{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DQGEHEZHGPWOAEC6DKRPOHPEF5","short_pith_number":"pith:DQGEHEZH","schema_version":"1.0","canonical_sha256":"1c0c43932733ece0105e1aa2f71de42f7c952c923f75bb3b892763e5bdb809bc","source":{"kind":"arxiv","id":"1906.12350","version":2},"attestation_state":"computed","paper":{"title":"Split Q Learning: Reinforcement Learning with Two-Stream Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi","submitted_at":"2019-06-21T01:59:52Z","abstract_excerpt":"Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to unders"},"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":"1906.12350","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T01:59:52Z","cross_cats_sorted":["cs.AI","cs.MA","q-bio.NC","stat.ML"],"title_canon_sha256":"72d748dc75acb51819f822f2e8454d93342b7d882926198399376eae008af6f4","abstract_canon_sha256":"0247a189cbf1c3a2c6a502d8230cc92c1713112f3bb681fe936a65765149c43b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:51.681666Z","signature_b64":"TYChUxVNOqgTLCnACgA+Cg9BvFFmYlefZ2sWv35Oom53WkxXs837XODZP2D7GnD4uygh3adu4T7lsZuzkbuPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c0c43932733ece0105e1aa2f71de42f7c952c923f75bb3b892763e5bdb809bc","last_reissued_at":"2026-07-05T00:18:51.681201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:51.681201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Split Q Learning: Reinforcement Learning with Two-Stream Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi","submitted_at":"2019-06-21T01:59:52Z","abstract_excerpt":"Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to unders"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12350","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.12350/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":"1906.12350","created_at":"2026-07-05T00:18:51.681257+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12350v2","created_at":"2026-07-05T00:18:51.681257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12350","created_at":"2026-07-05T00:18:51.681257+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQGEHEZHGPWO","created_at":"2026-07-05T00:18:51.681257+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQGEHEZHGPWOAEC6","created_at":"2026-07-05T00:18:51.681257+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQGEHEZH","created_at":"2026-07-05T00:18:51.681257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16121","citing_title":"Predicting human cooperation: sensitizing drift-diffusion model to interaction and external stimuli","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5","json":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5.json","graph_json":"https://pith.science/api/pith-number/DQGEHEZHGPWOAEC6DKRPOHPEF5/graph.json","events_json":"https://pith.science/api/pith-number/DQGEHEZHGPWOAEC6DKRPOHPEF5/events.json","paper":"https://pith.science/paper/DQGEHEZH"},"agent_actions":{"view_html":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5","download_json":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5.json","view_paper":"https://pith.science/paper/DQGEHEZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12350&json=true","fetch_graph":"https://pith.science/api/pith-number/DQGEHEZHGPWOAEC6DKRPOHPEF5/graph.json","fetch_events":"https://pith.science/api/pith-number/DQGEHEZHGPWOAEC6DKRPOHPEF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5/action/storage_attestation","attest_author":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5/action/author_attestation","sign_citation":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5/action/citation_signature","submit_replication":"https://pith.science/pith/DQGEHEZHGPWOAEC6DKRPOHPEF5/action/replication_record"}},"created_at":"2026-07-05T00:18:51.681257+00:00","updated_at":"2026-07-05T00:18:51.681257+00:00"}