{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQZJQDRRGQ7C5ZIES7WLHUWDWF","short_pith_number":"pith:CQZJQDRR","schema_version":"1.0","canonical_sha256":"1432980e31343e2ee50497ecb3d2c3b174e5d545373b89031e92b5532f6f7cc6","source":{"kind":"arxiv","id":"2405.08101","version":3},"attestation_state":"computed","paper":{"title":"Data-driven measures of high-frequency trading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-fin.CP","authors_text":"B. Moews, D. Muravyev, G. Ibikunle, K. Rzayev","submitted_at":"2024-05-13T18:28:39Z","abstract_excerpt":"High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed in a proprietary dataset using concurrent public intraday data. Once trained on the dataset, these models generate HFT measures for the entire U.S. stock universe from 2010 to 2023. Our measures outperform conventional proxies, which struggle to capture HFT's time dynamics. We further validate them "},"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":"2405.08101","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.CP","submitted_at":"2024-05-13T18:28:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"884e7de18f35bfeb3778b6476099265fdcc5be146b75964ecd5d2f9fc1804672","abstract_canon_sha256":"0edcc1590b80d516c046950047d74d56f58c3cce34321e1a7f01190a780ac8f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:25.145538Z","signature_b64":"f0vMQH2ZlY/R/anxvvC8oUTzT/St70h5WZlcE4jodtZIh+3hhEtvuZlbqlwvJPzMXHPB85yP4ahGkt83FlTRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1432980e31343e2ee50497ecb3d2c3b174e5d545373b89031e92b5532f6f7cc6","last_reissued_at":"2026-07-05T10:36:25.144642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:25.144642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-driven measures of high-frequency trading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-fin.CP","authors_text":"B. Moews, D. Muravyev, G. Ibikunle, K. Rzayev","submitted_at":"2024-05-13T18:28:39Z","abstract_excerpt":"High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed in a proprietary dataset using concurrent public intraday data. Once trained on the dataset, these models generate HFT measures for the entire U.S. stock universe from 2010 to 2023. Our measures outperform conventional proxies, which struggle to capture HFT's time dynamics. We further validate them "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08101","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/2405.08101/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":"2405.08101","created_at":"2026-07-05T10:36:25.144750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08101v3","created_at":"2026-07-05T10:36:25.144750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08101","created_at":"2026-07-05T10:36:25.144750+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQZJQDRRGQ7C","created_at":"2026-07-05T10:36:25.144750+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQZJQDRRGQ7C5ZIE","created_at":"2026-07-05T10:36:25.144750+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQZJQDRR","created_at":"2026-07-05T10:36:25.144750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19372","citing_title":"Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF","json":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF.json","graph_json":"https://pith.science/api/pith-number/CQZJQDRRGQ7C5ZIES7WLHUWDWF/graph.json","events_json":"https://pith.science/api/pith-number/CQZJQDRRGQ7C5ZIES7WLHUWDWF/events.json","paper":"https://pith.science/paper/CQZJQDRR"},"agent_actions":{"view_html":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF","download_json":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF.json","view_paper":"https://pith.science/paper/CQZJQDRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08101&json=true","fetch_graph":"https://pith.science/api/pith-number/CQZJQDRRGQ7C5ZIES7WLHUWDWF/graph.json","fetch_events":"https://pith.science/api/pith-number/CQZJQDRRGQ7C5ZIES7WLHUWDWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF/action/storage_attestation","attest_author":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF/action/author_attestation","sign_citation":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF/action/citation_signature","submit_replication":"https://pith.science/pith/CQZJQDRRGQ7C5ZIES7WLHUWDWF/action/replication_record"}},"created_at":"2026-07-05T10:36:25.144750+00:00","updated_at":"2026-07-05T10:36:25.144750+00:00"}