{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5C32FAFVHNP3YMCE2R53VERBPP","short_pith_number":"pith:5C32FAFV","schema_version":"1.0","canonical_sha256":"e8b7a280b53b5fbc3044d47bba92217bc18eb5eceeed5268216748d494e699c6","source":{"kind":"arxiv","id":"2207.00932","version":4},"attestation_state":"computed","paper":{"title":"Deep Bellman Hedging","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["q-fin.ST"],"primary_cat":"q-fin.CP","authors_text":"Ben Wood, Hans Buehler, Phillip Murray","submitted_at":"2022-07-03T01:35:21Z","abstract_excerpt":"We present an actor-critic-type reinforcement learning algorithm for solving the problem of hedging a portfolio of financial instruments such as securities and over-the-counter derivatives using purely historic data. The key characteristics of our approach are: the ability to hedge with derivatives such as forwards, swaps, futures, options; incorporation of trading frictions such as trading cost and liquidity constraints; applicability for any reasonable portfolio of financial instruments; realistic, continuous state and action spaces; and formal risk-adjusted return objectives. Most important"},"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":"2207.00932","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-fin.CP","submitted_at":"2022-07-03T01:35:21Z","cross_cats_sorted":["q-fin.ST"],"title_canon_sha256":"0c33dc45e64696541f22f204d94bd8df8d6c30f3ad99aa954cf8801e642633e4","abstract_canon_sha256":"77a42e2df5312e0e64e8f577f2f1f5709e94a23f4e907710b32a19453d93c8f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:16.317855Z","signature_b64":"OW4I6DTaYLu6WLJvTK5SZ+I5lr2Fd2qpWZbWB49JzuEgmxlxgSmxuVcPpkJ65v0CkTNzAQy2trJ9gRp5E/+wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b7a280b53b5fbc3044d47bba92217bc18eb5eceeed5268216748d494e699c6","last_reissued_at":"2026-07-05T08:36:16.317294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:16.317294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Bellman Hedging","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["q-fin.ST"],"primary_cat":"q-fin.CP","authors_text":"Ben Wood, Hans Buehler, Phillip Murray","submitted_at":"2022-07-03T01:35:21Z","abstract_excerpt":"We present an actor-critic-type reinforcement learning algorithm for solving the problem of hedging a portfolio of financial instruments such as securities and over-the-counter derivatives using purely historic data. The key characteristics of our approach are: the ability to hedge with derivatives such as forwards, swaps, futures, options; incorporation of trading frictions such as trading cost and liquidity constraints; applicability for any reasonable portfolio of financial instruments; realistic, continuous state and action spaces; and formal risk-adjusted return objectives. Most important"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00932","kind":"arxiv","version":4},"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/2207.00932/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":"2207.00932","created_at":"2026-07-05T08:36:16.317367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00932v4","created_at":"2026-07-05T08:36:16.317367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00932","created_at":"2026-07-05T08:36:16.317367+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C32FAFVHNP3","created_at":"2026-07-05T08:36:16.317367+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C32FAFVHNP3YMCE","created_at":"2026-07-05T08:36:16.317367+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C32FAFV","created_at":"2026-07-05T08:36:16.317367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07299","citing_title":"Uncertainty-Aware Strategies: A Model-Agnostic Framework for Robust Financial Optimization through Subsampling","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP","json":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP.json","graph_json":"https://pith.science/api/pith-number/5C32FAFVHNP3YMCE2R53VERBPP/graph.json","events_json":"https://pith.science/api/pith-number/5C32FAFVHNP3YMCE2R53VERBPP/events.json","paper":"https://pith.science/paper/5C32FAFV"},"agent_actions":{"view_html":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP","download_json":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP.json","view_paper":"https://pith.science/paper/5C32FAFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00932&json=true","fetch_graph":"https://pith.science/api/pith-number/5C32FAFVHNP3YMCE2R53VERBPP/graph.json","fetch_events":"https://pith.science/api/pith-number/5C32FAFVHNP3YMCE2R53VERBPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP/action/storage_attestation","attest_author":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP/action/author_attestation","sign_citation":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP/action/citation_signature","submit_replication":"https://pith.science/pith/5C32FAFVHNP3YMCE2R53VERBPP/action/replication_record"}},"created_at":"2026-07-05T08:36:16.317367+00:00","updated_at":"2026-07-05T08:36:16.317367+00:00"}