{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QPYQHUDLWDQYICJFXOLIYXZMEO","short_pith_number":"pith:QPYQHUDL","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"},"canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","source":{"kind":"arxiv","id":"2607.13353","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13353","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13353v1","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13353","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"QPYQHUDLWDQY","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"QPYQHUDLWDQYICJF","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"QPYQHUDL","created_at":"2026-07-16T00:22:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QPYQHUDLWDQYICJFXOLIYXZMEO","target":"record","payload":{"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"},"canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","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"},"source_kind":"arxiv","source_id":"2607.13353","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T00:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKTR07X2B5lYhcq7xTKhFfSsGk/RGDPtnb0Kb/4er+hKqHNLPBX1dxADLvgjkGNLBs/19hb2qsxj3kl00kW7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:15:42.170179Z"},"content_sha256":"c8f1b5b0ce2f66443364e89a383117fb6dd5c74f1315e87e750e2c76954725fc","schema_version":"1.0","event_id":"sha256:c8f1b5b0ce2f66443364e89a383117fb6dd5c74f1315e87e750e2c76954725fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QPYQHUDLWDQYICJFXOLIYXZMEO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T00:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Vpm3eQPVioIZjmoq5PmBmxCarWa8xso8JyLbMiQcUuRg7y5E/XorouATkWXRXU8Bkk84UQDYUW03rhI8VzwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:15:42.170718Z"},"content_sha256":"971b57c38aa2554628b8a03d8796f068c1d1c2666ceb9f1cc737066d711a3b3d","schema_version":"1.0","event_id":"sha256:971b57c38aa2554628b8a03d8796f068c1d1c2666ceb9f1cc737066d711a3b3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/bundle.json","state_url":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:15:42Z","links":{"resolver":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO","bundle":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/bundle.json","state":"https://pith.science/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPYQHUDLWDQYICJFXOLIYXZMEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPYQHUDLWDQYICJFXOLIYXZMEO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9bbf53c63db3835ec6bcfff43b415d3ecc59542564886d45e8d09de0a46da23d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2026-07-15T00:24:42Z","title_canon_sha256":"24886ef94d0e09f10ab9b634e0cfcb3b3963fc03976c4b430f55c1dd72078572"},"schema_version":"1.0","source":{"id":"2607.13353","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13353","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13353v1","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13353","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"QPYQHUDLWDQY","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"QPYQHUDLWDQYICJF","created_at":"2026-07-16T00:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"QPYQHUDL","created_at":"2026-07-16T00:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:971b57c38aa2554628b8a03d8796f068c1d1c2666ceb9f1cc737066d711a3b3d","target":"graph","created_at":"2026-07-16T00:22:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.13353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fr\\'ed\\'eric Godin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2026-07-15T00:24:42Z","title":"Is Deep Hedging Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13353","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8f1b5b0ce2f66443364e89a383117fb6dd5c74f1315e87e750e2c76954725fc","target":"record","created_at":"2026-07-16T00:22:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9bbf53c63db3835ec6bcfff43b415d3ecc59542564886d45e8d09de0a46da23d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2026-07-15T00:24:42Z","title_canon_sha256":"24886ef94d0e09f10ab9b634e0cfcb3b3963fc03976c4b430f55c1dd72078572"},"schema_version":"1.0","source":{"id":"2607.13353","kind":"arxiv","version":1}},"canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83f103d06bb0e1840925bb968c5f2c238e55220c0bf61a9acfd36fe6966be14d","first_computed_at":"2026-07-16T00:22:13.743742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:13.743742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KfdE2Cw3TOJVjVesYu7H/nceilrEkUX8aDI1M9gCC/D9EB4605xnMpcBQeX1RvtMuceVMOShikSC3R2A8e+qBQ==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:13.745050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13353","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8f1b5b0ce2f66443364e89a383117fb6dd5c74f1315e87e750e2c76954725fc","sha256:971b57c38aa2554628b8a03d8796f068c1d1c2666ceb9f1cc737066d711a3b3d"],"state_sha256":"2da1d5e07e233eeb45b9167be878da5cd23af42760ba9ec819c8c0687ea19935"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bNVQE8Uz7lBo70QkOz2wYIsNx3dW+wIMr+mN/fAdmp36nBv6wrtf6lP5qQLoRUEwD5fHYJFLEGcqbkl4paXDBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:15:42.182196Z","bundle_sha256":"067170aa8856ba6117080c36c940c4a4e0b80b087d824819343e6978427d7fdf"}}