{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJGXGWHKUV2HDERYHMYLTDEKIN","short_pith_number":"pith:GJGXGWHK","schema_version":"1.0","canonical_sha256":"324d7358eaa5747192383b30b98c8a435879423cb5e5b14ded0b8ba7b930c9c5","source":{"kind":"arxiv","id":"2507.09916","version":3},"attestation_state":"computed","paper":{"title":"Solving dynamic portfolio selection problems via score-based diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Ahmad Aghapour, Erhan Bayraktar, Fengyi Yuan","submitted_at":"2025-07-14T04:41:49Z","abstract_excerpt":"In this paper, we tackle the dynamic mean-variance portfolio selection problem in a {\\it model-free} manner, based on (generative) diffusion models. We propose using data sampled from the real model $\\mathbb P$ (which is unknown) with limited size to train a generative model $\\mathbb Q$ (from which we can easily and adequately sample). With adaptive training and sampling methods that are tailor-made for time series data, we obtain quantification bounds between $\\mathbb P$ and $\\mathbb Q$ in terms of the adapted Wasserstein metric $\\mathcal A W_2$. Importantly, the proposed adapted sampling met"},"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":"2507.09916","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2025-07-14T04:41:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"10f30aad02d0d840b0a4e56402f37263a5ac2c02d4053055c1626cc6d94f16bf","abstract_canon_sha256":"bc3435b5d74719f09dd3cd1a7faa42b06aaa83cd3b6104901f4e1d215e61089e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:03.633324Z","signature_b64":"XjL2o42IG5IRWivnczxzsonq4eJN4uMwFqkDGzeeWYfvJNSj67nuh9N/uV4LxscZp46oc6brqylLDO05sXBFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"324d7358eaa5747192383b30b98c8a435879423cb5e5b14ded0b8ba7b930c9c5","last_reissued_at":"2026-07-05T12:02:03.632666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:03.632666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving dynamic portfolio selection problems via score-based diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Ahmad Aghapour, Erhan Bayraktar, Fengyi Yuan","submitted_at":"2025-07-14T04:41:49Z","abstract_excerpt":"In this paper, we tackle the dynamic mean-variance portfolio selection problem in a {\\it model-free} manner, based on (generative) diffusion models. We propose using data sampled from the real model $\\mathbb P$ (which is unknown) with limited size to train a generative model $\\mathbb Q$ (from which we can easily and adequately sample). With adaptive training and sampling methods that are tailor-made for time series data, we obtain quantification bounds between $\\mathbb P$ and $\\mathbb Q$ in terms of the adapted Wasserstein metric $\\mathcal A W_2$. Importantly, the proposed adapted sampling met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09916","kind":"arxiv","version":3},"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/2507.09916/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":"2507.09916","created_at":"2026-07-05T12:02:03.632751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09916v3","created_at":"2026-07-05T12:02:03.632751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09916","created_at":"2026-07-05T12:02:03.632751+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJGXGWHKUV2H","created_at":"2026-07-05T12:02:03.632751+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJGXGWHKUV2HDERY","created_at":"2026-07-05T12:02:03.632751+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJGXGWHK","created_at":"2026-07-05T12:02:03.632751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.06007","citing_title":"Diffusion Models for Adaptive Sequential Data Generation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19391","citing_title":"Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN","json":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN.json","graph_json":"https://pith.science/api/pith-number/GJGXGWHKUV2HDERYHMYLTDEKIN/graph.json","events_json":"https://pith.science/api/pith-number/GJGXGWHKUV2HDERYHMYLTDEKIN/events.json","paper":"https://pith.science/paper/GJGXGWHK"},"agent_actions":{"view_html":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN","download_json":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN.json","view_paper":"https://pith.science/paper/GJGXGWHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09916&json=true","fetch_graph":"https://pith.science/api/pith-number/GJGXGWHKUV2HDERYHMYLTDEKIN/graph.json","fetch_events":"https://pith.science/api/pith-number/GJGXGWHKUV2HDERYHMYLTDEKIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN/action/storage_attestation","attest_author":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN/action/author_attestation","sign_citation":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN/action/citation_signature","submit_replication":"https://pith.science/pith/GJGXGWHKUV2HDERYHMYLTDEKIN/action/replication_record"}},"created_at":"2026-07-05T12:02:03.632751+00:00","updated_at":"2026-07-05T12:02:03.632751+00:00"}