{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CGKV2AVMTTWV7HTIZARHQ75LCB","short_pith_number":"pith:CGKV2AVM","schema_version":"1.0","canonical_sha256":"11955d02ac9ced5f9e68c822787fab1043d0240b06b21f5644d7a54d4546ec76","source":{"kind":"arxiv","id":"2407.09557","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning Strategies in Finance: Insights into Asset Holding, Trading Behavior, and Purchase Diversity","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-fin.TR","authors_text":"Akram Mirzaeinia, Alireza Mohammadshafie, Amir Mirzaeinia, Haseebullah Jumakhan","submitted_at":"2024-06-29T20:56:58Z","abstract_excerpt":"Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and"},"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":"2407.09557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"q-fin.TR","submitted_at":"2024-06-29T20:56:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e47260af80d85cf34379ceadfaff85e1a303fc328dcc3d70eebd2ed180ef9fc","abstract_canon_sha256":"b320bc4e4ac2b4b8bdffe64a026f2153eb58cce02dba130625bf0387dd3c8f61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:32.271060Z","signature_b64":"OP/343lFyYovnVA4GfRrFHOTekXIxum5p7I8LrPMrMI8OqvfQoOOK/EpaBbWEUXWfc8W5S9Z+Wzpwz2IWzLUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11955d02ac9ced5f9e68c822787fab1043d0240b06b21f5644d7a54d4546ec76","last_reissued_at":"2026-07-05T08:43:32.270590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:32.270590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning Strategies in Finance: Insights into Asset Holding, Trading Behavior, and Purchase Diversity","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-fin.TR","authors_text":"Akram Mirzaeinia, Alireza Mohammadshafie, Amir Mirzaeinia, Haseebullah Jumakhan","submitted_at":"2024-06-29T20:56:58Z","abstract_excerpt":"Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09557","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/2407.09557/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":"2407.09557","created_at":"2026-07-05T08:43:32.270646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09557v1","created_at":"2026-07-05T08:43:32.270646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09557","created_at":"2026-07-05T08:43:32.270646+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGKV2AVMTTWV","created_at":"2026-07-05T08:43:32.270646+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGKV2AVMTTWV7HTI","created_at":"2026-07-05T08:43:32.270646+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGKV2AVM","created_at":"2026-07-05T08:43:32.270646+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":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB","json":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB.json","graph_json":"https://pith.science/api/pith-number/CGKV2AVMTTWV7HTIZARHQ75LCB/graph.json","events_json":"https://pith.science/api/pith-number/CGKV2AVMTTWV7HTIZARHQ75LCB/events.json","paper":"https://pith.science/paper/CGKV2AVM"},"agent_actions":{"view_html":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB","download_json":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB.json","view_paper":"https://pith.science/paper/CGKV2AVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09557&json=true","fetch_graph":"https://pith.science/api/pith-number/CGKV2AVMTTWV7HTIZARHQ75LCB/graph.json","fetch_events":"https://pith.science/api/pith-number/CGKV2AVMTTWV7HTIZARHQ75LCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB/action/storage_attestation","attest_author":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB/action/author_attestation","sign_citation":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB/action/citation_signature","submit_replication":"https://pith.science/pith/CGKV2AVMTTWV7HTIZARHQ75LCB/action/replication_record"}},"created_at":"2026-07-05T08:43:32.270646+00:00","updated_at":"2026-07-05T08:43:32.270646+00:00"}