{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GGTWV6U3QFRXJIZQMJ5SOPBSMZ","short_pith_number":"pith:GGTWV6U3","schema_version":"1.0","canonical_sha256":"31a76afa9b816374a330627b273c326645623c162b48962d4ef5f84588f94aaa","source":{"kind":"arxiv","id":"2606.18367","version":1},"attestation_state":"computed","paper":{"title":"Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lingdong Kong, Wei Gao, Xian Sun, Yanhang Li, Yingshuo Wang, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-06-16T18:16:07Z","abstract_excerpt":"Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-stratified evaluation and apply it to three TSFMs on two standard traffic speed benchmarks. Traffic exhibits abrupt regime switching between free-flow and congested states, producing bimodal speed distributions during transitions. When we stratify by traffic regime, both accuracy and prediction-interval coverage degrade sharply during transitions: transition-regime MAE reaches 11 mph (versus 3 mph overall), and empiric"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.18367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T18:16:07Z","cross_cats_sorted":[],"title_canon_sha256":"6d597a4e2382a6ce0bb8c93cf3a54ae1ca456bffcdb4e70e79f81d22010a1af6","abstract_canon_sha256":"b9c233457762edbdb389182025daa5f3e221757a43b63b8be0ef616afcc8ebf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:59.191889Z","signature_b64":"coAGQA51wUXEnRi1ypKohdQMuH8pD4yziOXHd5gsgjYokx0AiwnkgnW2m90XRBYlyttqqSKGk3tGZ5Xp7tSwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a76afa9b816374a330627b273c326645623c162b48962d4ef5f84588f94aaa","last_reissued_at":"2026-06-19T16:10:59.191503Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:59.191503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lingdong Kong, Wei Gao, Xian Sun, Yanhang Li, Yingshuo Wang, Zexin Zhuang, Zhichao Fan","submitted_at":"2026-06-16T18:16:07Z","abstract_excerpt":"Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-stratified evaluation and apply it to three TSFMs on two standard traffic speed benchmarks. Traffic exhibits abrupt regime switching between free-flow and congested states, producing bimodal speed distributions during transitions. When we stratify by traffic regime, both accuracy and prediction-interval coverage degrade sharply during transitions: transition-regime MAE reaches 11 mph (versus 3 mph overall), and empiric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18367","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.18367/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.18367","created_at":"2026-06-19T16:10:59.191563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18367v1","created_at":"2026-06-19T16:10:59.191563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18367","created_at":"2026-06-19T16:10:59.191563+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGTWV6U3QFRX","created_at":"2026-06-19T16:10:59.191563+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGTWV6U3QFRXJIZQ","created_at":"2026-06-19T16:10:59.191563+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGTWV6U3","created_at":"2026-06-19T16:10:59.191563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ","json":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ.json","graph_json":"https://pith.science/api/pith-number/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/graph.json","events_json":"https://pith.science/api/pith-number/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/events.json","paper":"https://pith.science/paper/GGTWV6U3"},"agent_actions":{"view_html":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ","download_json":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ.json","view_paper":"https://pith.science/paper/GGTWV6U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18367&json=true","fetch_graph":"https://pith.science/api/pith-number/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/action/storage_attestation","attest_author":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/action/author_attestation","sign_citation":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/action/citation_signature","submit_replication":"https://pith.science/pith/GGTWV6U3QFRXJIZQMJ5SOPBSMZ/action/replication_record"}},"created_at":"2026-06-19T16:10:59.191563+00:00","updated_at":"2026-06-19T16:10:59.191563+00:00"}