{"as_of":"2026-08-10T02:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e86597bab72074fdadec413e0219ed555980f1fecae048439632f13bd798992","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:31:42.155985Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2608.01857/citation-record","integrity":"/paper/2608.01857/integrity","json":"/paper/2608.01857/citation-record.json","paper":"/paper/2608.01857"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:31:41.138930Z","title":"Fastdifferentiablesortingandranking","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.138930Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:f011264739fe362c820dd092d56acdcb3a356950a263e9c3266930755b5a8e50","observation_id":"3cde5670-a297-4d63-b40a-841bf2bfdca6","resolution":{"observed_at":"2026-08-04T19:31:41.138930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10721","last_updated":"2026-05-17T02:25:14Z","snapshot_observed_at":"2026-08-03T04:41:00.104637Z","submitted_at":"2023-05-18T05:39:46Z","title":"Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10721","snapshot_observed_at":"2026-08-04T19:31:41.382301Z","title":"arXiv preprint arXiv:2305.10721","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.382301Z"},"links":{"cited_paper":"/paper/2305.10721","citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:aa57b95a8b03b1f3c4be96dc10ae59a05f1406608366110b34d7244712d8f9a9","observation_id":"fa8ef2f5-1fe1-49cf-ac3f-ca119866a93e","resolution":{"observed_at":"2026-08-04T19:31:41.382301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.11200","last_updated":"2023-08-22T05:23:04Z","snapshot_observed_at":"2026-08-09T23:13:06.346823Z","submitted_at":"2023-08-22T05:23:04Z","title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.11200","snapshot_observed_at":"2026-08-04T19:31:41.456689Z","title":"Liu, S.; Yu, H.; Liao, C.; Li, J.; Lin, W.; Liu, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.456689Z"},"links":{"cited_paper":"/paper/2308.11200","citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:ee458077eeb069ff8a37f6f0019a4a85a04f834d80f630aafdaf61db930fede0","observation_id":"9f24d879-1f07-49d9-9e42-4b675dcfddea","resolution":{"observed_at":"2026-08-04T19:31:41.456689Z","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":"2026-08-04T19:31:42.155985Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:42.155985Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:b6579a19999673d5701f259cfca6bf8c88c9972bc4002ecf9bb0176acd7212e4","observation_id":"f0b70025-ff31-4259-ac8b-0d346cbf4b9c","resolution":{"observed_at":"2026-08-04T19:31:42.155985Z","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":"2026-08-04T19:31:41.910980Z","title":"InInternational Conference on Learning Representations (ICLR)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.910980Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:4eff513ce4680a0f9ea2bb8df2f616553a00718f398fc23cf885ad8f27a3be77","observation_id":"fd13ea74-326c-4c0b-9a4e-cc123483ca25","resolution":{"observed_at":"2026-08-04T19:31:41.910980Z","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":"2026-08-04T19:31:42.014164Z","title":"It improves DA over the baseline but, unlike CosDir, it op- timizes a hard up/down label that ignores how strongly the trajectories agree (Table 7)","venue":null,"work_id":null,"year":1920},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:42.014164Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:e8e49aee9c1a9c1eb076928482e79e4b03ede0203081e62e5cfa8320348e00ff","observation_id":"cc8d30ec-a5e0-4399-a936-498d4a1da368","resolution":{"observed_at":"2026-08-04T19:31:42.014164Z","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":"2026-08-04T19:31:42.062759Z","title":"2023), it reports the change in DA and MSE of each auxiliary loss relative to the base loss","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:42.062759Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:dcdda5cd0c6f611949bdcdfa0d27332b044aefeb627c24844cd5d8e380520d94","observation_id":"986f5404-6f72-4710-8376-c324c90463c1","resolution":{"observed_at":"2026-08-04T19:31:42.062759Z","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":"2026-08-04T19:31:41.246688Z","title":"Jiang,W.2021.Applicationsofdeeplearninginstockmarket prediction: Recent progress.Expert Systems with Applica- tions, 184: 115537","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":1970,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.246688Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:7584abec7defe106f586294f754689fd5506f2a807009e9caad48fd3de32f45f","observation_id":"bbfb54c7-1d9c-4c30-8e96-6e36c807b9d2","resolution":{"observed_at":"2026-08-04T19:31:41.246688Z","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":"2026-08-04T19:31:41.664313Z","title":"InAdvances in Neural Information Processing Systems (NeurIPS)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.664313Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:54c0a801844574f35fcecd84c55f704fef2d4499ded35d52a2c00760b013507d","observation_id":"0f2d4f72-aa65-4a84-9739-d9e806fb3729","resolution":{"observed_at":"2026-08-04T19:31:41.664313Z","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":"2026-08-04T19:31:41.331356Z","title":"LeGuen,V.;andThome,N.2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.331356Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:332cbe121d0064838422ee03f362ede810e0baccb171e25347a8a1643a85698d","observation_id":"22a5002a-3ffa-44d4-9da6-f79207d582c4","resolution":{"observed_at":"2026-08-04T19:31:41.331356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.01186","last_updated":"2022-07-04T04:03:00Z","snapshot_observed_at":"2026-08-09T16:47:41.631671Z","submitted_at":"2022-07-04T04:03:00Z","title":"Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.01186","snapshot_observed_at":"2026-08-04T19:31:41.808372Z","title":"Zhang, Y.; and Yan, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.808372Z"},"links":{"cited_paper":"/paper/2207.01186","citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:3965deeec1794794da27d74a8401fd8dd911c509506fc5e7a8f7016a0845aa97","observation_id":"53afc1a3-05c3-4bc8-a469-e635cee06aa1","resolution":{"observed_at":"2026-08-04T19:31:41.808372Z","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":"2026-08-04T19:31:41.192761Z","title":"predict,then optimize","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.192761Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:73ac0b1d254b934f35f5c20c79148d18b21ae09fc43915c37151d8dbe6aaf06c","observation_id":"6a18a2d5-18f2-4094-b614-139cb5c8a7a7","resolution":{"observed_at":"2026-08-04T19:31:41.192761Z","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":"2026-08-04T19:31:41.567795Z","title":"InInternational Confer- ence on Learning Representations (ICLR)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.567795Z"},"links":{"citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:50949a41a2bf174545a98662dcdbfcd1aa64d7d93341a8a0e46631226a018ea0","observation_id":"519f8b02-158a-48b3-a0df-15b8270f5a02","resolution":{"observed_at":"2026-08-04T19:31:41.567795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.09789","last_updated":"2026-06-10T10:00:58Z","snapshot_observed_at":"2026-08-06T13:39:41.543118Z","submitted_at":"2025-11-12T22:43:40Z","title":"CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.09789","snapshot_observed_at":"2026-08-04T19:31:41.735567Z","title":"Yi, K.; Zhang, Q.; Fan, W.; Wang, S.; Wang, P.; He, H.; An, N.; Lian, D.; Cao, L.; and Niu, Z","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T19:31:41.735567Z"},"links":{"cited_paper":"/paper/2511.09789","citing_paper":"/paper/2608.01857"},"observation_digest":"sha256:46f2d0c0f3ce87c0103f10ae1c2acce736916aecd0979c35f5f7e6914d8f4274","observation_id":"95d050bb-a6b2-48d2-8e4b-818dcab78fc3","resolution":{"observed_at":"2026-08-04T19:31:41.735567Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.01857","last_updated":"2026-08-03T08:06:39Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T20:37:23.434580Z","submitted_at":"2026-08-03T08:06:39Z","title":"Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":14},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2608.01857."}