{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RE4KBUKXAYTDF5YZOZVFMHXHEQ","short_pith_number":"pith:RE4KBUKX","schema_version":"1.0","canonical_sha256":"8938a0d157062632f719766a561ee7240128122bd9ceb2e325c9aba892b0f9d2","source":{"kind":"arxiv","id":"2106.00123","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.TR"],"primary_cat":"cs.LG","authors_text":"Tidor-Vlad Pricope","submitted_at":"2021-05-31T22:26:43Z","abstract_excerpt":"Algorithmic stock trading has become a staple in today's financial market, the majority of trades being now fully automated. Deep Reinforcement Learning (DRL) agents proved to be to a force to be reckon with in many complex games like Chess and Go. We can look at the stock market historical price series and movements as a complex imperfect information environment in which we try to maximize return - profit and minimize risk. This paper reviews the progress made so far with deep reinforcement learning in the subdomain of AI in finance, more precisely, automated low-frequency quantitative stock "},"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":"2106.00123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-31T22:26:43Z","cross_cats_sorted":["q-fin.TR"],"title_canon_sha256":"76f13542e53011dd285f18a696ee105b1646cb3eb7c6fa1d84e2518192392294","abstract_canon_sha256":"2c2c426d06b3efe1b50f3b778818988fcc5e0f329db928ad7980e142d47fd89b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:00.864871Z","signature_b64":"JGBptPWfwRsBDVCK9yZ0OlAq1yRCJDJydN+oWE+M23w0D/SjlpyX8lHTTRa2mh1QCDERezw/cpdRODO+dJvzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8938a0d157062632f719766a561ee7240128122bd9ceb2e325c9aba892b0f9d2","last_reissued_at":"2026-07-05T02:45:00.864404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:00.864404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.TR"],"primary_cat":"cs.LG","authors_text":"Tidor-Vlad Pricope","submitted_at":"2021-05-31T22:26:43Z","abstract_excerpt":"Algorithmic stock trading has become a staple in today's financial market, the majority of trades being now fully automated. Deep Reinforcement Learning (DRL) agents proved to be to a force to be reckon with in many complex games like Chess and Go. We can look at the stock market historical price series and movements as a complex imperfect information environment in which we try to maximize return - profit and minimize risk. This paper reviews the progress made so far with deep reinforcement learning in the subdomain of AI in finance, more precisely, automated low-frequency quantitative stock "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00123","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/2106.00123/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":"2106.00123","created_at":"2026-07-05T02:45:00.864461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00123v1","created_at":"2026-07-05T02:45:00.864461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00123","created_at":"2026-07-05T02:45:00.864461+00:00"},{"alias_kind":"pith_short_12","alias_value":"RE4KBUKXAYTD","created_at":"2026-07-05T02:45:00.864461+00:00"},{"alias_kind":"pith_short_16","alias_value":"RE4KBUKXAYTDF5YZ","created_at":"2026-07-05T02:45:00.864461+00:00"},{"alias_kind":"pith_short_8","alias_value":"RE4KBUKX","created_at":"2026-07-05T02:45:00.864461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19639","citing_title":"Directly Learning Stock Trading Strategies Through Profit Guided Loss Functions","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ","json":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ.json","graph_json":"https://pith.science/api/pith-number/RE4KBUKXAYTDF5YZOZVFMHXHEQ/graph.json","events_json":"https://pith.science/api/pith-number/RE4KBUKXAYTDF5YZOZVFMHXHEQ/events.json","paper":"https://pith.science/paper/RE4KBUKX"},"agent_actions":{"view_html":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ","download_json":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ.json","view_paper":"https://pith.science/paper/RE4KBUKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00123&json=true","fetch_graph":"https://pith.science/api/pith-number/RE4KBUKXAYTDF5YZOZVFMHXHEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RE4KBUKXAYTDF5YZOZVFMHXHEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ/action/storage_attestation","attest_author":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ/action/author_attestation","sign_citation":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ/action/citation_signature","submit_replication":"https://pith.science/pith/RE4KBUKXAYTDF5YZOZVFMHXHEQ/action/replication_record"}},"created_at":"2026-07-05T02:45:00.864461+00:00","updated_at":"2026-07-05T02:45:00.864461+00:00"}