{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3N6ID7VYTYXMWIO5A67IZI3S3U","short_pith_number":"pith:3N6ID7VY","schema_version":"1.0","canonical_sha256":"db7c81feb89e2ecb21dd07be8ca372dd2f752606f1cab90dd45c8557f239cd38","source":{"kind":"arxiv","id":"2504.04242","version":2},"attestation_state":"computed","paper":{"title":"Task-based Loss Functions in Computer Vision: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Elarbi Badidi, Hamid Tairi, Jamal Riffi, Mohamed Adel Serhani, Omar Elharrouss, Yasir Mahmood, Yassine Bechqito","submitted_at":"2025-04-05T18:07:20Z","abstract_excerpt":"Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and ground truth labels, guiding the optimization process to minimize errors. Selecting the right loss function is critical, as it directly impacts model convergence, generalization, and overall performance across various applications, from computer vision to time series forecasting. This paper presents a comprehensive review of loss functions, covering fundamental metrics like Mean Squared Error and Cross-Entropy to adv"},"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":"2504.04242","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-05T18:07:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e11d09ffe8ca16d222023c01b9cdd7fa942f414ee93f83c67196f5b83f508e6a","abstract_canon_sha256":"2c2b61b08c1aa1369ab37d0d27dfacb7ba0fe9c49aa95ee26b5c6541d6b65553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:01.962722Z","signature_b64":"Ntjp6QjTirqXD/2VM58LTydPW0JvBx+dIMQupWH4fe8V0nNXKbOhgJ+HU59kwMu+FsuvnsM+XSVFPHMsZewnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db7c81feb89e2ecb21dd07be8ca372dd2f752606f1cab90dd45c8557f239cd38","last_reissued_at":"2026-07-05T12:08:01.962217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:01.962217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-based Loss Functions in Computer Vision: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Elarbi Badidi, Hamid Tairi, Jamal Riffi, Mohamed Adel Serhani, Omar Elharrouss, Yasir Mahmood, Yassine Bechqito","submitted_at":"2025-04-05T18:07:20Z","abstract_excerpt":"Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and ground truth labels, guiding the optimization process to minimize errors. Selecting the right loss function is critical, as it directly impacts model convergence, generalization, and overall performance across various applications, from computer vision to time series forecasting. This paper presents a comprehensive review of loss functions, covering fundamental metrics like Mean Squared Error and Cross-Entropy to adv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04242","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/2504.04242/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":"2504.04242","created_at":"2026-07-05T12:08:01.962274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04242v2","created_at":"2026-07-05T12:08:01.962274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04242","created_at":"2026-07-05T12:08:01.962274+00:00"},{"alias_kind":"pith_short_12","alias_value":"3N6ID7VYTYXM","created_at":"2026-07-05T12:08:01.962274+00:00"},{"alias_kind":"pith_short_16","alias_value":"3N6ID7VYTYXMWIO5","created_at":"2026-07-05T12:08:01.962274+00:00"},{"alias_kind":"pith_short_8","alias_value":"3N6ID7VY","created_at":"2026-07-05T12:08:01.962274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.02071","citing_title":"FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00407","citing_title":"Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11446","citing_title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U","json":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U.json","graph_json":"https://pith.science/api/pith-number/3N6ID7VYTYXMWIO5A67IZI3S3U/graph.json","events_json":"https://pith.science/api/pith-number/3N6ID7VYTYXMWIO5A67IZI3S3U/events.json","paper":"https://pith.science/paper/3N6ID7VY"},"agent_actions":{"view_html":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U","download_json":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U.json","view_paper":"https://pith.science/paper/3N6ID7VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04242&json=true","fetch_graph":"https://pith.science/api/pith-number/3N6ID7VYTYXMWIO5A67IZI3S3U/graph.json","fetch_events":"https://pith.science/api/pith-number/3N6ID7VYTYXMWIO5A67IZI3S3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U/action/storage_attestation","attest_author":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U/action/author_attestation","sign_citation":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U/action/citation_signature","submit_replication":"https://pith.science/pith/3N6ID7VYTYXMWIO5A67IZI3S3U/action/replication_record"}},"created_at":"2026-07-05T12:08:01.962274+00:00","updated_at":"2026-07-05T12:08:01.962274+00:00"}