{"as_of":"2026-08-06T18:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f851239d9dd6dbf4873161deb22ebdb5960e1d6ecb8add1202f1fbf9e8179435","coverage":[{"denominator":85,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":85,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T01:11:06.195977Z","state":"measured"},{"denominator":85,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":85,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+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/2607.14771/citation-record","integrity":"/paper/2607.14771/integrity","json":"/paper/2607.14771/citation-record.json","paper":"/paper/2607.14771"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T01:11:06.017589Z","title":"2023 , doi =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.017589Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:8730975175decfd5e388fbd4fbc4931fce02d36d7ddd40fe360175c1ac9957bf","observation_id":"61c924a8-f328-4ba2-b94a-36e623bba07a","resolution":{"observed_at":"2026-08-02T01:11:06.017589Z","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":"2026-08-02T01:11:06.021191Z","title":"and Ng, Serena , journal =","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.021191Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:22f40dfafc575513e4dc879aa01e166e7e595f518d7b618836873a50b49c5c44","observation_id":"ece5d31a-693e-4247-906a-8a57abb4054e","resolution":{"observed_at":"2026-08-02T01:11:06.021191Z","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":"2026-08-02T01:11:06.023584Z","title":"2020 , doi =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.023584Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:cfd50cfcb22f5783996235ef34700adcb7a7ee0d5b0857f3756c15ff5256be30","observation_id":"37d44f79-f73d-4985-992d-3322d11982be","resolution":{"observed_at":"2026-08-02T01:11:06.023584Z","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":"2026-08-02T01:11:06.026066Z","title":"2022 , doi =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.026066Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:29c06a149cf6683c83ae91c17687cb148a65888eaf65bcbb3cc8f4812c197b42","observation_id":"69e29cd4-270e-47e6-aab5-466194860566","resolution":{"observed_at":"2026-08-02T01:11:06.026066Z","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":"2026-08-02T01:11:06.028810Z","title":"2020 , doi =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.028810Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:aede362c11dd517e211eb02c9fbd9502eb78dba80ff78130ddeb94a71fd43aa4","observation_id":"1f039cb0-4c1c-4e90-9803-db39d5657a1b","resolution":{"observed_at":"2026-08-02T01:11:06.028810Z","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":"2026-08-02T01:11:06.031476Z","title":"Journal of Business & Economic Statistics , volume=","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.031476Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:35f85bc18b689537ec5be0888e9dc21b1222abb70d0f87fa2a6801558656c3fc","observation_id":"dccc014f-8b9d-4cb4-bb23-740e36e47158","resolution":{"observed_at":"2026-08-02T01:11:06.031476Z","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":"2026-08-02T01:11:06.033772Z","title":"2016 , publisher=","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.033772Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:c91093487026be542c4caa3b2cf740664f0c359bebb22d423fe61bf44bd08e0d","observation_id":"3a7de3f8-ece7-47a1-86be-1bd6357e84b7","resolution":{"observed_at":"2026-08-02T01:11:06.033772Z","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":"2026-08-02T01:11:06.036022Z","title":"2014 , url =","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.036022Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:49af0b284523b8ca10fcb276048b2faaac93e5e7ee9f19595b35f47db99c8e8e","observation_id":"f0e325bc-3ce8-4e34-8749-c42e25a3799f","resolution":{"observed_at":"2026-08-02T01:11:06.036022Z","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":"2026-08-02T01:11:06.038036Z","title":"2021 , doi =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.038036Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:755de6b3cd00887f016b66be5d8fadc03dfaf4ea8ce84f66276adc99f951d1d2","observation_id":"1d4222b0-2655-438c-af5d-31826841fc69","resolution":{"observed_at":"2026-08-02T01:11:06.038036Z","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":"2026-08-02T01:11:06.040509Z","title":"2004 , url =","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.040509Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:700eb6cbad433ae6dcc44771bb1bbd6d2d15110d3ad5c8b40d5c9e7015b7b33d","observation_id":"056f7851-bfd6-4764-8362-1b8dbc601b9a","resolution":{"observed_at":"2026-08-02T01:11:06.040509Z","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":"2026-08-02T01:11:06.042593Z","title":", journal =","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.042593Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:0bcb62e8ac74e27ee8cbcb5ce261c6f62ef9858a2573fe464b3ee34dfe2aea66","observation_id":"eb075b3d-a444-4376-9e40-75c6e57fa735","resolution":{"observed_at":"2026-08-02T01:11:06.042593Z","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":"2026-08-02T01:11:06.044571Z","title":"2008 , url =","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.044571Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:02c42d61db372f3c5903d6bb61469ffe196d95eee5304c2e3879a7f83340215b","observation_id":"b7703e34-03fa-4eac-b079-9fc3dc6aba7f","resolution":{"observed_at":"2026-08-02T01:11:06.044571Z","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":"2026-08-02T01:11:06.046564Z","title":"2010 , doi =","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.046564Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:67a2efa1c6cc3c528d0620dad362eacbf53968b8f9f0b1ce08a11be8857e6e1b","observation_id":"4b9cc975-0ee3-4c6a-92dd-0cfaa59aa6f2","resolution":{"observed_at":"2026-08-02T01:11:06.046564Z","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":"2026-08-02T01:11:06.048887Z","title":"2010 , url =","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.048887Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:fbcfe352b3effee79282a2368c97b534a98ffce266420e39cbde342a4b9f0ade","observation_id":"b0aa5f9c-70bd-4b32-b704-c59e25beff39","resolution":{"observed_at":"2026-08-02T01:11:06.048887Z","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":"2026-08-02T01:11:06.050889Z","title":"2010 , doi =","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.050889Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:3959749dcac21f56d5c46c78897a2c3952748d8cfeb90309e93c6a24ca23acb8","observation_id":"17074031-553e-4121-9c3d-cd4570153d6a","resolution":{"observed_at":"2026-08-02T01:11:06.050889Z","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":"2026-08-02T01:11:06.052641Z","title":"2013 , doi =","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.052641Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:1281d5bae31133433a6d212c61cac389c950aefca95b8b5ea616b499f7374297","observation_id":"b5bfcb73-b43a-46ae-b659-729384b21ccf","resolution":{"observed_at":"2026-08-02T01:11:06.052641Z","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":"2026-08-02T01:11:06.054559Z","title":"and Ghysels, Eric and Sohn, Bumjean , journal =","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.054559Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:0ee0c1ef6b0c85435496a9b53052691baa9370b2478de45c10609cd3d9d3522b","observation_id":"3d8840cb-192c-472b-a45a-54247eb87770","resolution":{"observed_at":"2026-08-02T01:11:06.054559Z","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":"2026-08-02T01:11:06.056874Z","title":"2018 , doi =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.056874Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:620a36dc91adef8a77f062e51fadca85e4f3892e58bf5174e1041c514a47578e","observation_id":"0b5eb6bc-77b7-436b-8705-cfdaa9e63913","resolution":{"observed_at":"2026-08-02T01:11:06.056874Z","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":"2026-08-02T01:11:06.058818Z","title":", journal =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.058818Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d910cf8d0d6aa99d11b9db0fd78a500afce6e268a7861ccddcd92c0284e036c6","observation_id":"a4a78ec9-08f8-417f-872d-9efd2600da15","resolution":{"observed_at":"2026-08-02T01:11:06.058818Z","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":"2026-08-02T01:11:06.060654Z","title":"2015 , doi =","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.060654Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:e8639d6e510b97f78dcb8a0c2df38d87aced46871a848770b74de634563ca832","observation_id":"327d5b19-1375-4d66-899c-5df20f40f704","resolution":{"observed_at":"2026-08-02T01:11:06.060654Z","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":"2026-08-02T01:11:06.062521Z","title":", journal =","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.062521Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:0e0d888a3f7be82ba2e690f55bded0c0339cf7c3ad08ecc906e3acdba9c5f3d4","observation_id":"bdab8204-a6f8-4557-b229-e1995c079367","resolution":{"observed_at":"2026-08-02T01:11:06.062521Z","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":"2026-08-02T01:11:06.064459Z","title":"2016 , doi =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.064459Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:cdc884d7edf54cb038f616e249b0e9bc36cc60c4f3e712718f0c37f6da763996","observation_id":"ae3ed9bb-3cf4-4094-bd18-12a4ecc7b02c","resolution":{"observed_at":"2026-08-02T01:11:06.064459Z","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":"2026-08-02T01:11:06.066763Z","title":"2022 , url =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.066763Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:918587e3667e77b5dc1e3e8baaa6d2f3e26bb9746ae06b02227d478082871605","observation_id":"aecd2d86-bf1d-4e84-969d-b101a11d1d6f","resolution":{"observed_at":"2026-08-02T01:11:06.066763Z","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":"2026-08-02T01:11:06.068778Z","title":"2018 , doi =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.068778Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d9747dffd08805edfbec1e931c2ba6bd3639780323723deb2101e1a791994b39","observation_id":"59a2ad7d-13d8-4a53-bf1d-dac91f1f5ff3","resolution":{"observed_at":"2026-08-02T01:11:06.068778Z","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":"2026-08-02T01:11:06.070608Z","title":"2021 , doi =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.070608Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:af2e8428f47e659e4b30f806e76722651063ba11c59be59eb0833d3465726ab4","observation_id":"8b8e08b4-0ffa-44ad-8eac-4f8415b7ec2f","resolution":{"observed_at":"2026-08-02T01:11:06.070608Z","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":"2026-08-02T01:11:06.072842Z","title":"2024 , doi =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.072842Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:65ccaff890f6bb0a1fa3de6d77fe0aaccf95ca81f2a8f60b21ece369a4b8a349","observation_id":"6b434da4-2ea4-4d1b-a36d-86aa3543cd39","resolution":{"observed_at":"2026-08-02T01:11:06.072842Z","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":"2026-08-02T01:11:06.075162Z","title":"2020 , doi =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.075162Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:f6e9b7d47b15b5a380129282c12c9abc83c17ad438a9bed924773f7bb63e1989","observation_id":"f844379d-9524-460c-80bb-69315d5c4838","resolution":{"observed_at":"2026-08-02T01:11:06.075162Z","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":"2026-08-02T01:11:06.077141Z","title":"2024 , doi =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.077141Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:b73de4d9c21089258ffc0344c2b1ee435d3377453d727e3b7f4edf2ad548b833","observation_id":"c9fa3e63-1f58-4ebb-b14e-c2f1d42e823e","resolution":{"observed_at":"2026-08-02T01:11:06.077141Z","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":"2026-08-02T01:11:06.079147Z","title":"2025 , doi =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.079147Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:487d0e7d8cdd1a188ce3b5769f029954f4c39e78718a89e004379daf41e8f4ac","observation_id":"dcf0eaa3-6177-454f-ac71-7bbb8c42a3ab","resolution":{"observed_at":"2026-08-02T01:11:06.079147Z","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":"2026-08-02T01:11:06.081068Z","title":"Statistica Sinica , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.081068Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:956abbeca499818a9c38c17be62a085122d4b5587ecd1a35e328af6bdf8ca8f0","observation_id":"b96ed856-aaac-4545-bf51-a91fdd78f867","resolution":{"observed_at":"2026-08-02T01:11:06.081068Z","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":"2026-08-02T01:11:06.082999Z","title":"International Journal of Forecasting , volume=","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.082999Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:eac20d65334d64c431d7e15a7869a36245fd58f8969693632606fc12a76000df","observation_id":"fc7055ed-0b41-4fa1-9d83-5c14a2127046","resolution":{"observed_at":"2026-08-02T01:11:06.082999Z","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":"2026-08-02T01:11:06.085254Z","title":"Oxford Bulletin of Economics and Statistics , volume=","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.085254Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:83ccc81688a417298ff99d12e35bf820087a496dbb58a2e3267c03e51bda6c07","observation_id":"23e93820-8a27-4594-8b59-edbd82ae7ad4","resolution":{"observed_at":"2026-08-02T01:11:06.085254Z","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":"2026-08-02T01:11:06.087338Z","title":"Journal