{"as_of":"2026-08-08T07:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1230c8f264b0e7554010ad0d0a7c224173f29f2cd668edfee1d83d85daa843e","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:26:16.724559Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T16:27:45.767100Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T16:35:12.732159Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"cited_work":{"arxiv_id":"2506.05515","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05515","snapshot_observed_at":"2026-06-30T16:35:12.732159Z","title":"arXiv preprint arXiv:2506.05515 , year=","venue":null,"work_id":"4c41fb59-1508-4092-bae9-99cbc8181bf9","year":2025},"citing_paper":{"arxiv_id":"2509.25914","last_updated":"2026-05-14T06:25:26Z","snapshot_observed_at":"2026-08-04T06:16:10.775788Z","submitted_at":"2025-09-30T08:05:59Z","title":"ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters","version":6},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T13:03:25.032299Z"},"links":{"cited_paper":"/paper/2506.05515","citing_paper":"/paper/2509.25914"},"observation_digest":"sha256:be613f38e2befc9e28b0d4ec139d374f5c6f2e76c48ad1f00e6a7f3a9fafcda2","observation_id":"5aae305a-1816-444c-b026-2862800ef945","resolution":{"observed_at":"2026-05-18T13:06:23.910170Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"cited_work":{"arxiv_id":"2506.05515","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05515","snapshot_observed_at":"2026-06-30T16:35:12.732159Z","title":"arXiv preprint arXiv:2506.05515 , year=","venue":null,"work_id":"4c41fb59-1508-4092-bae9-99cbc8181bf9","year":2025},"citing_paper":{"arxiv_id":"2605.23402","last_updated":"2026-05-22T09:13:29Z","snapshot_observed_at":"2026-07-06T23:33:39.204744Z","submitted_at":"2026-05-22T09:13:29Z","title":"Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-25T05:09:06.410581Z"},"links":{"cited_paper":"/paper/2506.05515","citing_paper":"/paper/2605.23402"},"observation_digest":"sha256:43ad977093837c154eb8a1bc5c1d74ae4e1fce690420a14386b56beb6854b3ef","observation_id":"056bc1e7-bb0b-45b4-a607-31297e1bc102","resolution":{"observed_at":"2026-05-25T05:10:21.972854Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"cited_work":{"arxiv_id":"2506.05515","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05515","snapshot_observed_at":"2026-06-30T16:35:12.732159Z","title":"arXiv preprint arXiv:2506.05515 , year=","venue":null,"work_id":"4c41fb59-1508-4092-bae9-99cbc8181bf9","year":2025},"citing_paper":{"arxiv_id":"2605.28867","last_updated":"2026-05-22T07:10:20Z","snapshot_observed_at":"2026-08-04T16:22:45.174745Z","submitted_at":"2026-05-22T07:10:20Z","title":"PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-30T16:27:45.767100Z"},"links":{"cited_paper":"/paper/2506.05515","citing_paper":"/paper/2605.28867"},"observation_digest":"sha256:8249efba5627cdac4866dabc539cf7710a9bbb5fc1a383a2f8a5e971cfb41716","observation_id":"e35492e8-6739-46bd-a772-4d22274a63d0","resolution":{"observed_at":"2026-06-30T16:35:12.733607Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.05515/citation-record","integrity":"/paper/2506.05515/integrity","json":"/paper/2506.05515/citation-record.json","paper":"/paper/2506.05515"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.980537Z","title":null,"venue":null,"work_id":"d710d4de-4d7d-4b04-b3c4-f4d92523d309","year":2018},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.885941Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:6021e9f2472caadf88175a0d092b7943101c0a0bd44a75dd4df494e8f08a87a2","observation_id":"29ac5364-c82e-4591-8c9d-71916030f04e","resolution":{"observed_at":"2026-08-07T10:26:18.984782Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:17.964249Z","title":null,"venue":null,"work_id":"469a2db6-5dcb-48bf-9e8a-4dffa37c6964","year":2023},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.629706Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:f1b9974eec1e9a597552564e77ef2ad03d374719f5935c7bca779b8a2c6dbb9e","observation_id":"2392e214-d797-4818-b5a6-670658596b65","resolution":{"observed_at":"2026-08-07T10:26:18.050293Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.500753Z","title":"ETS, Trf.TempFlow and Tactis2, columns are in gray because they don’t share the same backbone as the other baselines","venue":null,"work_id":"f91d5193-ac8d-4f7f-a76b-a90d5b0ef41a","year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.244508Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:06488a0bc4737a7e279f27dcef18063967ffbfe27c2a2c87c175a2eb0d571af7","observation_id":"2b22b066-d006-480b-a940-359035a29f59","resolution":{"observed_at":"2026-08-07T10:26:18.624780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.142187Z","title":"In this table, the distortion is computed with a variable number of hypothesesKfor each baseline, as in Table 4 of the main paper","venue":null,"work_id":"8676ed2c-356e-4a31-80a1-60c2ec7cbaca","year":2024},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.515208Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:42ec5f5dd261b30b1ceaa4bb9d598f500c99079fe51a4f60245f59719436c742","observation_id":"75b78a53-b4c6-4989-8ecd-142a7654e594","resolution":{"observed_at":"2026-08-07T10:26:18.213116Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.965905Z","title":"These