{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PEELGEGNQGIAY6OSA5SSW754LX","short_pith_number":"pith:PEELGEGN","schema_version":"1.0","canonical_sha256":"7908b310cd81900c79d207652b7fbc5de47af3a6ae32f49e27634485767bea7c","source":{"kind":"arxiv","id":"2303.09935","version":4},"attestation_state":"computed","paper":{"title":"Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Arindam Banerjee, Geraldine Bessie Amali D, Mathew Mithra Noel, Venkataraman Muthiah-Nakarajan, Yug Oswal","submitted_at":"2023-03-17T12:52:06Z","abstract_excerpt":"All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that determines how incorrect outputs are penalized and can be tuned to improve performance. This paper shows that training speed and final accuracy of neural networks can significantly depend on the loss function used to train neural networks. In particular derivative values can be significantly different with different loss functions leading to significantly different "},"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":"2303.09935","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-03-17T12:52:06Z","cross_cats_sorted":[],"title_canon_sha256":"7d371955b4bc61b3b65b73a37df690cd591ca251b608ed4138f5e270fa286d68","abstract_canon_sha256":"7543822d744074b612b2b104658fc623958697c91d390b32e6d654ce60cca15a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:55.359840Z","signature_b64":"jDRlLGt7NGWD6yBErkxhGHT4cG+8JTvXJ8EuY+Kni9Vj0WevCpH+4jIWMu/EA4vkLpTQrIM5vb0wc5uquMruAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7908b310cd81900c79d207652b7fbc5de47af3a6ae32f49e27634485767bea7c","last_reissued_at":"2026-07-05T09:30:55.359335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:55.359335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Arindam Banerjee, Geraldine Bessie Amali D, Mathew Mithra Noel, Venkataraman Muthiah-Nakarajan, Yug Oswal","submitted_at":"2023-03-17T12:52:06Z","abstract_excerpt":"All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that determines how incorrect outputs are penalized and can be tuned to improve performance. This paper shows that training speed and final accuracy of neural networks can significantly depend on the loss function used to train neural networks. In particular derivative values can be significantly different with different loss functions leading to significantly different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09935","kind":"arxiv","version":4},"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/2303.09935/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":"2303.09935","created_at":"2026-07-05T09:30:55.359396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09935v4","created_at":"2026-07-05T09:30:55.359396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09935","created_at":"2026-07-05T09:30:55.359396+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEELGEGNQGIA","created_at":"2026-07-05T09:30:55.359396+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEELGEGNQGIAY6OS","created_at":"2026-07-05T09:30:55.359396+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEELGEGN","created_at":"2026-07-05T09:30:55.359396+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/PEELGEGNQGIAY6OSA5SSW754LX","json":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX.json","graph_json":"https://pith.science/api/pith-number/PEELGEGNQGIAY6OSA5SSW754LX/graph.json","events_json":"https://pith.science/api/pith-number/PEELGEGNQGIAY6OSA5SSW754LX/events.json","paper":"https://pith.science/paper/PEELGEGN"},"agent_actions":{"view_html":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX","download_json":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX.json","view_paper":"https://pith.science/paper/PEELGEGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09935&json=true","fetch_graph":"https://pith.science/api/pith-number/PEELGEGNQGIAY6OSA5SSW754LX/graph.json","fetch_events":"https://pith.science/api/pith-number/PEELGEGNQGIAY6OSA5SSW754LX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX/action/storage_attestation","attest_author":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX/action/author_attestation","sign_citation":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX/action/citation_signature","submit_replication":"https://pith.science/pith/PEELGEGNQGIAY6OSA5SSW754LX/action/replication_record"}},"created_at":"2026-07-05T09:30:55.359396+00:00","updated_at":"2026-07-05T09:30:55.359396+00:00"}