{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OBWZQ353DCTDGVSZV6WVPXIT6V","short_pith_number":"pith:OBWZQ353","schema_version":"1.0","canonical_sha256":"706d986fbb18a6335659afad57dd13f57bd2db4b856f32698126d463c83e2e16","source":{"kind":"arxiv","id":"2507.16548","version":2},"attestation_state":"computed","paper":{"title":"Alternative Loss Function in Evaluation of Transformer Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","q-fin.TR"],"primary_cat":"q-fin.CP","authors_text":"Jakub Micha\\'nk\\'ow, Pawe{\\l} Sakowski, Robert \\'Slepaczuk","submitted_at":"2025-07-22T12:57:25Z","abstract_excerpt":"The proper design and architecture of testing machine learning models, especially in their application to quantitative finance problems, is crucial. The most important aspect of this process is selecting an adequate loss function for training, validation, estimation purposes, and hyperparameter tuning. Therefore, in this research, through empirical experiments on equity and cryptocurrency assets, we apply the Mean Absolute Directional Loss (MADL) function, which is more adequate for optimizing forecast-generating models used in algorithmic investment strategies. The MADL function results are 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":"2507.16548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.CP","submitted_at":"2025-07-22T12:57:25Z","cross_cats_sorted":["cs.LG","q-fin.TR"],"title_canon_sha256":"06737da65614b37f654f6fbe62ba74cff206ed5784746419309e6197116eeee3","abstract_canon_sha256":"22ebaa0e86421f4bbb8301efc94d9ecf7195279f8296413b252398566388c518"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:33.651178Z","signature_b64":"Ns0Z42MbyFNEOQ5kNeDLDYrQhPp5cSCUMft9ug7chIHlD7iqE6VghH7CGnESuR+QzVh5e8AozEPJ8xQ8BaNMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706d986fbb18a6335659afad57dd13f57bd2db4b856f32698126d463c83e2e16","last_reissued_at":"2026-07-05T11:42:33.650709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:33.650709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alternative Loss Function in Evaluation of Transformer Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","q-fin.TR"],"primary_cat":"q-fin.CP","authors_text":"Jakub Micha\\'nk\\'ow, Pawe{\\l} Sakowski, Robert \\'Slepaczuk","submitted_at":"2025-07-22T12:57:25Z","abstract_excerpt":"The proper design and architecture of testing machine learning models, especially in their application to quantitative finance problems, is crucial. The most important aspect of this process is selecting an adequate loss function for training, validation, estimation purposes, and hyperparameter tuning. Therefore, in this research, through empirical experiments on equity and cryptocurrency assets, we apply the Mean Absolute Directional Loss (MADL) function, which is more adequate for optimizing forecast-generating models used in algorithmic investment strategies. The MADL function results are c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16548","kind":"arxiv","version":2},"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/2507.16548/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":"2507.16548","created_at":"2026-07-05T11:42:33.650773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16548v2","created_at":"2026-07-05T11:42:33.650773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16548","created_at":"2026-07-05T11:42:33.650773+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBWZQ353DCTD","created_at":"2026-07-05T11:42:33.650773+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBWZQ353DCTDGVSZ","created_at":"2026-07-05T11:42:33.650773+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBWZQ353","created_at":"2026-07-05T11:42:33.650773+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/OBWZQ353DCTDGVSZV6WVPXIT6V","json":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V.json","graph_json":"https://pith.science/api/pith-number/OBWZQ353DCTDGVSZV6WVPXIT6V/graph.json","events_json":"https://pith.science/api/pith-number/OBWZQ353DCTDGVSZV6WVPXIT6V/events.json","paper":"https://pith.science/paper/OBWZQ353"},"agent_actions":{"view_html":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V","download_json":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V.json","view_paper":"https://pith.science/paper/OBWZQ353","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16548&json=true","fetch_graph":"https://pith.science/api/pith-number/OBWZQ353DCTDGVSZV6WVPXIT6V/graph.json","fetch_events":"https://pith.science/api/pith-number/OBWZQ353DCTDGVSZV6WVPXIT6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V/action/storage_attestation","attest_author":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V/action/author_attestation","sign_citation":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V/action/citation_signature","submit_replication":"https://pith.science/pith/OBWZQ353DCTDGVSZV6WVPXIT6V/action/replication_record"}},"created_at":"2026-07-05T11:42:33.650773+00:00","updated_at":"2026-07-05T11:42:33.650773+00:00"}