{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJGDJ5W4ZJ5PB2GYVDKHON3EKS","short_pith_number":"pith:HJGDJ5W4","schema_version":"1.0","canonical_sha256":"3a4c34f6dcca7af0e8d8a8d477376454a44eea50b551ed9533b823186c5ab345","source":{"kind":"arxiv","id":"2606.08379","version":1},"attestation_state":"computed","paper":{"title":"TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade Execution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.LG","q-fin.CP","q-fin.TR"],"primary_cat":"cs.AI","authors_text":"Alfonso Dufour, Atta Badii, Ilia Zaznov, Julian Kunkel","submitted_at":"2026-06-07T00:20:29Z","abstract_excerpt":"This study addresses the optimal execution of large stock sell programs by introducing TT-DAC-PS (Twin-Target Deterministic Actor-Critic with Policy Smoothing), a deterministic actor-critic architecture that combines twin exponential-moving-average critic targets with pessimistic min backup, TD3-style target policy smoothing noise, delayed actor updates, and conservative Q regularisation to curb overestimation. Exploration uses Ornstein-Uhlenbeck (OU) noise with a hybrid schedule: deterministic episode-wise decay, variance-guided adjustment based on recent reward dispersion, and a Soft Actor-C"},"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":"2606.08379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T00:20:29Z","cross_cats_sorted":["cs.CE","cs.LG","q-fin.CP","q-fin.TR"],"title_canon_sha256":"a0ad03594cad693bcb7d76a032a6aef3c123b5758255ccc034ada3804c8d5660","abstract_canon_sha256":"8461cc9610deaf7c1b7c697236852714c3ea6602e5ead7ec4691fa6edfd9ef28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:35.183939Z","signature_b64":"QA850rNTkizIqEeV1wqu9m7yvlD3uFnDy7hqLY8vqhdK+tuPWVlyaW8CDp8gtf8n6wIB3lAFt1db/t7esOu7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a4c34f6dcca7af0e8d8a8d477376454a44eea50b551ed9533b823186c5ab345","last_reissued_at":"2026-06-09T01:05:35.183519Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:35.183519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade Execution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","cs.LG","q-fin.CP","q-fin.TR"],"primary_cat":"cs.AI","authors_text":"Alfonso Dufour, Atta Badii, Ilia Zaznov, Julian Kunkel","submitted_at":"2026-06-07T00:20:29Z","abstract_excerpt":"This study addresses the optimal execution of large stock sell programs by introducing TT-DAC-PS (Twin-Target Deterministic Actor-Critic with Policy Smoothing), a deterministic actor-critic architecture that combines twin exponential-moving-average critic targets with pessimistic min backup, TD3-style target policy smoothing noise, delayed actor updates, and conservative Q regularisation to curb overestimation. Exploration uses Ornstein-Uhlenbeck (OU) noise with a hybrid schedule: deterministic episode-wise decay, variance-guided adjustment based on recent reward dispersion, and a Soft Actor-C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08379","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/2606.08379/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":"2606.08379","created_at":"2026-06-09T01:05:35.183583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08379v1","created_at":"2026-06-09T01:05:35.183583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08379","created_at":"2026-06-09T01:05:35.183583+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJGDJ5W4ZJ5P","created_at":"2026-06-09T01:05:35.183583+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJGDJ5W4ZJ5PB2GY","created_at":"2026-06-09T01:05:35.183583+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJGDJ5W4","created_at":"2026-06-09T01:05:35.183583+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/HJGDJ5W4ZJ5PB2GYVDKHON3EKS","json":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS.json","graph_json":"https://pith.science/api/pith-number/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/graph.json","events_json":"https://pith.science/api/pith-number/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/events.json","paper":"https://pith.science/paper/HJGDJ5W4"},"agent_actions":{"view_html":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS","download_json":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS.json","view_paper":"https://pith.science/paper/HJGDJ5W4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08379&json=true","fetch_graph":"https://pith.science/api/pith-number/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/graph.json","fetch_events":"https://pith.science/api/pith-number/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/action/storage_attestation","attest_author":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/action/author_attestation","sign_citation":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/action/citation_signature","submit_replication":"https://pith.science/pith/HJGDJ5W4ZJ5PB2GYVDKHON3EKS/action/replication_record"}},"created_at":"2026-06-09T01:05:35.183583+00:00","updated_at":"2026-06-09T01:05:35.183583+00:00"}