{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YDZLJE52OPNUUHWISG7RYMBQH6","short_pith_number":"pith:YDZLJE52","schema_version":"1.0","canonical_sha256":"c0f2b493ba73db4a1ec891bf1c30303fb36a9ede599d67736b72e291e6dc2d2a","source":{"kind":"arxiv","id":"1805.09360","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning of Marked Temporal Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abir De, Manuel Gomez-Rodriguez, Utkarsh Upadhyay","submitted_at":"2018-05-23T18:06:10Z","abstract_excerpt":"In a wide variety of applications, humans interact with a complex environment by means of asynchronous stochastic discrete events in continuous time. Can we design online interventions that will help humans achieve certain goals in such asynchronous setting? In this paper, we address the above problem from the perspective of deep reinforcement learning of marked temporal point processes, where both the actions taken by an agent and the feedback it receives from the environment are asynchronous stochastic discrete events characterized using marked temporal point processes. In doing so, we defin"},"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":"1805.09360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:06:10Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"40b8a87c61ca2f1da6e708701e2f0a20af7fd8c9fa4e3ed4868a7d10381b3ff5","abstract_canon_sha256":"80ceffb0444fb15f997612b95c3fa56f03f9f9f5fe92b7b20dcc6100fdc3a614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:29.520292Z","signature_b64":"n05iWHj1XDOL0/o2kCCD6qqP5GGTmQCkfjs1L1GjbeK5Up4RIzhGI7Er1Oh5k0NDe2jyUYiiaknOoJ+y7IF4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f2b493ba73db4a1ec891bf1c30303fb36a9ede599d67736b72e291e6dc2d2a","last_reissued_at":"2026-05-18T00:01:29.519846Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:29.519846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning of Marked Temporal Point Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abir De, Manuel Gomez-Rodriguez, Utkarsh Upadhyay","submitted_at":"2018-05-23T18:06:10Z","abstract_excerpt":"In a wide variety of applications, humans interact with a complex environment by means of asynchronous stochastic discrete events in continuous time. Can we design online interventions that will help humans achieve certain goals in such asynchronous setting? In this paper, we address the above problem from the perspective of deep reinforcement learning of marked temporal point processes, where both the actions taken by an agent and the feedback it receives from the environment are asynchronous stochastic discrete events characterized using marked temporal point processes. In doing so, we defin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09360","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.09360","created_at":"2026-05-18T00:01:29.519924+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09360v2","created_at":"2026-05-18T00:01:29.519924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09360","created_at":"2026-05-18T00:01:29.519924+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDZLJE52OPNU","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDZLJE52OPNUUHWI","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDZLJE52","created_at":"2026-05-18T12:33:04.347982+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/YDZLJE52OPNUUHWISG7RYMBQH6","json":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6.json","graph_json":"https://pith.science/api/pith-number/YDZLJE52OPNUUHWISG7RYMBQH6/graph.json","events_json":"https://pith.science/api/pith-number/YDZLJE52OPNUUHWISG7RYMBQH6/events.json","paper":"https://pith.science/paper/YDZLJE52"},"agent_actions":{"view_html":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6","download_json":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6.json","view_paper":"https://pith.science/paper/YDZLJE52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09360&json=true","fetch_graph":"https://pith.science/api/pith-number/YDZLJE52OPNUUHWISG7RYMBQH6/graph.json","fetch_events":"https://pith.science/api/pith-number/YDZLJE52OPNUUHWISG7RYMBQH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6/action/storage_attestation","attest_author":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6/action/author_attestation","sign_citation":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6/action/citation_signature","submit_replication":"https://pith.science/pith/YDZLJE52OPNUUHWISG7RYMBQH6/action/replication_record"}},"created_at":"2026-05-18T00:01:29.519924+00:00","updated_at":"2026-05-18T00:01:29.519924+00:00"}