{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CUYJHCVIIJL2ZVV37BUIU6XDIS","short_pith_number":"pith:CUYJHCVI","schema_version":"1.0","canonical_sha256":"1530938aa84257acd6bbf8688a7ae344b834a2dabb10f1823ee2a8834bd59f7a","source":{"kind":"arxiv","id":"2409.03282","version":1},"attestation_state":"computed","paper":{"title":"Interpretable mixture of experts for time series prediction under recurrent and non-recurrent conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Haocheng Duan, Sean Qian, Zemian Ke","submitted_at":"2024-09-05T06:47:01Z","abstract_excerpt":"Non-recurrent conditions caused by incidents are different from recurrent conditions that follow periodic patterns. Existing traffic speed prediction studies are incident-agnostic and use one single model to learn all possible patterns from these drastically diverse conditions. This study proposes a novel Mixture of Experts (MoE) model to improve traffic speed prediction under two separate conditions, recurrent and non-recurrent (i.e., with and without incidents). The MoE leverages separate recurrent and non-recurrent expert models (Temporal Fusion Transformers) to capture the distinct pattern"},"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":"2409.03282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T06:47:01Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"26d1a46b097eb92e849fcad98ca537e8aef4caa7aae00da0f031c9b596b1d49d","abstract_canon_sha256":"7e3417511e75ceae5fe8620c78df9bc5500251d8ffe5bc2a6c514917650bd5aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:29.048422Z","signature_b64":"mxBSU0Np8MiWvcQCymwXESpQFQ/Dc4gN/Fh3zLW/FCG6b3i9Izg/zGCssqneySUlT2QbRiZRbfq6JKMxXvAYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1530938aa84257acd6bbf8688a7ae344b834a2dabb10f1823ee2a8834bd59f7a","last_reissued_at":"2026-07-05T09:03:29.047921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:29.047921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable mixture of experts for time series prediction under recurrent and non-recurrent conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Haocheng Duan, Sean Qian, Zemian Ke","submitted_at":"2024-09-05T06:47:01Z","abstract_excerpt":"Non-recurrent conditions caused by incidents are different from recurrent conditions that follow periodic patterns. Existing traffic speed prediction studies are incident-agnostic and use one single model to learn all possible patterns from these drastically diverse conditions. This study proposes a novel Mixture of Experts (MoE) model to improve traffic speed prediction under two separate conditions, recurrent and non-recurrent (i.e., with and without incidents). The MoE leverages separate recurrent and non-recurrent expert models (Temporal Fusion Transformers) to capture the distinct pattern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03282","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/2409.03282/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":"2409.03282","created_at":"2026-07-05T09:03:29.047980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03282v1","created_at":"2026-07-05T09:03:29.047980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03282","created_at":"2026-07-05T09:03:29.047980+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUYJHCVIIJL2","created_at":"2026-07-05T09:03:29.047980+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUYJHCVIIJL2ZVV3","created_at":"2026-07-05T09:03:29.047980+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUYJHCVI","created_at":"2026-07-05T09:03:29.047980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10892","citing_title":"Know Unreported Roadway Incidents in Real-time: Early Traffic Anomaly Detection","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS","json":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS.json","graph_json":"https://pith.science/api/pith-number/CUYJHCVIIJL2ZVV37BUIU6XDIS/graph.json","events_json":"https://pith.science/api/pith-number/CUYJHCVIIJL2ZVV37BUIU6XDIS/events.json","paper":"https://pith.science/paper/CUYJHCVI"},"agent_actions":{"view_html":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS","download_json":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS.json","view_paper":"https://pith.science/paper/CUYJHCVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03282&json=true","fetch_graph":"https://pith.science/api/pith-number/CUYJHCVIIJL2ZVV37BUIU6XDIS/graph.json","fetch_events":"https://pith.science/api/pith-number/CUYJHCVIIJL2ZVV37BUIU6XDIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS/action/storage_attestation","attest_author":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS/action/author_attestation","sign_citation":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS/action/citation_signature","submit_replication":"https://pith.science/pith/CUYJHCVIIJL2ZVV37BUIU6XDIS/action/replication_record"}},"created_at":"2026-07-05T09:03:29.047980+00:00","updated_at":"2026-07-05T09:03:29.047980+00:00"}