{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7U4JPHD6M2MPKAUIWWWC736KDW","short_pith_number":"pith:7U4JPHD6","schema_version":"1.0","canonical_sha256":"fd38979c7e6698f50288b5ac2fefca1da1625ff60f63477a154f87e033261f5f","source":{"kind":"arxiv","id":"2406.14341","version":4},"attestation_state":"computed","paper":{"title":"HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Savchenko, Foma Shipilov, Ivan Karpukhin","submitted_at":"2024-06-20T14:09:00Z","abstract_excerpt":"Forecasting multiple future events within a given time horizon is essential for applications in finance, retail, social networks, and healthcare. Marked Temporal Point Processes (MTPP) provide a principled framework to model both the timing and labels of events. However, most existing research focuses on predicting only the next event, leaving long-horizon forecasting largely underexplored. To address this gap, we introduce HoTPP, the first benchmark specifically designed to rigorously evaluate long-horizon predictions. We identify shortcomings in widely used evaluation metrics, propose a theo"},"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":"2406.14341","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T14:09:00Z","cross_cats_sorted":[],"title_canon_sha256":"9a9f47d6747e44ab1ec2ba726795a590f222a85bf6da37ae7ada452695da67b5","abstract_canon_sha256":"198dff936619198dd0f1a4d916f6fd6f6d764622551fb7b6bf0e31abc4d0977a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:12.325468Z","signature_b64":"ooSlfcL6LKTIPvb4I1NHB1xMz1pP8XIh1sNmphgz5wQ0bnAKillYOTxm6tbKHeQqCARsTPTjq/Cr1U7AyMzJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd38979c7e6698f50288b5ac2fefca1da1625ff60f63477a154f87e033261f5f","last_reissued_at":"2026-07-05T11:47:12.324974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:12.324974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Savchenko, Foma Shipilov, Ivan Karpukhin","submitted_at":"2024-06-20T14:09:00Z","abstract_excerpt":"Forecasting multiple future events within a given time horizon is essential for applications in finance, retail, social networks, and healthcare. Marked Temporal Point Processes (MTPP) provide a principled framework to model both the timing and labels of events. However, most existing research focuses on predicting only the next event, leaving long-horizon forecasting largely underexplored. To address this gap, we introduce HoTPP, the first benchmark specifically designed to rigorously evaluate long-horizon predictions. We identify shortcomings in widely used evaluation metrics, propose a theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14341","kind":"arxiv","version":4},"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/2406.14341/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":"2406.14341","created_at":"2026-07-05T11:47:12.325030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14341v4","created_at":"2026-07-05T11:47:12.325030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14341","created_at":"2026-07-05T11:47:12.325030+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U4JPHD6M2MP","created_at":"2026-07-05T11:47:12.325030+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U4JPHD6M2MPKAUI","created_at":"2026-07-05T11:47:12.325030+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U4JPHD6","created_at":"2026-07-05T11:47:12.325030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01022","citing_title":"Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW","json":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW.json","graph_json":"https://pith.science/api/pith-number/7U4JPHD6M2MPKAUIWWWC736KDW/graph.json","events_json":"https://pith.science/api/pith-number/7U4JPHD6M2MPKAUIWWWC736KDW/events.json","paper":"https://pith.science/paper/7U4JPHD6"},"agent_actions":{"view_html":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW","download_json":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW.json","view_paper":"https://pith.science/paper/7U4JPHD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14341&json=true","fetch_graph":"https://pith.science/api/pith-number/7U4JPHD6M2MPKAUIWWWC736KDW/graph.json","fetch_events":"https://pith.science/api/pith-number/7U4JPHD6M2MPKAUIWWWC736KDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW/action/storage_attestation","attest_author":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW/action/author_attestation","sign_citation":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW/action/citation_signature","submit_replication":"https://pith.science/pith/7U4JPHD6M2MPKAUIWWWC736KDW/action/replication_record"}},"created_at":"2026-07-05T11:47:12.325030+00:00","updated_at":"2026-07-05T11:47:12.325030+00:00"}