{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPYQHUDLWDQYICJFXOLIYXZMEO","short_pith_number":"pith:QPYQHUDL","schema_version":"1.0","canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","source":{"kind":"arxiv","id":"2607.13353","version":1},"attestation_state":"computed","paper":{"title":"Is Deep Hedging Reinforcement Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Fr\\'ed\\'eric Godin","submitted_at":"2026-07-15T00:24:42Z","abstract_excerpt":"The deep hedging framework of Buehler et al. (2019) trains a neural network policy, via Monte Carlo simulation of price paths and stochastic gradient descent, to minimize a risk measure applied to the terminal hedging error. In a recent stream of papers, my coauthors and I have referred to this technique as reinforcement learning (RL), a characterization that referees on several submissions have challenged on two grounds, among others: first, that because feedback is generated only at the terminal date, with no intermediate reward signal, the method cannot constitute genuine RL; and second, th"},"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":"2607.13353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2026-07-15T00:24:42Z","cross_cats_sorted":[],"title_canon_sha256":"24886ef94d0e09f10ab9b634e0cfcb3b3963fc03976c4b430f55c1dd72078572","abstract_canon_sha256":"9bbf53c63db3835ec6bcfff43b415d3ecc59542564886d45e8d09de0a46da23d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:13.745050Z","signature_b64":"KfdE2Cw3TOJVjVesYu7H/nceilrEkUX8aDI1M9gCC/D9EB4605xnMpcBQeX1RvtMuceVMOShikSC3R2A8e+qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","last_reissued_at":"2026-07-16T00:22:13.743742Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:13.743742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Deep Hedging Reinforcement Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Fr\\'ed\\'eric Godin","submitted_at":"2026-07-15T00:24:42Z","abstract_excerpt":"The deep hedging framework of Buehler et al. (2019) trains a neural network policy, via Monte Carlo simulation of price paths and stochastic gradient descent, to minimize a risk measure applied to the terminal hedging error. In a recent stream of papers, my coauthors and I have referred to this technique as reinforcement learning (RL), a characterization that referees on several submissions have challenged on two grounds, among others: first, that because feedback is generated only at the terminal date, with no intermediate reward signal, the method cannot constitute genuine RL; and second, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13353","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/2607.13353/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":"2607.13353","created_at":"2026-07-16T00:22:13.744650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13353v1","created_at":"2026-07-16T00:22:13.744650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13353","created_at":"2026-07-16T00:22:13.744650+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPYQHUDLWDQY","created_at":"2026-07-16T00:22:13.744650+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPYQHUDLWDQYICJF","created_at":"2026-07-16T00:22:13.744650+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPYQHUDL","created_at":"2026-07-16T00:22:13.744650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO","json":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO.json","graph_json":"https://pith.science/api/pith-number/QPYQHUDLWDQYICJFXOLIYXZMEO/graph.json","events_json":"https://pith.science/api/pith-number/QPYQHUDLWDQYICJFXOLIYXZMEO/events.json","paper":"https://pith.science/paper/QPYQHUDL"},"agent_actions":{"view_html":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO","download_json":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO.json","view_paper":"https://pith.science/paper/QPYQHUDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13353&json=true","fetch_graph":"https://pith.science/api/pith-number/QPYQHUDLWDQYICJFXOLIYXZMEO/graph.json","fetch_events":"https://pith.science/api/pith-number/QPYQHUDLWDQYICJFXOLIYXZMEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/action/storage_attestation","attest_author":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/action/author_attestation","sign_citation":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/action/citation_signature","submit_replication":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/action/replication_record"}},"created_at":"2026-07-16T00:22:13.744650+00:00","updated_at":"2026-07-16T00:22:13.744650+00:00"}