{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SJ3Z46U3PM2254RQR4EROZAWYW","short_pith_number":"pith:SJ3Z46U3","schema_version":"1.0","canonical_sha256":"92779e7a9b7b35aef2308f09176416c5af663e618e5f2cf113b00366b540237b","source":{"kind":"arxiv","id":"2306.12964","version":1},"attestation_state":"computed","paper":{"title":"Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","q-fin.CP"],"primary_cat":"q-fin.ST","authors_text":"Dandan Tu, Feiyang Pan, Hongyan Xue, Jia He, Qing He, Shuo Yu, Xiang Ao","submitted_at":"2023-05-25T13:41:07Z","abstract_excerpt":"In the field of quantitative trading, it is common practice to transform raw historical stock data into indicative signals for the market trend. Such signals are called alpha factors. Alphas in formula forms are more interpretable and thus favored by practitioners concerned with risk. In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together. However, most traditional alpha generators mine alphas one by one separately, overlooking the fact that the alphas would be combined later. In t"},"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":"2306.12964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2023-05-25T13:41:07Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG","q-fin.CP"],"title_canon_sha256":"64ddb81009ebd4da1d89d809f14cbf7c362e44df59547e6ce8674de330d67c31","abstract_canon_sha256":"0cb4b759559ef06c1dddbb29762d805b4e489439f6d40d98a8b00225c5bd0bff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:50.777306Z","signature_b64":"cgZDjHJ5JCsNJn2Y3rdeoVJa/ZnMNk4bXRGqEjk95dzv7FzYXsFBpxcJFCOif+pwCLqxGpa3Hc/GlCkoV9dpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92779e7a9b7b35aef2308f09176416c5af663e618e5f2cf113b00366b540237b","last_reissued_at":"2026-07-05T06:23:50.776845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:50.776845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","q-fin.CP"],"primary_cat":"q-fin.ST","authors_text":"Dandan Tu, Feiyang Pan, Hongyan Xue, Jia He, Qing He, Shuo Yu, Xiang Ao","submitted_at":"2023-05-25T13:41:07Z","abstract_excerpt":"In the field of quantitative trading, it is common practice to transform raw historical stock data into indicative signals for the market trend. Such signals are called alpha factors. Alphas in formula forms are more interpretable and thus favored by practitioners concerned with risk. In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together. However, most traditional alpha generators mine alphas one by one separately, overlooking the fact that the alphas would be combined later. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12964","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/2306.12964/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":"2306.12964","created_at":"2026-07-05T06:23:50.776905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12964v1","created_at":"2026-07-05T06:23:50.776905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12964","created_at":"2026-07-05T06:23:50.776905+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJ3Z46U3PM22","created_at":"2026-07-05T06:23:50.776905+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJ3Z46U3PM2254RQ","created_at":"2026-07-05T06:23:50.776905+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJ3Z46U3","created_at":"2026-07-05T06:23:50.776905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12841","citing_title":"AQuA: Recursively Self-Improving Quantitative Trading Research Agents","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW","json":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW.json","graph_json":"https://pith.science/api/pith-number/SJ3Z46U3PM2254RQR4EROZAWYW/graph.json","events_json":"https://pith.science/api/pith-number/SJ3Z46U3PM2254RQR4EROZAWYW/events.json","paper":"https://pith.science/paper/SJ3Z46U3"},"agent_actions":{"view_html":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW","download_json":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW.json","view_paper":"https://pith.science/paper/SJ3Z46U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12964&json=true","fetch_graph":"https://pith.science/api/pith-number/SJ3Z46U3PM2254RQR4EROZAWYW/graph.json","fetch_events":"https://pith.science/api/pith-number/SJ3Z46U3PM2254RQR4EROZAWYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW/action/storage_attestation","attest_author":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW/action/author_attestation","sign_citation":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW/action/citation_signature","submit_replication":"https://pith.science/pith/SJ3Z46U3PM2254RQR4EROZAWYW/action/replication_record"}},"created_at":"2026-07-05T06:23:50.776905+00:00","updated_at":"2026-07-05T06:23:50.776905+00:00"}