{"as_of":"2026-08-11T15:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5fcdd1d1956983253a0a3dfd2e9c2d46d74a004c9ef4fd5a21458a76405a7738","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T10:12:26.798895Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2608.07333/citation-record","integrity":"/paper/2608.07333/integrity","json":"/paper/2608.07333/citation-record.json","paper":"/paper/2608.07333"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:28.439065Z","title":"In: Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (2020)","venue":null,"work_id":"713a905d-f64d-4dca-a516-517531b9f169","year":2020},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.651666Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:6e9bd45bfa7acb57367829bd257442b024a96c5327f1bb722a1daa7eac00e255","observation_id":"4b17b9e3-57c4-40b0-8b86-094c9092c995","resolution":{"observed_at":"2026-08-10T10:12:28.442707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01271","last_updated":"2018-04-19T14:32:38Z","snapshot_observed_at":"2026-07-06T06:26:27.965096Z","submitted_at":"2018-03-04T00:20:29Z","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01271","snapshot_observed_at":"2026-08-10T10:12:26.656107Z","title":"ArXivabs/1803.01271(2018), https://api.semanticscholar.org/CorpusID:4747877","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.656107Z"},"links":{"cited_paper":"/paper/1803.01271","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:b26b7ab73fcade1b7b5f1be5eb25365857a0c3d543ddc9fbb7bcb17198d326ad","observation_id":"fc7f70fe-5acd-4270-88a1-e29142dce5ac","resolution":{"observed_at":"2026-08-10T10:12:26.656107Z","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":"2026-08-10T10:12:28.429530Z","title":"In: Advances in Social Networks Analysis and Mining 2013, ASONAM","venue":null,"work_id":"2220eb5f-e0e1-4565-b74a-55e21e5cad0f","year":2013},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.660279Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:d2eed638c5fe64baeeb67013759826c5ce886e9ba5ae43f6059def8b59d83506","observation_id":"bbbf93f5-f458-41c6-8338-d0734ea88a1f","resolution":{"observed_at":"2026-08-10T10:12:28.432867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.419465Z","title":"ACM Comput","venue":null,"work_id":"f4b73fe9-276f-4611-8367-5e2636ab9115","year":2018},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.664074Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:421e2b76bae6f0aaa5ba53b7b62d7f368d67f7504887e55b43edbc9b3dc0ef6f","observation_id":"64d717dd-b257-4d1a-8b88-91b5f9a57e50","resolution":{"observed_at":"2026-08-10T10:12:28.422715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13513","last_updated":"2023-07-09T11:55:29Z","snapshot_observed_at":"2026-07-06T13:56:54.255166Z","submitted_at":"2022-09-27T16:32:11Z","title":"DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning","version":3},"cited_work":{"arxiv_id":"2209.13513","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.13513","snapshot_observed_at":"2026-08-10T10:12:28.192648Z","title":"DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning","venue":"cs.LG","work_id":"16085eda-c3e8-4211-8961-c8d84c1e7d7e","year":2022},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.667738Z"},"links":{"cited_paper":"/paper/2209.13513","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:26f8727d05f2fad33af26c280e12421d83fe9c4870c2b2876bdaaebc274735c4","observation_id":"9d6a9cee-2a3a-4036-aeca-ba3c75927df7","resolution":{"observed_at":"2026-08-10T10:12:28.196936Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.07719","last_updated":"2021-03-13T13:44:20Z","snapshot_observed_at":"2026-07-06T10:49:36.487832Z","submitted_at":"2021-03-13T13:44:20Z","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","version":1},"cited_work":{"arxiv_id":"2103.07719","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.07719","snapshot_observed_at":"2026-08-10T10:12:28.177470Z","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","venue":"cs.LG","work_id":"b10bfd7f-7efe-4606-88c3-ddf42f1e00fb","year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.671925Z"},"links":