of Forecasting , volume=","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.087338Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:df700d11ecddb1474c92d1e93e0c4c64e8e35f3089504e7862f0b3b83e4bf582","observation_id":"e8b5a482-5a3b-4614-b596-0117e3f13872","resolution":{"observed_at":"2026-08-02T01:11:06.087338Z","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":"2026-08-02T01:11:06.089271Z","title":"Electronic Journal of Statistics , volume=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.089271Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:c84fb9b82a870a84989981741b510f0e43eafb82d0654c6aea704f920e7afb2c","observation_id":"923b05b6-84e5-4d0b-808d-ec7fdf815454","resolution":{"observed_at":"2026-08-02T01:11:06.089271Z","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":"2026-08-02T01:11:06.091297Z","title":", journal =","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.091297Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:c4a88ae6c334e521ae9aeedbc1d7566fb9ff8ba35a87b9e1cfc9c2d6d3f51867","observation_id":"49b35e46-283d-43b2-a034-2f468b0e50ce","resolution":{"observed_at":"2026-08-02T01:11:06.091297Z","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":"2026-08-02T01:11:06.093137Z","title":"2024 , url =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.093137Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:981e0116895633fb684a458350b323128efda8638476eb64cb7378dfa6035872","observation_id":"c2710248-44da-4caf-9422-e68338931d65","resolution":{"observed_at":"2026-08-02T01:11:06.093137Z","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":"2026-08-02T01:11:06.095318Z","title":"and Kim, Tae Bong and Seoane, Hernán D","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.095318Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:9d8abb90f3a7c2a1128f8508ed6a7f220805bae9d813d4dd8ceb1fc5e1a4be25","observation_id":"cfd7f313-7b0a-4233-b427-6905c2d41fc2","resolution":{"observed_at":"2026-08-02T01:11:06.095318Z","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":"2026-08-02T01:11:06.097224Z","title":"and Marcellino, Massimiliano , journal =","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.097224Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:2b9f61dde37d6015af0217ed25cfb09dc8c8af9b3ad2fe886bef1a26e3c1b8f7","observation_id":"a9503dab-02e8-4836-8c67-102d8a1cab76","resolution":{"observed_at":"2026-08-02T01:11:06.097224Z","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":"2026-08-02T01:11:06.099130Z","title":"2016 , doi =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.099130Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d312860a09a57e992accad1800d91269c4ecd053f1a8d4967cea564e09f93737","observation_id":"6b01f17b-e1bf-47a2-922f-77751d65745d","resolution":{"observed_at":"2026-08-02T01:11:06.099130Z","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":"2026-08-02T01:11:06.101034Z","title":"2021 , url =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.101034Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:20e6e2d45cbc56faeb0b9da53a6403ee12d01d518142f599f3e746337d91bbcb","observation_id":"c7f6e4b3-30e5-4bbb-babc-c452163ccde8","resolution":{"observed_at":"2026-08-02T01:11:06.101034Z","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":"2026-08-02T01:11:06.102996Z","title":"and Murasawa, Yasutomo , journal =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.102996Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:cb708fd4b94eb5d4f56ede1f2eb8266ada3f6baa3883aa807004b1e6ba8bda00","observation_id":"64696440-4bfa-4127-aece-f4b2784efe9e","resolution":{"observed_at":"2026-08-02T01:11:06.102996Z","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":"2026-08-02T01:11:06.105792Z","title":"2007 , doi =","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.105792Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:697e6a77f890a84fe25074ddd2dc889f4ef5f2560477717b0bbf84893a0a376a","observation_id":"f289186d-f4b6-4350-b843-383476120f36","resolution":{"observed_at":"2026-08-02T01:11:06.105792Z","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":"2026-08-02T01:11:06.107776Z","title":"2008 , doi =","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.107776Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:ffdce8d91cff8f17e5e2970aa4238105f93cefbad560a5bd8290a34c521d2482","observation_id":"9cbc0aa8-c445-4e35-924b-d48e5bc650be","resolution":{"observed_at":"2026-08-02T01:11:06.107776Z","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":"2026-08-02T01:11:06.109831Z","title":"European