{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VXI6AGKYUDPX4ETMX36LJXZ5FL","short_pith_number":"pith:VXI6AGKY","schema_version":"1.0","canonical_sha256":"add1e01958a0df7e126cbefcb4df3d2ac2f993d2301f91243391d89023414908","source":{"kind":"arxiv","id":"2112.08534","version":3},"attestation_state":"computed","paper":{"title":"Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kieran Wood, Stefan Zohren, Stephen Roberts, Sven Giegerich","submitted_at":"2021-12-16T00:04:12Z","abstract_excerpt":"We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM) architectures, which are sequential in nature and tailored to local processing, an attention mechanism provides our architecture with a direct connection to all previous time-steps. Our architecture, an attention-LSTM hybrid, enables us to learn longer-term dependencies, improves performance when considering returns net of transaction costs and naturally adapts to new m"},"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":"2112.08534","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T00:04:12Z","cross_cats_sorted":["q-fin.TR","stat.ML"],"title_canon_sha256":"131b8c6e54ca686f9f0b778226262e99a9bee135c75825458d4a295fb20c026c","abstract_canon_sha256":"fad5e330be56954e871fbae624b63062fbce1d61a7a11b3a18d12a64456bc194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:44.287395Z","signature_b64":"joAxxiGKn4yDvrlTcvhWhAm3gkAwPIAWEO6pxgDzrN6WnxIJ+2HJRazY+yRaeQI3KMopGuvXG/jjhB/U97fODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"add1e01958a0df7e126cbefcb4df3d2ac2f993d2301f91243391d89023414908","last_reissued_at":"2026-07-05T05:18:44.286899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:44.286899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kieran Wood, Stefan Zohren, Stephen Roberts, Sven Giegerich","submitted_at":"2021-12-16T00:04:12Z","abstract_excerpt":"We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM) architectures, which are sequential in nature and tailored to local processing, an attention mechanism provides our architecture with a direct connection to all previous time-steps. Our architecture, an attention-LSTM hybrid, enables us to learn longer-term dependencies, improves performance when considering returns net of transaction costs and naturally adapts to new m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08534","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/2112.08534/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":"2112.08534","created_at":"2026-07-05T05:18:44.286958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08534v3","created_at":"2026-07-05T05:18:44.286958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08534","created_at":"2026-07-05T05:18:44.286958+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXI6AGKYUDPX","created_at":"2026-07-05T05:18:44.286958+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXI6AGKYUDPX4ETM","created_at":"2026-07-05T05:18:44.286958+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXI6AGKY","created_at":"2026-07-05T05:18:44.286958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00475","citing_title":"End-to-End Parametric Portfolio Policies for Cross-Asset Futures Timing: When Do AI Models Beat Simple Rules?","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00624","citing_title":"Macro-aware time series forecasting via hierarchical mixed-frequency attention models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL","json":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL.json","graph_json":"https://pith.science/api/pith-number/VXI6AGKYUDPX4ETMX36LJXZ5FL/graph.json","events_json":"https://pith.science/api/pith-number/VXI6AGKYUDPX4ETMX36LJXZ5FL/events.json","paper":"https://pith.science/paper/VXI6AGKY"},"agent_actions":{"view_html":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL","download_json":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL.json","view_paper":"https://pith.science/paper/VXI6AGKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08534&json=true","fetch_graph":"https://pith.science/api/pith-number/VXI6AGKYUDPX4ETMX36LJXZ5FL/graph.json","fetch_events":"https://pith.science/api/pith-number/VXI6AGKYUDPX4ETMX36LJXZ5FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL/action/storage_attestation","attest_author":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL/action/author_attestation","sign_citation":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL/action/citation_signature","submit_replication":"https://pith.science/pith/VXI6AGKYUDPX4ETMX36LJXZ5FL/action/replication_record"}},"created_at":"2026-07-05T05:18:44.286958+00:00","updated_at":"2026-07-05T05:18:44.286958+00:00"}