{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VQRMP3OSFWA57IQV2PPKOV22YK","short_pith_number":"pith:VQRMP3OS","schema_version":"1.0","canonical_sha256":"ac22c7edd22d81dfa215d3dea7575ac28044e07bbf4db3881910652712f309f5","source":{"kind":"arxiv","id":"2005.07039","version":1},"attestation_state":"computed","paper":{"title":"On the derivatives of feed-forward neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ph"],"primary_cat":"physics.comp-ph","authors_text":"Rabah Abdul Khalek, Valerio Bertone","submitted_at":"2020-05-12T14:24:41Z","abstract_excerpt":"In this paper we present a C++ implementation of the analytic derivative of a feed-forward neural network with respect to its free parameters for an arbitrary architecture, known as back-propagation. We dubbed this code NNAD (Neural Network Analytic Derivatives) and interfaced it with the widely-used ceres-solver minimiser to fit neural networks to pseudodata in two different least-squares problems. The first is a direct fit of Legendre polynomials. The second is a somewhat more involved minimisation problem where the function to be fitted takes part in an integral. Finally, using a consistent"},"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":"2005.07039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2020-05-12T14:24:41Z","cross_cats_sorted":["hep-ph"],"title_canon_sha256":"3b110f6f182b53765d15f45ede155d3016a68753517386d64651605a4566a463","abstract_canon_sha256":"9528eb46879ce4e48f7eba44aae9e3915e8f9bb9eb83b11bec95f4a4325386cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:52.825343Z","signature_b64":"ZHGQnCyOxVMrw1JYAC0gLm0NBPbKhJmovo0Rr63nfw+I4BTN5QzP/E/koC3RPLRzGpfwBwB5QQK9HAwPajoFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac22c7edd22d81dfa215d3dea7575ac28044e07bbf4db3881910652712f309f5","last_reissued_at":"2026-07-05T01:02:52.824899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:52.824899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the derivatives of feed-forward neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["hep-ph"],"primary_cat":"physics.comp-ph","authors_text":"Rabah Abdul Khalek, Valerio Bertone","submitted_at":"2020-05-12T14:24:41Z","abstract_excerpt":"In this paper we present a C++ implementation of the analytic derivative of a feed-forward neural network with respect to its free parameters for an arbitrary architecture, known as back-propagation. We dubbed this code NNAD (Neural Network Analytic Derivatives) and interfaced it with the widely-used ceres-solver minimiser to fit neural networks to pseudodata in two different least-squares problems. The first is a direct fit of Legendre polynomials. The second is a somewhat more involved minimisation problem where the function to be fitted takes part in an integral. Finally, using a consistent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07039","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/2005.07039/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":"2005.07039","created_at":"2026-07-05T01:02:52.824964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.07039v1","created_at":"2026-07-05T01:02:52.824964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07039","created_at":"2026-07-05T01:02:52.824964+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQRMP3OSFWA5","created_at":"2026-07-05T01:02:52.824964+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQRMP3OSFWA57IQV","created_at":"2026-07-05T01:02:52.824964+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQRMP3OS","created_at":"2026-07-05T01:02:52.824964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31325","citing_title":"Revisiting Unidentified Charged-Hadron Fragmentation Functions with Modern COMPASS SIDIS Multiplicities","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05314","citing_title":"First next-to-next-to-leading-order extraction of fragmentation functions for Lambda hyperons","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK","json":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK.json","graph_json":"https://pith.science/api/pith-number/VQRMP3OSFWA57IQV2PPKOV22YK/graph.json","events_json":"https://pith.science/api/pith-number/VQRMP3OSFWA57IQV2PPKOV22YK/events.json","paper":"https://pith.science/paper/VQRMP3OS"},"agent_actions":{"view_html":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK","download_json":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK.json","view_paper":"https://pith.science/paper/VQRMP3OS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.07039&json=true","fetch_graph":"https://pith.science/api/pith-number/VQRMP3OSFWA57IQV2PPKOV22YK/graph.json","fetch_events":"https://pith.science/api/pith-number/VQRMP3OSFWA57IQV2PPKOV22YK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK/action/storage_attestation","attest_author":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK/action/author_attestation","sign_citation":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK/action/citation_signature","submit_replication":"https://pith.science/pith/VQRMP3OSFWA57IQV2PPKOV22YK/action/replication_record"}},"created_at":"2026-07-05T01:02:52.824964+00:00","updated_at":"2026-07-05T01:02:52.824964+00:00"}