{"cited_paper":"/paper/2103.07719","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:a304966dd67985cf632b5a3ae8b0ea33e67879db263f749a95603563cf341303","observation_id":"58651acc-8456-4421-9a53-d389101d3d29","resolution":{"observed_at":"2026-08-10T10:12:28.182445Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:28.163372Z","title":"In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada","venue":null,"work_id":"65066039-918e-462b-b24f-ad4fcbdac7a4","year":2017},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.676127Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:b09a71c8a19a1d793d2b69f974f9a4664896be0ae26177747cd6cea25c2711ae","observation_id":"3b253e5a-f950-452e-874d-807b8bbcd5d5","resolution":{"observed_at":"2026-08-10T10:12:28.166971Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.410054Z","title":"In: International Conference on Artificial Intelligence and Statistics, AISTATS","venue":null,"work_id":"c97ba07e-4cd4-4e6e-af33-f5addc2d1024","year":2025},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.679442Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:006d782283e0a34450ab2cc3f1d71981df3eeb048a1bae3e91e2021459beb20f","observation_id":"1483e263-9f87-461b-9358-b7121248f311","resolution":{"observed_at":"2026-08-10T10:12:28.413359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04451","last_updated":"2020-02-18T16:01:18Z","snapshot_observed_at":"2026-07-06T08:50:12.690900Z","submitted_at":"2020-01-13T18:38:28Z","title":"Reformer: The Efficient Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.04451","snapshot_observed_at":"2026-08-10T10:12:26.682641Z","title":"ArXiv abs/2001.04451(2020) Overcoming Temporal Correlation Volatility in GNNs 17","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.682641Z"},"links":{"cited_paper":"/paper/2001.04451","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:55d7f7115e9666927cb8917d8edeb083878a2efb9392b7521c613376a1527897","observation_id":"24381856-d13b-45a1-aad5-672ca822cd7f","resolution":{"observed_at":"2026-08-10T10:12:26.682641Z","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":"2026-08-10T10:12:26.686639Z","title":"The Annals of Applied Statistics4(1), 94–123 (2010)","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.686639Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:ffd2d14aad5fe5a9a263e302590896d39d351dd24663e2fbd581ed588eee82f7","observation_id":"a3739a8a-6e34-41a7-b021-e61d812dabd5","resolution":{"observed_at":"2026-08-10T10:12:26.686639Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-10T10:12:28.400085Z","title":"In: Proceedings of the 13th SIAM International Conference on Data Mining","venue":null,"work_id":"cb6e5421-6684-411f-b045-b2d6e651430b","year":2013},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.690152Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:2bb54f6d00d49939c73cfc458dbf6ffece095b55f803768ded7726dfd004b147","observation_id":"793565b1-a577-4a28-b259-dc8c9528a399","resolution":{"observed_at":"2026-08-10T10:12:28.403539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.389769Z","title":"The 41st International ACM SI- GIR Conference on Research & Development in Information Retrieval (2017), https://api.semanticscholar.org/CorpusID:4922476","venue":null,"work_id":"2d6572a7-9807-4ca6-8aa1-89a6534e4c58","year":2017},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.693703Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:150f7bcfecf06d66b2ec5d6ca5364fda2e519fade848a952247fadb39abd8c70","observation_id":"e48e3844-fac2-4646-87cf-fe7ef5ec1a0e","resolution":{"observed_at":"2026-08-10T10:12:28.393340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.379538Z","title":"ACM Transactions on Knowledge Discovery from Data17, 1 – 21 (2021)","venue":null,"work_id":"f1bde8b2-6712-424f-ab04-3a9a55fa8d5c","year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.696963Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:8bfc250edac44803615b1e8af3164bb54b859ff7faa14bcc5a8c00f46d4a8732","observation_id":"d90e1dcc-cfdf-476d-a5a8-f1d7a5cc21da","resolution":{"observed_at":"2026-08-10T10:12:28.383304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.368494Z","title":"In: International Conference on Learning Represen- tations (ICLR ’18) (2018),https://openreview.net/forum?id=SJiHXGWAZ","venue":null,"work_id":"1c54c4b4-33ee-4c94-a047-def013f7bd25","year":2018},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.700564Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:260c35bc8ec70be2168f6058646f616fbaa59252d995063d0f1e9cbedc69399e","observation_id":"20d46566-6d05-4f7f-bb39-eb253446f8cd","resolution":{"observed_at":"2026-08-10T10:12:28.372638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.358200Z","title":"In: Annual Conference on Neural Information Processing Systems (NeurIPS) 2022, New Orleans, LA, USA","venue":null,"work_id":"70ad8d58-f172-4ada-877b-40cd73bd71ba","year":2022},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.703926Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:dc4ecb09f9ae36a6e4bcdfbdcbed7c20e820e65c70e9e9f212f43b55daa9cd9f","observation_id":"af3e8b99-cec3-41a3-9999-9ec0a1dd7828","resolution":{"observed_at":"2026-08-10T10:12:28.361640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11017","last_updated":"2022-05-24T09:39:59Z","snapshot_observed_at":"2026-08-03T02:18:13.187861Z","submitted_at":"2021-10-21T09:46:44Z","title":"Learning Time-Varying Graphs from Online Data","version":2},"cited_work":{"arxiv_id":"2110.11017","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.11017","snapshot_observed_at":"2026-08-10T10:12:27.955325Z","title":"Learning Time-Varying Graphs from Online Data","venue":"cs.LG","work_id":"1148544c-7c63-4ca1-b451-b91da22c7fc8","year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.707205Z"},"links":{"cited_paper":"/paper/2110.11017","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:161a25437f1844aec28a99ef8adb402227cef2ad55125d9b1005cc216625c188","observation_id":"1b2229e5-bb31-4354-848a-077ceef08f8f","resolution":{"observed_at":"2026-08-10T10:12:27.960071Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:26.710758Z","title":"https://doi.org/10.1088/1367-2630/ac54c9","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.710758Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:f5a7a3a0f967c4c4834491aebd98331fde5dab32c27670887394dd3810168ba2","observation_id":"f936c846-651d-4a48-88b4-92c88861b7f1","resolution":{"observed_at":"2026-08-10T10:12:26.710758Z","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":"2026-08-10T10:12:28.347839Z","title":"In: The Eleventh International Conference on Learning Representations, ICLR, Kigali, Rwanda (2023),https: //openreview.net/forum?id=Jbdc0vTOcol","venue":null,"work_id":"cb60d716-476d-41ac-9805-0def8f2efc64","year":2023},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.714084Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:dd40d608d1fd736cc8f2fc59d73fb0698485f7b492a8928ebfed1cf02d32be68","observation_id":"fbb9894a-bc5d-45be-944b-99299219193c","resolution":{"observed_at":"2026-08-10T10:12:28.351703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:27.939510Z","title":null,"venue":null,"work_id":"6b3feadf-7889-402d-a56b-cf0d3f82ca2e","year":2018},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.717416Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:a760797910a68754711b8671545eb6566f481deaa13daa2154fb6c5231b68c9d","observation_id":"b3d1057d-1591-42e3-ac39-8a17629cf169","resolution":{"observed_at":"2026-08-10T10:12:27.944698Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.337226Z","title":"In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","venue":null,"work_id":"233e88ab-88d6-4716-8ecc-9c217a999d8d","year":2020},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.720712Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:cd02b5af7b91a4bbd94709a845bf59d5866f1aec7e9eeba13a607e4f402baa9c","observation_id":"eac4e518-cdaf-4da7-b3ad-eef155802e42","resolution":{"observed_at":"2026-08-10T10:12:28.340641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.326844Z","title":"In: 2017 IEEE International Conference on Data