63c","resolution":{"observed_at":"2026-08-02T09:50:22.382020Z","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":"2026-08-02T09:50:22.456763Z","title":"Lade: The first comprehensive last-mile express dataset from industry,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.456763Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:eb5ab6b7cea884f37282b514aff6485a36cb92d22e1958bc8e85e94882748123","observation_id":"a1a362dc-0eb7-4435-b46d-7bfbb9c08f44","resolution":{"observed_at":"2026-08-02T09:50:22.456763Z","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":"2026-08-02T09:50:22.522699Z","title":"Generative adversarial networks for spatio-temporal data: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.522699Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:c069eaaaa17dd9608a46ff2961e4e73d92b9f66bede10c7e2256186fc83d083a","observation_id":"8ec15eb6-9a79-4e04-afe6-13cf9a862fc7","resolution":{"observed_at":"2026-08-02T09:50:22.522699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.04140","last_updated":"2025-07-15T16:09:44Z","snapshot_observed_at":"2026-08-07T01:27:28.075638Z","submitted_at":"2025-02-06T15:20:32Z","title":"Synthetic Datasets for Machine Learning on Spatio-Temporal Graphs using PDEs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.04140","snapshot_observed_at":"2026-08-02T09:50:22.627360Z","title":"Synthetic datasets for machine learning on spatio-temporal graphs using pdes,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.627360Z"},"links":{"cited_paper":"/paper/2502.04140","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:81f547a67485a6307a6531faa396982675fa051e6e2ba7ab95497ace0eb2b732","observation_id":"5ec2a6b0-e850-466b-8278-8b77286fa349","resolution":{"observed_at":"2026-08-02T09:50:22.627360Z","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":"2026-08-02T09:50:22.721786Z","title":"Difftraj: Generating gps trajectory with diffusion probabilistic model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.721786Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:4f7b8030ffb3bb748c5071705dc96326437ddb840fbe076498ee5a4c95c63181","observation_id":"a6306d0c-4710-4567-8fec-520b802d9373","resolution":{"observed_at":"2026-08-02T09:50:22.721786Z","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":"2026-08-02T09:50:22.815657Z","title":"Controltraj: Controllable trajectory generation with topology-constrained diffusion model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.815657Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:d1e8843365e91639a7483596c065dd0be8010da1372e9c525b5db4175e9f46bf","observation_id":"f7e27382-fd07-4335-8423-a23180c5a917","resolution":{"observed_at":"2026-08-02T09:50:22.815657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.20846","last_updated":"2026-05-14T08:13:14Z","snapshot_observed_at":"2026-08-03T01:47:34.109311Z","submitted_at":"2025-09-25T07:34:46Z","title":"Causal Time Series Generation via Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.20846","snapshot_observed_at":"2026-08-02T09:50:22.909940Z","title":"Causal time series generation via diffusion models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:22.909940Z"},"links":{"cited_paper":"/paper/2509.20846","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:271e29926573d1b9eaa7616d21973792a44b29f0b6afd3fd715001ee0df071e4","observation_id":"da64f3bd-a0aa-4142-8e68-cce6c989a5b6","resolution":{"observed_at":"2026-08-02T09:50:22.909940Z","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":"2026-08-02T09:50:23.044248Z","title":"Self-supervised learning for time series analysis: Taxonomy, progress, and prospects,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.044248Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:1951b2fbd7a4587752d4f341d67b0ea612ce737fa25b5ccaea69c1d9b7d9f65a","observation_id":"ce62061e-6e33-4daf-b81f-5119033438c5","resolution":{"observed_at":"2026-08-02T09:50:23.044248Z","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":"2026-08-02T09:50:23.154275Z","title":"Self-supervised learning from images with a joint-embedding predictive architecture,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.154275Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:4b5df2472394f7c3ba553bfa8b2b7d221503e092cd537a1f2a43c67adad0e224","observation_id":"e211c1b7-6d52-4138-80cd-4a1935cf7754","resolution":{"observed_at":"2026-08-02T09:50:23.154275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.08544","last_updated":"2025-11-14T08:38:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-11T18:21:55Z","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.08544","snapshot_observed_at":"2026-08-02T09:50:23.273927Z","title":"Lejepa: Provable and scalable self-supervised learning without the heuristics,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.273927Z"},"links":{"cited_paper":"/paper/2511.08544","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:2e13fcdb5298e9f928636a5edeff541c8ee8e3d896924f2b017f6827809cf8cc","observation_id":"a1872483-6447-46cc-a898-ded3277166d9","resolution":{"observed_at":"2026-08-02T09:50:23.273927Z","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":"2026-08-02T09:50:23.367869Z","title":"T-jepa: A joint-embedding predictive architecture for trajectory similarity computation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.367869Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:e0441251d1d36eba952c23ba404e32a5f1899d9dfbc191e4e4145fab8d399df6","observation_id":"86bc99d0-ef9b-4e8b-9ee1-dd7c0c55316c","resolution":{"observed_at":"2026-08-02T09:50:23.367869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.00028","last_updated":"2026-06-24T09:19:05Z","snapshot_observed_at":"2026-08-07T00:15:20.565016Z","submitted_at":"2025-06-17T11:46:03Z","title":"HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.00028","snapshot_observed_at":"2026-08-02T09:50:23.455528Z","title":"Hit-jepa: A hierarchical self-supervised trajectory embedding framework for similarity computation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.455528Z"},"links":{"cited_paper":"/paper/2507.00028","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:34bc67090720d6734457ecf762e19c77babc1a8e46614a5f7270e4f49f40376f","observation_id":"e651b091-2a4f-4dc4-a34e-0215d0bab56d","resolution":{"observed_at":"2026-08-02T09:50:23.455528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12360","last_updated":"2025-03-18T06:54:45Z","snapshot_observed_at":"2026-08-05T11:14:21.998874Z","submitted_at":"2024-10-16T08:23:39Z","title":"Towards Neural Scaling Laws for Time Series Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12360","snapshot_observed_at":"2026-08-02T09:50:23.556077Z","title":"Towards neural scaling laws for time series foundation models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.556077Z"},"links":{"cited_paper":"/paper/2410.12360","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:5fba8237a150ccd2be6f75c052d3bffbf816d5ebc839f3065e61267ce965277a","observation_id":"c186d53f-5251-462e-add7-9f8ce92e424e","resolution":{"observed_at":"2026-08-02T09:50:23.556077Z","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":"2026-08-02T09:50:23.737645Z","title":"Scaling law for time series forecasting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.737645Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:2491a6a26a9778e31013753997fb11805ecb218b930854b85c20dc804115ade3","observation_id":"c675dced-d8c0-413a-bb64-73ffc87ba9b6","resolution":{"observed_at":"2026-08-02T09:50:23.737645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13867","last_updated":"2025-01-08T14:08:11Z","snapshot_observed_at":"2026-08-02T22:13:00.551592Z","submitted_at":"2024-05-22T17:48:17Z","title":"Scaling-laws for Large Time-series Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13867","snapshot_observed_at":"2026-08-02T09:50:23.904462Z","title":"Scaling-laws for large time-series models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:23.904462Z"},"links":{"cited_paper":"/paper/2405.13867","citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:3b535936ed7ef37678ab79de6da8b885bb76f0ff63d0d62b8d9229162fbdbe89","observation_id":"3266b451-762d-4163-9a63-bcab426e6722","resolution":{"observed_at":"2026-08-02T09:50:23.904462Z","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":"2026-08-02T09:50:24.075860Z","title":"sim-to-real","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-02T09:50:24.075860Z"},"links":{"citing_paper":"/paper/2607.16251"},"observation_digest":"sha256:b1c8cea5c97eda87a011a949847b9acb296615a18a5c6d2263a675426dba9054","observation_id":"77ebc6f0-70df-4f1e-aa68-487695e33c88","resolution":{"observed_at":"2026-08-02T09:50:24.075860Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.16251","last_updated":"2026-06-27T02:56:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T15:16:34.197063Z","submitted_at":"2026-06-27T02:56:46Z","title":"Learning Spatio-Temporal Foundation Models from Pure Synthetic Data"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":64},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2607.16251."}