Central Bank , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.109831Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:11ffa83b8653f8e071007ae09bc7e6ad3af5247f3429e1d1c4810fad8da296df","observation_id":"60ecf5c8-6975-4135-ac40-7a99d7cb455c","resolution":{"observed_at":"2026-08-02T01:11:06.109831Z","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":"2026-08-02T01:11:06.112052Z","title":"2022 , doi =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.112052Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:9b2c5912d6dcb49e11fcb32d31cbddcb407f493a689c1aa47bebc1b33a2b7111","observation_id":"698c33df-c9b9-4512-afac-7e17599b0f22","resolution":{"observed_at":"2026-08-02T01:11:06.112052Z","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":"2026-08-02T01:11:06.114239Z","title":"2016 , doi =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.114239Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:e1ae1bbdda115da3a824945b489f66548fc50100d544801aed0dffb12d945332","observation_id":"ada0fcc6-c58a-4bbb-9569-ce573906d684","resolution":{"observed_at":"2026-08-02T01:11:06.114239Z","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":"2026-08-02T01:11:06.116216Z","title":", month =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.116216Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:4dee568a9858c362b77df3d1e135d49700a136de4f63a0af4b8c4d1b2e345169","observation_id":"3591add2-a03d-4cdf-8e5e-0f9b82673d69","resolution":{"observed_at":"2026-08-02T01:11:06.116216Z","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":"2026-08-02T01:11:06.118214Z","title":"2024 , doi =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.118214Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:88066ccf6e4f19c4786b78a0e040c44ff08c4069924fdb374ea7a5afa88eaa56","observation_id":"4cdebf9c-8f4d-46a5-b0d7-27f2e3c29854","resolution":{"observed_at":"2026-08-02T01:11:06.118214Z","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":"2026-08-02T01:11:06.120109Z","title":"2020 , doi =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.120109Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:367c9052b8b28cde003ece264fe459f1e981e6ea607d84dbdbd281aceaad1435","observation_id":"8586fb37-d10b-4bdc-8cfe-efafff9abccc","resolution":{"observed_at":"2026-08-02T01:11:06.120109Z","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":"2026-08-02T01:11:06.122203Z","title":"2021 , doi =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.122203Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:e2b7a81892159e11cc4b4ca1830b6a995ea915aa1d57aede250bedb060293300","observation_id":"022e27c0-752d-439e-919f-4e6393106f4d","resolution":{"observed_at":"2026-08-02T01:11:06.122203Z","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":"2026-08-02T01:11:06.124096Z","title":"2021 , doi =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.124096Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:19e0b8aabfe07e0eb4175c3830e825d4933d1cdacb5a79cae715ee2f58176934","observation_id":"de82f542-ec59-42fa-ab0c-8814e02600c4","resolution":{"observed_at":"2026-08-02T01:11:06.124096Z","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":"2026-08-02T01:11:06.126453Z","title":"2021 , doi =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.126453Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:22bbb0e3399f0d2ea5e082219ed8709d56395816c22d6b7b4a51c26636dc684e","observation_id":"4b87c06b-0fe6-457a-a47b-1fa0c90c3e9e","resolution":{"observed_at":"2026-08-02T01:11:06.126453Z","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":"2026-08-02T01:11:06.128653Z","title":"2022 , url =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.128653Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:b14961c1163b2aac1226e58c678edf73d4a74cf6ab5cb851f2c565fa7463c528","observation_id":"e197d23f-85ce-4121-bf28-5c312bed7980","resolution":{"observed_at":"2026-08-02T01:11:06.128653Z","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":"2026-08-02T01:11:06.131105Z","title":"and Liang, Tengyuan and Misra, Sanjog , journal =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.131105Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:b09f67cfad670fd464f271a03f13295da1af1f363477f8f0e0111a0ebef96200","observation_id":"c12e7ad5-fff9-4fcc-8a93-dae477301685","resolution":{"observed_at":"2026-08-02T01:11:06.131105Z","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":"2026-08-02T01:11:06.133137Z","title":"2018 , url =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.133137Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:8a647952c7cbc95bbaf0af8a3672bcf081f73148cdacb9c1d4e6390c09fbee2f","observation_id":"602599be-509f-4e34-8893-17d22d57a77b","resolution":{"observed_at":"2026-08-02T01:11:06.133137Z","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":"2026-08-02T01:11:06.135164Z","title":"2019 , doi =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.135164Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d3bb13de15064dd0a14a9fddb1234004ca2264e69b7a3015558deda48091ebc3","observation_id":"da55290f-c057-427c-ac13-0e4cf4398917","resolution":{"observed_at":"2026-08-02T01:11:06.135164Z","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":"2026-08-02T01:11:06.137345Z","title":"2025 , url =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.137345Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:aade6b475f39c3ff22a7595ee3431cad2eb41adf11af3e340cb358fa665a2b4d","observation_id":"fb5782c7-bdeb-4809-9198-c1933db71407","resolution":{"observed_at":"2026-08-02T01:11:06.137345Z","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":"2026-08-02T01:11:06.139416Z","title":"2002 , doi =","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.139416Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:5a1428a9a615028fe0b733d155c30f014837b4aa0492e0e888e37027539863a8","observation_id":"44564a0c-bd97-4b4e-8c02-6e92c879b59b","resolution":{"observed_at":"2026-08-02T01:11:06.139416Z","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":"2026-08-02T01:11:06.141441Z","title":"Nature , volume=","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.141441Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:6e039ca94d11f0341b66e4ae2d6f1e2012ce308ad050a3d1ccc971a9d700da8a","observation_id":"5e5b2cbd-9eb2-4aa8-8cc0-7e2e66a0ebfd","resolution":{"observed_at":"2026-08-02T01:11:06.141441Z","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":"2026-08-02T01:11:06.143466Z","title":"Neural Computation , volume=","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.143466Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:00a79c2d20136a1a625b87634f41e58c69a9896303886c28fa9c4499c0c76614","observation_id":"a3df6f97-f4a8-4a0a-ae23-377fe339273a","resolution":{"observed_at":"2026-08-02T01:11:06.143466Z","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":"2026-08-02T01:11:06.145504Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.145504Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:1d1ea96b4f20a924970c82a5fb6cc6daafd019981b423c4719da07c809af3922","observation_id":"bf9e9764-272d-497a-85c3-8de433aea9a2","resolution":{"observed_at":"2026-08-02T01:11:06.145504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-07-06T03:45:28.546418Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-02T01:11:06.147871Z","title":"arXiv preprint arXiv:1406.1078 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.147871Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:2ad33a61c459556aa445cd2d833cf6db43e82996129a697a009c598256676c60","observation_id":"e72948f5-950e-4b41-88b8-d53a6c441148","resolution":{"observed_at":"2026-08-02T01:11:06.147871Z","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":"2026-08-02T01:11:06.150484Z","title":"2014 , url =","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.150484Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d87a9c018204ce51d264b4c7d1d4963662a0b9d7f52cd5015d9c8b45631a599f","observation_id":"79bdefcb-4961-499c-8087-2d1ad0fccc18","resolution":{"observed_at":"2026-08-02T01:11:06.150484Z","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":"2026-08-02T01:11:06.152744Z","title":"2016 , doi =","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.152744Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:7922b93a9760f65ef88268bf49b2df1e6bded1175d7c23aad5bbd6a29ec9bae3","observation_id":"b1a3b952-b99c-4647-aa21-4a368aef3e08","resolution":{"observed_at":"2026-08-02T01:11:06.152744Z","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":"2026-08-02T01:11:06.154600Z","title":"2023 , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.154600Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:9ac599fd86188379830ca10fa2e5c78b941effa158ba572e21b0aa109be7048d","observation_id":"f62e6368-645e-4193-a1ba-222c6a8ec28b","resolution":{"observed_at":"2026-08-02T01:11:06.154600Z","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":"2026-08-02T01:11:06.156538Z","title":"2015 , doi =","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.156538Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:c74eb28cb74970ac459ce727a49550efd28fb83d7c425d58bccdf41926ff4e30","observation_id":"d456f72e-d641-4751-8842-61d8c45031d8","resolution":{"observed_at":"2026-08-02T01:11:06.156538Z","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":"2026-08-02T01:11:06.158459Z","title":"2019 , doi =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.158459Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:80e2cb89a71f8233942a113ce7ece3c270f16627badcaf5e5005c16b7dc98d21","observation_id":"63fe11d7-5e59-4ed4-8d0d-a025ae7872a6","resolution":{"observed_at":"2026-08-02T01:11:06.158459Z","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":"2026-08-02T01:11:06.160405Z","title":"2024 , doi =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.160405Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:a6676b1f73774ebc1484b76f86a695d2ea29cbbe7cf6bb55c5c6ff66d5704e11","observation_id":"78fd82a6-bc7c-4837-9416-497ceb2b8a79","resolution":{"observed_at":"2026-08-02T01:11:06.160405Z","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":"2026-08-02T01:11:06.162495Z","title":"Lecture notes in electrical engineering , month =","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.162495Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:9185c1b2050090ebcd1403bf3d28a9bc593350baafd4e18a3c4c19172fe3418f","observation_id":"0e366500-4e0d-42fb-b099-20ddef7ffa81","resolution":{"observed_at":"2026-08-02T01:11:06.162495Z","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":"2026-08-02T01:11:06.164426Z","title":"José and Louhichi, Sana and Prieur, Clémentine , month =","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.164426Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:ab9abb4f5bbb5fcc3ee6d3d552234e8c3cea0af2a85b663475de8980aa7208ff","observation_id":"1292eca3-acc4-4e79-b10c-5f7bd5886bdd","resolution":{"observed_at":"2026-08-02T01:11:06.164426Z","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":"2026-08-02T01:11:06.166585Z","title":"2024 , url =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.166585Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:b12afad80673c679496d523c8a11ebd5d4f64afaa3a3c232082898edb7a6ac61","observation_id":"2d78ced8-f41b-44ca-a040-a9a6b169d94b","resolution":{"observed_at":"2026-08-02T01:11:06.166585Z","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":"2026-08-02T01:11:06.168610Z","title":"2019 , publisher=","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.168610Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:4bfa757604683f36011bb12ea460009b60dc4344054fa854484d6bd6adf468fc","observation_id":"c8901b9c-2429-4e55-8e96-4e5f2a854340","resolution":{"observed_at":"2026-08-02T01:11:06.168610Z","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":"2026-08-02T01:11:06.170587Z","title":"2019 , url =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.170587Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:a32a35d8333cd1db04b8ac58d584caacb64bf57d37a0fc5d7f1f421c6e62ab4b","observation_id":"7dfae34f-9df0-49a9-87be-35781daa50ce","resolution":{"observed_at":"2026-08-02T01:11:06.170587Z","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":"2026-08-02T01:11:06.173073Z","title":"and Harvey, Nick and Liaw, Christopher and Mehrabian, Abbas , journal =","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.173073Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:f11c143db6d7434937090fa6b3c38115d90ecbb3dd27ac346354cdf716b3ac67","observation_id":"43fb6703-b3de-4b0c-b84d-1a09424d6812","resolution":{"observed_at":"2026-08-02T01:11:06.173073Z","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":"2026-08-02T01:11:06.174974Z","title":"IEEE Transactions on Information Theory , volume=","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.174974Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:2121494a5cb895c0adf6f500865509226c7d387d21b33ae289e9bb4e07651123","observation_id":"e45c8db8-27c9-460d-989e-3922873a28c9","resolution":{"observed_at":"2026-08-02T01:11:06.174974Z","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":"2026-08-02T01:11:06.176909Z","title":"2023 , url =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.176909Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:d7f84bd35d4a91a8050983f7e399fec22e4e10a9f2d4ae1752e5fafeabb772c8","observation_id":"d64d5a8e-5428-4468-8f77-1973da14140c","resolution":{"observed_at":"2026-08-02T01:11:06.176909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1211.1847","last_updated":"2012-11-08T13:39:25Z","snapshot_observed_at":"2026-07-06T02:59:26.086131Z","submitted_at":"2012-11-08T13:39:25Z","title":"Prediction