Mining, ICDM","venue":null,"work_id":"341bdf17-1688-4a01-9f9d-aa70d95782c9","year":2017},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.723836Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:be152d79e3911e2bd3988895d3e362d91530c3a44d1b6cb124d1fe36bdb699a1","observation_id":"d4a60c1c-e50c-43d8-8cee-103d8c0b5d15","resolution":{"observed_at":"2026-08-10T10:12:28.330391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.13288","last_updated":"2019-11-29T18:43:18Z","snapshot_observed_at":"2026-08-10T18:13:51.605800Z","submitted_at":"2019-11-29T18:43:18Z","title":"Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.13288","snapshot_observed_at":"2026-08-10T10:12:26.727594Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.727594Z"},"links":{"cited_paper":"/paper/1911.13288","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:c45e91803c56697a9a18b24afad66dec224e0919d4064df5f8b0c083819b4ec9","observation_id":"8be6334a-da82-42de-a1cb-0d1c796db64c","resolution":{"observed_at":"2026-08-10T10:12:26.727594Z","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":"2026-08-10T10:12:28.316365Z","title":"In: 9th International Conference on Learning Representations, ICLR, Virtual Event, Austria, May 3-7 (2021)","venue":null,"work_id":"70cf4d81-c823-40bc-92aa-6592c971f9c0","year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.731306Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:2a72479e620f557be7ab39dfac975b2af3794592d352ac761031ca88fe7aafc4","observation_id":"02b19492-76c1-47ac-b26e-6f05c30c48bd","resolution":{"observed_at":"2026-08-10T10:12:28.319921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:27.774737Z","title":"CIKM ’25, Association for Computing Machinery (2025)","venue":null,"work_id":"b113c82d-f0f1-4421-bd26-cb80b4fc3ccf","year":2025},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.734450Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:05110c2cb20aa1a505c55a39620b41d7d8adf03a1cae43558108fd6db290cb74","observation_id":"35cc0990-ea9e-4113-bb11-553312a70410","resolution":{"observed_at":"2026-08-10T10:12:27.781527Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.304929Z","title":"In: The Twelfth In- ternational Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024.https://openreview.net/forum?id=7oLshfEIC2","venue":null,"work_id":"50a4ba98-a826-40a2-bf4b-27b8e05b4c0e","year":2024},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.737661Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:64f353bb515ceb5d82344745967b2c5c025e7f99eb27f406ccc9e45a395634e7","observation_id":"4a675b66-9f1b-4eba-bf4f-e790392afc0c","resolution":{"observed_at":"2026-08-10T10:12:28.309038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.294508Z","title":null,"venue":null,"work_id":"3ea8f74c-a808-4e6e-9d7e-bea9e7ef43be","year":2024},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.740949Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:f082f4815880fa50846d5648b5d67bf90f5b822c265482aa592b13ef889d0ce4","observation_id":"3971fbda-a545-4b74-b747-fec89d6011ce","resolution":{"observed_at":"2026-08-10T10:12:28.298291Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.283227Z","title":"In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda","venue":null,"work_id":"d5838ac0-daa7-4e5d-b483-eb60da5d356e","year":2023},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.744629Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:47f0f11d76d7672ffb7ef049b0175a454de230f94521abd68d69f8ceecbdb5df","observation_id":"16a111fb-6603-441d-8fa2-3f09fb14a8f7","resolution":{"observed_at":"2026-08-10T10:12:28.287048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.13008","last_updated":"2022-01-07T13:39:16Z","snapshot_observed_at":"2026-08-07T16:47:22.460515Z","submitted_at":"2021-06-24T13:43:43Z","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.13008","snapshot_observed_at":"2026-08-10T10:12:26.748499Z","title":"In: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, virtual","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.748499Z"},"links":{"cited_paper":"/paper/2106.13008","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:3066439c46a061940de2b3641ea60e7a5de15772497bdc97f733615602053e70","observation_id":"4cf16480-ef97-46ae-baac-564c36234e5f","resolution":{"observed_at":"2026-08-10T10:12:26.748499Z","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":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:27.605205Z","title":"KDD ’20, Association for Computing Machinery, New York, NY, USA","venue":null,"work_id":"667a01d1-a553-47f4-a449-5629f7055a17","year":null},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.752064Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:6b0a2f036ffda3b8a65e49c9f49bdb85ea9e2d730fb369f55d1e151cedaf96d1","observation_id":"29ecec11-959a-4f31-80fd-152202cb9a44","resolution":{"observed_at":"2026-08-10T10:12:27.608910Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:26.755365Z","title":"In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI, Macao, China, August 10-16, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.755365Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:13de94cd290b0f80d17e6f24999a090782a619d0c5d77beecd1b3d7403affc54","observation_id":"3ba6b459-2d56-4c09-9244-1a2c5971ee95","resolution":{"observed_at":"2026-08-10T10:12:26.755365Z","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":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:27.290553Z","title":"IEEE Internet Things J","venue":null,"work_id":"489c52aa-e640-43d0-8914-0bff998a8704","year":2023},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.758677Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:b4220a6e5b04634cb6c715f6d2809e41f6827d22fd9b585835f93d819267a86e","observation_id":"45d5900c-74e6-4aa7-912c-28d15e7eac40","resolution":{"observed_at":"2026-08-10T10:12:27.295188Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.08305","last_updated":"2025-01-17T08:56:04Z","snapshot_observed_at":"2026-08-11T13:56:19.790107Z","submitted_at":"2025-01-14T18:41:15Z","title":"Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification","version":2},"cited_work":{"arxiv_id":"2501.08305","doi":"10.48550/arxiv.2501.08305","metadata_source":"pith","pith_arxiv_id":"2501.08305","snapshot_observed_at":"2026-08-10T12:16:17.067364Z","title":"Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification","venue":"cs.LG","work_id":"1b671c8f-24e7-45f7-8cb1-049fca7618ea","year":2025},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.761977Z"},"links":{"cited_paper":"/paper/2501.08305","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:dffd01c66842c7e97b0841f4fd6b0eaf300762e2b001970203235e1ef0a7cbe1","observation_id":"90c8f3f8-e0b2-4b29-a337-8bd2bc9405e8","resolution":{"observed_at":"2026-08-10T10:12:26.852514Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06190","last_updated":"2023-11-10T17:13:26Z","snapshot_observed_at":"2026-07-06T16:45:47.395736Z","submitted_at":"2023-11-10T17:13:26Z","title":"FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06190","snapshot_observed_at":"2026-08-10T10:12:26.765528Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.765528Z"},"links":{"cited_paper":"/paper/2311.06190","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:5c8a1cabc36770a25fcdf0654ac0c2bb703640803128e13eab7d7c20c1a7f900","observation_id":"a93a2fdc-7532-4b89-a752-94a1517ccfe9","resolution":{"observed_at":"2026-08-10T10:12:26.765528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07122","last_updated":"2016-04-30T18:19:37Z","snapshot_observed_at":"2026-07-06T04:37:24.552839Z","submitted_at":"2015-11-23T07:32:14Z","title":"Multi-Scale Context Aggregation by Dilated Convolutions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07122","snapshot_observed_at":"2026-08-10T10:12:26.769096Z","title":"In: