{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6ZJ7DM2INCUA7D32XP5WY4ABHV","short_pith_number":"pith:6ZJ7DM2I","schema_version":"1.0","canonical_sha256":"f653f1b34868a80f8f7abbfb6c70013d7b7f77e30390c2836eb9c75a22248e09","source":{"kind":"arxiv","id":"2002.09291","version":5},"attestation_state":"computed","paper":{"title":"Transformer Hawkes Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoming Jiang, Hongyuan Zha, Simiao Zuo, Tuo Zhao, Zichong Li","submitted_at":"2020-02-21T13:48:13Z","abstract_excerpt":"Modern data acquisition routinely produce massive amounts of event sequence data in various domains, such as social media, healthcare, and financial markets. These data often exhibit complicated short-term and long-term temporal dependencies. However, most of the existing recurrent neural network based point process models fail to capture such dependencies, and yield unreliable prediction performance. To address this issue, we propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies and meanwhile enjoys computational effic"},"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":"2002.09291","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-21T13:48:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"55d6fca09afa184f7ada8b0a127306f0a2ff02133cf28c65f8e84de047b5809c","abstract_canon_sha256":"0d8c39349e76f7eb4d183a10c4ba3293d89ee04fe2d0738cd8b7af03177d03f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:43.459670Z","signature_b64":"DUGuLWEHR19M8jQnu81a7pKxewRHH6hphNgSxdt1rH8MGngKAmvNZn8R2eAFs5HGyDbnGwnWnmq6W+ywyifAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f653f1b34868a80f8f7abbfb6c70013d7b7f77e30390c2836eb9c75a22248e09","last_reissued_at":"2026-07-05T02:16:43.459184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:43.459184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer Hawkes Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haoming Jiang, Hongyuan Zha, Simiao Zuo, Tuo Zhao, Zichong Li","submitted_at":"2020-02-21T13:48:13Z","abstract_excerpt":"Modern data acquisition routinely produce massive amounts of event sequence data in various domains, such as social media, healthcare, and financial markets. These data often exhibit complicated short-term and long-term temporal dependencies. However, most of the existing recurrent neural network based point process models fail to capture such dependencies, and yield unreliable prediction performance. To address this issue, we propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies and meanwhile enjoys computational effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09291","kind":"arxiv","version":5},"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/2002.09291/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":"2002.09291","created_at":"2026-07-05T02:16:43.459252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09291v5","created_at":"2026-07-05T02:16:43.459252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09291","created_at":"2026-07-05T02:16:43.459252+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZJ7DM2INCUA","created_at":"2026-07-05T02:16:43.459252+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZJ7DM2INCUA7D32","created_at":"2026-07-05T02:16:43.459252+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZJ7DM2I","created_at":"2026-07-05T02:16:43.459252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14069","citing_title":"SurF: A Generative Model for Multivariate Irregular Time Series Forecasting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05844","citing_title":"Modeling Patient Care Trajectories with Transformer Hawkes Processes","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07437","citing_title":"ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV","json":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV.json","graph_json":"https://pith.science/api/pith-number/6ZJ7DM2INCUA7D32XP5WY4ABHV/graph.json","events_json":"https://pith.science/api/pith-number/6ZJ7DM2INCUA7D32XP5WY4ABHV/events.json","paper":"https://pith.science/paper/6ZJ7DM2I"},"agent_actions":{"view_html":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV","download_json":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV.json","view_paper":"https://pith.science/paper/6ZJ7DM2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09291&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZJ7DM2INCUA7D32XP5WY4ABHV/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZJ7DM2INCUA7D32XP5WY4ABHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV/action/storage_attestation","attest_author":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV/action/author_attestation","sign_citation":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV/action/citation_signature","submit_replication":"https://pith.science/pith/6ZJ7DM2INCUA7D32XP5WY4ABHV/action/replication_record"}},"created_at":"2026-07-05T02:16:43.459252+00:00","updated_at":"2026-07-05T02:16:43.459252+00:00"}