{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M7ZM724CKQ2U42G4Q36SAW6LNB","short_pith_number":"pith:M7ZM724C","schema_version":"1.0","canonical_sha256":"67f2cfeb8254354e68dc86fd205bcb6851ff5832fec39cc7e0aa33e16a753127","source":{"kind":"arxiv","id":"2603.07600","version":4},"attestation_state":"computed","paper":{"title":"Differential Machine Learning for 0DTE Options with Stochastic Volatility and Jumps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-stage differential machine learning procedure approximates jump terms more accurately in ultra-short maturity options while preserving pricing accuracy and delivering faster Greeks than Fourier methods.","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Takayuki Sakuma","submitted_at":"2026-03-08T12:10:24Z","abstract_excerpt":"We present a differential machine learning method for zero-days-to-expiry (0DTE) options under a stochastic-volatility jump-diffusion model. To handle the ultra-short-maturity regime, we express the option price in Black-Scholes form with a maturity-gated variance correction, combining supervision on prices and Greeks with a PIDE-residual penalty. Prices and Greeks are derived from a single trained pricing network, while jump-term identifiability is ensured by a jump-operator network fitted jointly in a three-stage procedure. The method improves jump-term approximation relative to one-stage ba"},"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":"2603.07600","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2026-03-08T12:10:24Z","cross_cats_sorted":[],"title_canon_sha256":"9a9040508f4b80e7a6d6fd4777c881eab81d45e3a0b132ecd32343f8c2754abb","abstract_canon_sha256":"0d82d2e74083e135083ed3672a40da590a481fb8deca130cc5ff40e29bc54fd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:23.352728Z","signature_b64":"EJZHaESIZFr6Ftz/iRyXPUbXano2/0AXIAFMOvrHuw62vBzfhlYUhWzhYsMRQhSuRAZc6+UA70zR/ARXaloCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f2cfeb8254354e68dc86fd205bcb6851ff5832fec39cc7e0aa33e16a753127","last_reissued_at":"2026-06-09T02:07:23.351847Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:23.351847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differential Machine Learning for 0DTE Options with Stochastic Volatility and Jumps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-stage differential machine learning procedure approximates jump terms more accurately in ultra-short maturity options while preserving pricing accuracy and delivering faster Greeks than Fourier methods.","cross_cats":[],"primary_cat":"q-fin.CP","authors_text":"Takayuki Sakuma","submitted_at":"2026-03-08T12:10:24Z","abstract_excerpt":"We present a differential machine learning method for zero-days-to-expiry (0DTE) options under a stochastic-volatility jump-diffusion model. To handle the ultra-short-maturity regime, we express the option price in Black-Scholes form with a maturity-gated variance correction, combining supervision on prices and Greeks with a PIDE-residual penalty. Prices and Greeks are derived from a single trained pricing network, while jump-term identifiability is ensured by a jump-operator network fitted jointly in a three-stage procedure. The method improves jump-term approximation relative to one-stage ba"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The method improves jump-term approximation relative to one-stage baselines while maintaining comparable pricing errors. Furthermore, it reduces errors in Greeks, produces stable one-day delta hedges, and offers significant speedups over Fourier-based benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three-stage joint training of pricing and jump-operator networks, together with the maturity-gated variance correction, reliably identifies jump terms and produces accurate Greeks for ultra-short maturities without overfitting to the specific training data or model assumptions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A three-stage differential ML method prices 0DTE options under SVJD by combining Black-Scholes with maturity-gated variance correction, joint pricing and jump-operator networks, and PIDE-residual penalties to improve jump approximation and Greeks while speeding up computation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A three-stage differential machine learning procedure approximates jump terms more accurately in ultra-short maturity options while preserving pricing accuracy and delivering faster Greeks than Fourier methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"45ebb2b1bbc677e2f4668afc6e37d4e2af8880c955735bb759ca84336d0f009f"},"source":{"id":"2603.07600","kind":"arxiv","version":4},"verdict":{"id":"a56ac7a9-b345-4c3d-829c-7d1cd571f30e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:55:45.002559Z","strongest_claim":"The method improves jump-term approximation relative to one-stage baselines while maintaining comparable pricing errors. Furthermore, it reduces errors in Greeks, produces stable one-day delta hedges, and offers significant speedups over Fourier-based benchmarks.","one_line_summary":"A three-stage differential ML method prices 0DTE options under SVJD by combining Black-Scholes with maturity-gated variance correction, joint pricing and jump-operator networks, and PIDE-residual penalties to improve jump approximation and Greeks while speeding up computation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three-stage joint training of pricing and jump-operator networks, together with the maturity-gated variance correction, reliably identifies jump terms and produces accurate Greeks for ultra-short maturities without overfitting to the specific training data or model assumptions.","pith_extraction_headline":"A three-stage differential machine learning procedure approximates jump terms more accurately in ultra-short maturity options while preserving pricing accuracy and delivering faster Greeks than Fourier methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.07600/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":"2603.07600","created_at":"2026-06-09T02:07:23.351982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07600v4","created_at":"2026-06-09T02:07:23.351982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07600","created_at":"2026-06-09T02:07:23.351982+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7ZM724CKQ2U","created_at":"2026-06-09T02:07:23.351982+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7ZM724CKQ2U42G4","created_at":"2026-06-09T02:07:23.351982+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7ZM724C","created_at":"2026-06-09T02:07:23.351982+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/M7ZM724CKQ2U42G4Q36SAW6LNB","json":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB.json","graph_json":"https://pith.science/api/pith-number/M7ZM724CKQ2U42G4Q36SAW6LNB/graph.json","events_json":"https://pith.science/api/pith-number/M7ZM724CKQ2U42G4Q36SAW6LNB/events.json","paper":"https://pith.science/paper/M7ZM724C"},"agent_actions":{"view_html":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB","download_json":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB.json","view_paper":"https://pith.science/paper/M7ZM724C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07600&json=true","fetch_graph":"https://pith.science/api/pith-number/M7ZM724CKQ2U42G4Q36SAW6LNB/graph.json","fetch_events":"https://pith.science/api/pith-number/M7ZM724CKQ2U42G4Q36SAW6LNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB/action/storage_attestation","attest_author":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB/action/author_attestation","sign_citation":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB/action/citation_signature","submit_replication":"https://pith.science/pith/M7ZM724CKQ2U42G4Q36SAW6LNB/action/replication_record"}},"created_at":"2026-06-09T02:07:23.351982+00:00","updated_at":"2026-06-09T02:07:23.351982+00:00"}