{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GC2423M73KZKBM324RXX4AZ4IP","short_pith_number":"pith:GC2423M7","schema_version":"1.0","canonical_sha256":"30b5cd6d9fdab2a0b37ae46f7e033c43f986dc083031486f0a3fb4037dadd75c","source":{"kind":"arxiv","id":"2406.00630","version":1},"attestation_state":"computed","paper":{"title":"On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guanhua Fang, Wen Yu, Zhiheng Chen","submitted_at":"2024-06-02T06:19:25Z","abstract_excerpt":"Temporal point process (TPP) is an important tool for modeling and predicting irregularly timed events across various domains. Recently, the recurrent neural network (RNN)-based TPPs have shown practical advantages over traditional parametric TPP models. However, in the current literature, it remains nascent in understanding neural TPPs from theoretical viewpoints. In this paper, we establish the excess risk bounds of RNN-TPPs under many well-known TPP settings. We especially show that an RNN-TPP with no more than four layers can achieve vanishing generalization errors. Our technical contribut"},"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":"2406.00630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-02T06:19:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"821f04738f0137feaaff2627c68c4749569a78bbee59d61c4168430ca65a7397","abstract_canon_sha256":"0b8d010b94e96ec1f68d1ecf3ecc3b17fc260d5bfad55a097b2b27c12daf2950"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:28.336834Z","signature_b64":"NvurrM/5//ssXWTxddGZGw1P/b5nxTzC24usA+pZpy8EQNoleBuzp6Ql4ipFLrbbbBDKBhSv7q3H3pdL7DvPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b5cd6d9fdab2a0b37ae46f7e033c43f986dc083031486f0a3fb4037dadd75c","last_reissued_at":"2026-07-05T08:26:28.336336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:28.336336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guanhua Fang, Wen Yu, Zhiheng Chen","submitted_at":"2024-06-02T06:19:25Z","abstract_excerpt":"Temporal point process (TPP) is an important tool for modeling and predicting irregularly timed events across various domains. Recently, the recurrent neural network (RNN)-based TPPs have shown practical advantages over traditional parametric TPP models. However, in the current literature, it remains nascent in understanding neural TPPs from theoretical viewpoints. In this paper, we establish the excess risk bounds of RNN-TPPs under many well-known TPP settings. We especially show that an RNN-TPP with no more than four layers can achieve vanishing generalization errors. Our technical contribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00630","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/2406.00630/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":"2406.00630","created_at":"2026-07-05T08:26:28.336389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00630v1","created_at":"2026-07-05T08:26:28.336389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00630","created_at":"2026-07-05T08:26:28.336389+00:00"},{"alias_kind":"pith_short_12","alias_value":"GC2423M73KZK","created_at":"2026-07-05T08:26:28.336389+00:00"},{"alias_kind":"pith_short_16","alias_value":"GC2423M73KZKBM32","created_at":"2026-07-05T08:26:28.336389+00:00"},{"alias_kind":"pith_short_8","alias_value":"GC2423M7","created_at":"2026-07-05T08:26:28.336389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14291","citing_title":"Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approaches","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP","json":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP.json","graph_json":"https://pith.science/api/pith-number/GC2423M73KZKBM324RXX4AZ4IP/graph.json","events_json":"https://pith.science/api/pith-number/GC2423M73KZKBM324RXX4AZ4IP/events.json","paper":"https://pith.science/paper/GC2423M7"},"agent_actions":{"view_html":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP","download_json":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP.json","view_paper":"https://pith.science/paper/GC2423M7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00630&json=true","fetch_graph":"https://pith.science/api/pith-number/GC2423M73KZKBM324RXX4AZ4IP/graph.json","fetch_events":"https://pith.science/api/pith-number/GC2423M73KZKBM324RXX4AZ4IP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP/action/storage_attestation","attest_author":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP/action/author_attestation","sign_citation":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP/action/citation_signature","submit_replication":"https://pith.science/pith/GC2423M73KZKBM324RXX4AZ4IP/action/replication_record"}},"created_at":"2026-07-05T08:26:28.336389+00:00","updated_at":"2026-07-05T08:26:28.336389+00:00"}