{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FK7UVWJZASMGVRODOKXV4DTWLU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9dfc1def78f745629c35d5b323cef35915e2baf25c83011d6de98153ad759d84","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T17:00:49Z","title_canon_sha256":"0be3c89ef24f4e65b48f539d8d51da484705f64b6a0c4a68d7ff28e5ed5a97d7"},"schema_version":"1.0","source":{"id":"2006.07322","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07322","created_at":"2026-07-05T03:24:54Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07322v5","created_at":"2026-07-05T03:24:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07322","created_at":"2026-07-05T03:24:54Z"},{"alias_kind":"pith_short_12","alias_value":"FK7UVWJZASMG","created_at":"2026-07-05T03:24:54Z"},{"alias_kind":"pith_short_16","alias_value":"FK7UVWJZASMGVROD","created_at":"2026-07-05T03:24:54Z"},{"alias_kind":"pith_short_8","alias_value":"FK7UVWJZ","created_at":"2026-07-05T03:24:54Z"}],"graph_snapshots":[{"event_id":"sha256:b20e3901ec404707745159a62b4dcb7d099882870f08418e4f5ae86d5ea228f2","target":"graph","created_at":"2026-07-05T03:24:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.07322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern neural architectures for classification tasks are trained using the cross-entropy loss, which is widely believed to be empirically superior to the square loss. In this work we provide evidence indicating that this belief may not be well-founded. We explore several major neural architectures and a range of standard benchmark datasets for NLP, automatic speech recognition (ASR) and computer vision tasks to show that these architectures, with the same hyper-parameter settings as reported in the literature, perform comparably or better when trained with the square loss, even after equalizin","authors_text":"Like Hui, Mikhail Belkin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T17:00:49Z","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07322","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36ffbb5eef074b7af8517e43ccd18263877fdef2c160837c244836901b2e6777","target":"record","created_at":"2026-07-05T03:24:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9dfc1def78f745629c35d5b323cef35915e2baf25c83011d6de98153ad759d84","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T17:00:49Z","title_canon_sha256":"0be3c89ef24f4e65b48f539d8d51da484705f64b6a0c4a68d7ff28e5ed5a97d7"},"schema_version":"1.0","source":{"id":"2006.07322","kind":"arxiv","version":5}},"canonical_sha256":"2abf4ad93904986ac5c372af5e0e765d31928a91304d02f66ee875631cbb19c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2abf4ad93904986ac5c372af5e0e765d31928a91304d02f66ee875631cbb19c3","first_computed_at":"2026-07-05T03:24:54.718562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:54.718562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cJwDoSiX2iQfg0d1h+qmtTg0ho8q8ZFWsP7W2LKGWzujidApOCo3zwnij43pEwyPznbcW8qaAAtmm+b7BTxRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:54.719067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07322","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36ffbb5eef074b7af8517e43ccd18263877fdef2c160837c244836901b2e6777","sha256:b20e3901ec404707745159a62b4dcb7d099882870f08418e4f5ae86d5ea228f2"],"state_sha256":"efed7c24908e18b9e78c22915bf2f5d48610351cdedbca3ade60a59042951fd6"}