series generally display recurrent rush-hour peaks as well as differences between weekdays and weekends","venue":null,"work_id":"6a5a501e-6451-4141-a71f-f4b839b0bda9","year":2015},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.985694Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:e572ac370d3087003f0048ad50d7ebcf27c509da738f36592e9c5a3dc67e3705","observation_id":"23a0659b-05df-41d0-84c4-78e3adb82549","resolution":{"observed_at":"2026-08-07T10:26:18.970535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1047.49812","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:16.940392Z","title":"Here, TimeMCL follows the same experimental setup as in the previous benchmark, except that we used Z-Score normalization (instead of mean scaling) during training","venue":null,"work_id":"bb7ce5fd-131e-460e-a48f-219beef37bf5","year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.583538Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:ed84dd59877a63cd403dcd1494e80f8dd68f56db91e3a96426334b56c31cc318","observation_id":"a397e219-41ce-4875-80a6-c8b20bcc0545","resolution":{"observed_at":"2026-08-07T10:26:17.051466Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.308022Z","title":"Inference.We used the official experimental protocol for evaluation in this benchmark (e.g.,(Rasul et al., 2021a))","venue":null,"work_id":"0f3cefb1-cf95-47fd-ac65-cdea4bde676b","year":2021},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.414967Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:67b4b0d41abfe0cd93ba87e53a2619a1c6de4430f034f462010fa08a0bf497be","observation_id":"f0c5781a-f612-49c1-9ce0-eee22ab39b8a","resolution":{"observed_at":"2026-08-07T10:26:18.412653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:17.814599Z","title":"We observe thatTimeMCL produces smoother predictions compared to other methods and effectively captures different modes in the conditional distribution","venue":null,"work_id":"dbb6b529-7e42-4a4b-b226-36c8c48169bf","year":2025},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.724559Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:b4469e74c0c8c87a10a86cfa1c85acc1c87f601acf02b27f401033156b4e7432","observation_id":"e821046b-aea0-4732-a947-aedbf4733e0d","resolution":{"observed_at":"2026-08-07T10:26:17.869413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1050.0235","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:17.247827Z","title":null,"venue":null,"work_id":"9839a099-836b-41af-a285-99c09490381e","year":2021},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.334981Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:bfdd9544122bf3b1041d6c971f485e49df38ffb074e6cc2da7cd95b7c589317b","observation_id":"9aa28ab2-11cd-40ce-97f6-771ba723fefe","resolution":{"observed_at":"2026-08-07T10:26:17.297167Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.941714Z","title":null,"venue":null,"work_id":"3851438e-09a7-4606-a476-fa59e2d5afa3","year":2019},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":1976,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.076046Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:4011b238dae3c08dbc11929a6637464cd88c3ffcd34d72edc845b9845916d4b3","observation_id":"d1b9560b-83be-4a42-a61e-871fd52a885f","resolution":{"observed_at":"2026-08-07T10:26:18.954025Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:19.013310Z","title":"Appendix A contains the proofs of the theoretical results, establishing that TimeMCL can be interpreted as a functional quantizer","venue":null,"work_id":"cf8fa7b5-b74f-4630-a980-4f35eef7e4a6","year":2024},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":1982,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.661435Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:d9b09b53602b2329e164371a89a9b68d27e7ec239b0236a6bfacd4f1ffe17fcd","observation_id":"d0aad034-de61-4b90-9979-65dddb916c3c","resolution":{"observed_at":"2026-08-07T10:26:19.019692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.03499","last_updated":"2016-09-19T18:04:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-09-12T17:29:40Z","title":"WaveNet: A Generative Model for Raw Audio","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.03499","snapshot_observed_at":"2026-08-07T10:26:15.614683Z","title":"Wavenet: A generative model for raw audio.arXiv preprint arXiv:1609.03499,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2005,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.614683Z"},"links":{"cited_paper":"/paper/1609.03499","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:c526e8e700a485a24d13e7f3d914b4725966ab78f91a3b5644f089ec62380f1a","observation_id":"859c22ac-99a8-47f0-a808-49434e87a16f","resolution":{"observed_at":"2026-08-07T10:26:15.614683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10240","last_updated":"2022-06-15T20:16:03Z","snapshot_observed_at":"2026-07-06T09:14:10.074582Z","submitted_at":"2020-04-21T18:53:42Z","title":"Deep Learning for Time Series