{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4OZHGM25QQMWHW2RN2AWY7LAJ7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad946717d47c86e743b2df91fa1df63a8740116f2cfb66e876e1dd9795942d2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T16:17:18Z","title_canon_sha256":"da2af2e187788e448c1e6f53bd9ae715fe23ad0818ba4cfeb093e10a7903772d"},"schema_version":"1.0","source":{"id":"2509.26468","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26468","created_at":"2026-06-30T02:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26468v3","created_at":"2026-06-30T02:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26468","created_at":"2026-06-30T02:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"4OZHGM25QQMW","created_at":"2026-06-30T02:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"4OZHGM25QQMWHW2R","created_at":"2026-06-30T02:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"4OZHGM25","created_at":"2026-06-30T02:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:24558be32c163675d22bf5cdeee7fb8ce0d425fb462c84ff21e0bd6326a5db85","target":"graph","created_at":"2026-06-30T02:17:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.26468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained models. Existing benchmarks often have limited domain coverage or overlook real-world settings such as tasks with covariates. Their aggregation procedures frequently lack statistical rigor, making it unclear whether observed performance differences reflect true improvements or random variation. Many benchmarks lack consistent evaluation infrastructure or are too rigid for integration into existing pipelines. To address these gaps, we propose fev-be","authors_text":"Abdul Fatir Ansari, Caner Turkmen, Lorenzo Stella, Michael Bohlke-Schneider, Nick Erickson, Oleksandr Shchur, Pablo Guerron, Yuyang Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T16:17:18Z","title":"fev-bench: A Realistic Benchmark for Time Series Forecasting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26468","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c0a1f2320ae94fa94a28c79b3fbb484562ca84fb9a87d3bb078dc70a01d6d5dd","target":"record","created_at":"2026-06-30T02:17:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad946717d47c86e743b2df91fa1df63a8740116f2cfb66e876e1dd9795942d2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T16:17:18Z","title_canon_sha256":"da2af2e187788e448c1e6f53bd9ae715fe23ad0818ba4cfeb093e10a7903772d"},"schema_version":"1.0","source":{"id":"2509.26468","kind":"arxiv","version":3}},"canonical_sha256":"e3b273335d841963db516e816c7d604fe74041b309d17a651b47edeebdd4947c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3b273335d841963db516e816c7d604fe74041b309d17a651b47edeebdd4947c","first_computed_at":"2026-06-30T02:17:09.934101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:09.934101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wXDiL6G7TTKEgUdv7Kx1Um9mlkFW/MpAQRLfJiDrBxDE3ipIN0a/tqRsVJ0MJzKvrC1nj3aZVQkU8jDYU7BqCg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:09.934887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.26468","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0a1f2320ae94fa94a28c79b3fbb484562ca84fb9a87d3bb078dc70a01d6d5dd","sha256:24558be32c163675d22bf5cdeee7fb8ce0d425fb462c84ff21e0bd6326a5db85"],"state_sha256":"e298ac4ec438e6c9f4e5bafb34dc6b56250bf7a1e918b97ea2753c3041a22ff5"}