Ben- gio, Y., LeCun, Y","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.769096Z"},"links":{"cited_paper":"/paper/1511.07122","citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:3f38ca1b84f0043a1a48be7b5ecbe637607224ded025e7d4f0e6f14a4ca439aa","observation_id":"95d70a8a-7b56-4c16-a111-c4229c7a05d8","resolution":{"observed_at":"2026-08-10T10:12:26.769096Z","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":"2026-08-10T10:12:28.271717Z","title":"In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025),https://openreview.net/forum?id=DAyKP1tvwI","venue":null,"work_id":"f72b6778-0269-4d87-bbf9-87d88c680242","year":2025},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.773194Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:d83530eac94680a3e0a49c42aba61e6b3e56789fe3cfbb529d741c75ad6d6b30","observation_id":"ead4d179-5454-4b06-8204-ae06aa380fcd","resolution":{"observed_at":"2026-08-10T10:12:28.276437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.259674Z","title":null,"venue":null,"work_id":"99af3710-e09e-48a7-b227-ea94ce9eda11","year":2023},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.777301Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:737897b458fbf7e08327723b3efc4a07361798729cc32e7093944d096db1c0f0","observation_id":"0bc5905e-5af4-4fe5-9334-4ddcee45e421","resolution":{"observed_at":"2026-08-10T10:12:28.263541Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.246946Z","title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2017) Overcoming Temporal Correlation Volatility in GNNs 19","venue":null,"work_id":"9679f6c5-5bf5-4d6d-837d-6bca68f7c46a","year":2017},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.781033Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:c6ac105f582f61cee903beb437beb3ef41079cc1e0243ed977c8f5d83f27c073","observation_id":"157e657d-5672-4091-8d45-405339574d5f","resolution":{"observed_at":"2026-08-10T10:12:28.252561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:26.784564Z","title":"In: Thirty-Fifth Conference on Artificial Intelligence","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.784564Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:dd433c59d3a6dfb23060ae55ae32aa44eb499b6009792b79fa8de55c07ed338f","observation_id":"84fe7c51-9973-4e03-bc4c-c52e2acdc336","resolution":{"observed_at":"2026-08-10T10:12:26.784564Z","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":"2026-08-10T10:12:28.233995Z","title":"In: Proc","venue":null,"work_id":"04aa27dd-d9df-429c-94cd-4a52a8b6e8d6","year":2022},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.788091Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:edfeab3185bae0e21e2fe9fe614554662c6edaf7a52851adf9cb25a37a690be4","observation_id":"49bf32e1-2ee1-4f13-8660-f27e1a74915c","resolution":{"observed_at":"2026-08-10T10:12:28.238739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.223720Z","title":null,"venue":null,"work_id":"df8edfcb-341b-4183-bcbc-8c1748d4eff3","year":null},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.791859Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:298f1c4029a39ff8e0f79f8d98123567cfe6918d26e4a2188d6f908c45d4c265","observation_id":"e6f4ded4-ebe2-4aaf-bb73-d5d257e70bc2","resolution":{"observed_at":"2026-08-10T10:12:28.227126Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T10:12:28.213012Z","title":null,"venue":null,"work_id":"58e6e93b-2aee-44be-87e5-3357e1a9bae5","year":null},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.795425Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:6f1bac17d6ba16f9dae9d9612dd64cf4efbb0a2b8e761cc1a4c32fc12877d678","observation_id":"2b537692-9cab-4a9b-92d6-90d82558c90e","resolution":{"observed_at":"2026-08-10T10:12:28.216397Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T10:12:27.119162Z","title":null,"venue":null,"work_id":"5092a5fc-90cd-45b1-a793-d75114110840","year":null},"citing_paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T10:12:26.798895Z"},"links":{"citing_paper":"/paper/2608.07333"},"observation_digest":"sha256:29a0bf178fd581d50331319f2d82194e30333e3da3325738b4504ecf6a7f9748","observation_id":"52cae605-a1ea-4a06-aa7c-05f2f1df0810","resolution":{"observed_at":"2026-08-10T10:12:27.122495Z","resolver_source":"arxiv_id_nonexistent","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.07333","last_updated":"2026-08-07T15:28:45Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T14:11:47.587934Z","submitted_at":"2026-08-07T15:28:45Z","title":"When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":2,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":13,"verified_exact":7,"verified_fuzzy":18},"total_outbound_references":42},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2608.07333."}