of time series by statistical learning: general losses and fast rates","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1211.1847","snapshot_observed_at":"2026-08-02T01:11:06.178802Z","title":"arXiv preprint arXiv:1211.1847 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.178802Z"},"links":{"cited_paper":"/paper/1211.1847","citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:ed8dae40d9c47d3039aea0ccaaf53cb7984fa636b085a583f64154300e711919","observation_id":"887be60d-5b5c-4ca4-8861-a29e0d7e74ec","resolution":{"observed_at":"2026-08-02T01:11:06.178802Z","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":"2026-08-02T01:11:06.181249Z","title":"Journal of Machine Learning Research , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.181249Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:df9ce8e343a9f3fcd2401354bece2fd1da90ef76359cae74d0301035bc338c59","observation_id":"0d1028b9-0f37-4fb6-b13c-ff3c2b70bb83","resolution":{"observed_at":"2026-08-02T01:11:06.181249Z","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":"2026-08-02T01:11:06.183433Z","title":"2024 , url =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.183433Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:632895a9c2eaae0e1464ce8bde1b139123404f85e623d1b37704a032926a3351","observation_id":"87199c42-a6f2-4388-86d7-80325805a8dc","resolution":{"observed_at":"2026-08-02T01:11:06.183433Z","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":"2026-08-02T01:11:06.185422Z","title":"Pattern Recognition , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.185422Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:4ec2cecc7b2188575147c94784b3d15f8b7d208bef069bcd9b73183a67aa6e5c","observation_id":"bcec4929-bcd6-403c-8916-0b83e79f25f8","resolution":{"observed_at":"2026-08-02T01:11:06.185422Z","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":"2026-08-02T01:11:06.187388Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.187388Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:c5de38e8af6c0a49156e5a943d75b83db74c46a95edade1dfd47d80f44587951","observation_id":"18742b05-481e-4045-8da4-bb3d807dfa39","resolution":{"observed_at":"2026-08-02T01:11:06.187388Z","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":"2026-08-02T01:11:06.189711Z","title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.189711Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:a9a7bac900c48d56017350893a9914c04e1fffa5b20985deb0787b67f3d6b832","observation_id":"c2ab03ad-7394-4925-9168-4a1090e13ee4","resolution":{"observed_at":"2026-08-02T01:11:06.189711Z","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":"2026-08-02T01:11:06.191956Z","title":"arXiv preprint arXiv:2503.11835 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.191956Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:55b9b52be57f086e7ea5a39d358236a0f22474e5c0d83e3c35142833acb19911","observation_id":"d030b526-855b-4ac2-b139-8eb9b6f0cb4a","resolution":{"observed_at":"2026-08-02T01:11:06.191956Z","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":"2026-08-02T01:11:06.193874Z","title":"Proceedings of the IEEE conference on computer vision and pattern recognition , pages=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.193874Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:75393837befc878e035a8726c9139ea53b9083c677789e005a359cd0ca564951","observation_id":"8a98bf34-b513-449d-aaec-56eea848db5d","resolution":{"observed_at":"2026-08-02T01:11:06.193874Z","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":"2026-08-02T01:11:06.195977Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence, 34:6145--6152 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-02T01:11:06.195977Z"},"links":{"citing_paper":"/paper/2607.14771"},"observation_digest":"sha256:6538d5b1544f47cc310a9e124e97183efa76ff17c6708bc959e0428484cab9e2","observation_id":"82b38f1e-1718-4015-8bb4-79f65baedb9b","resolution":{"observed_at":"2026-08-02T01:11:06.195977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14771","last_updated":"2026-07-16T09:53:41Z","latest_version":1,"primary_category":"stat.ME","snapshot_observed_at":"2026-08-03T11:00:41.412888Z","submitted_at":"2026-07-16T09:53:41Z","title":"Mixed-Frequency Time Series Forecasting via Depth-Separable Neural Networks"},"reference_resolution":{"displayed":85,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":85,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":85},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 0 inbound Pith citation observations for arXiv:2607.14771."}