Forecasting: Tutorial and Literature Survey","version":2},"cited_work":{"arxiv_id":"2004.10240","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.10240","snapshot_observed_at":"2026-08-07T10:26:17.600112Z","title":"Deep Learning for Time Series Forecasting: Tutorial and Literature Survey","venue":"cs.LG","work_id":"dab3a380-46f4-413a-95b2-99f7fddec852","year":2020},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.169687Z"},"links":{"cited_paper":"/paper/2004.10240","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:d74dabb4e23553beb7e24148c6150bd33f8b20decc0cdb1dd8fb7594349290e9","observation_id":"17cb7ebb-6195-4579-ae8b-42637caf965b","resolution":{"observed_at":"2026-08-07T10:26:17.665874Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-07-06T05:01:27.910364Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-07T10:26:15.528426Z","title":"and Gimpel, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.528426Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:92095f34b9c57e01ca532f0b74afc8fb6ae68e77b537ac85749b969f07222d20","observation_id":"e7ce6dc0-ba67-4a09-9ec7-fff44ec9c5aa","resolution":{"observed_at":"2026-08-07T10:26:15.528426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1009.1241","last_updated":"2010-09-07T09:42:51Z","snapshot_observed_at":"2026-07-06T02:15:04.001544Z","submitted_at":"2010-09-07T09:42:51Z","title":"The Nystr\\\"om method for functional quantization with an application to the fractional Brownian motion","version":1},"cited_work":{"arxiv_id":"1009.1241","doi":null,"metadata_source":"pith","pith_arxiv_id":"1009.1241","snapshot_observed_at":"2026-08-07T10:26:17.458845Z","title":"The Nystr\\\"om method for functional quantization with an application to the fractional Brownian motion","venue":"math.PR","work_id":"fa543979-eb0c-4810-9070-e5b92d5e0872","year":2010},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.370684Z"},"links":{"cited_paper":"/paper/1009.1241","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:58390b275347f3aafa1e5aea9d29b87b8830b7c8342499a5aa5e5ae11b2d1c05","observation_id":"dfcac169-d09d-472e-85e6-01e5c0bf56e4","resolution":{"observed_at":"2026-08-07T10:26:17.504349Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.995713Z","title":null,"venue":null,"work_id":"f234cc66-fb5a-4699-b231-3cab32caefb1","year":2009},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.783774Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:bd934304d3a26972a975128fd23b952b62c40d011e61c908e9f8990f87183621","observation_id":"1f201c24-5a06-4c5d-a0a7-aead95f03395","resolution":{"observed_at":"2026-08-07T10:26:19.001378Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3555","last_updated":"2014-12-11T06:46:53Z","snapshot_observed_at":"2026-08-03T11:40:51.182181Z","submitted_at":"2014-12-11T06:46:53Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3555","snapshot_observed_at":"2026-08-07T10:26:15.266633Z","title":"Empirical evaluation of gated recurrent neural networks on sequence modeling.arXiv preprint arXiv:1412.3555,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.266633Z"},"links":{"cited_paper":"/paper/1412.3555","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:afa16399b899c80c9029af680002c088c73d14ea52bf5c764cf23efb6f86b685","observation_id":"84661d3e-f5f8-41c8-8c5d-5ae643f3f9c9","resolution":{"observed_at":"2026-08-07T10:26:15.266633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1308.0850","last_updated":"2014-06-05T16:04:02Z","snapshot_observed_at":"2026-08-05T10:16:44.137827Z","submitted_at":"2013-08-04T21:04:36Z","title":"Generating Sequences With Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.0850","snapshot_observed_at":"2026-08-07T10:26:15.434691Z","title":"Generating sequences with recurrent neural networks.arXiv preprint arXiv:1308.0850,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:15.434691Z"},"links":{"cited_paper":"/paper/1308.0850","citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:cb8cf318d82bec765db5c09012db6ead5fa35524c15f7f65ed75ea783ccc1b6e","observation_id":"f30e7056-564e-4f09-b608-0069c2f8dd2c","resolution":{"observed_at":"2026-08-07T10:26:15.434691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:26:18.730633Z","title":null,"venue":null,"work_id":"ac17976f-7fab-4883-81e1-a3753f53e418","year":2009},"citing_paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T10:26:16.169666Z"},"links":{"citing_paper":"/paper/2506.05515"},"observation_digest":"sha256:385633738658f73473a7af69938b56317597825e66959c6e9ae874ea4551aa81","observation_id":"27d62e35-9cdf-4c55-b1ff-9e39548f80ab","resolution":{"observed_at":"2026-08-07T10:26:18.830421Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.05515","last_updated":"2025-08-11T12:57:52Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:17:38.520014Z","submitted_at":"2025-06-05T18:56:14Z","title":"Winner-takes-all for Multivariate Probabilistic Time Series Forecasting"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":5},"total_outbound_references":19},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 3 inbound Pith citation observations for arXiv:2506.05515."}