{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:H7X2XQBB4IBAKA54FBXNKIRIN4","short_pith_number":"pith:H7X2XQBB","schema_version":"1.0","canonical_sha256":"3fefabc021e2020503bc286ed522286f099de939b241cf552b45cec248ec1aee","source":{"kind":"arxiv","id":"1612.00775","version":2},"attestation_state":"computed","paper":{"title":"A simple squared-error reformulation for ordinal classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher Beckham, Christopher Pal","submitted_at":"2016-12-02T17:57:04Z","abstract_excerpt":"In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes. Our formulation is based on the use of a softmax hidden layer, which has received relatively little attention in the literature. We empirically evaluate its performance on the Kaggle diabetic retinopathy dataset, an ordinal and high-resolution dataset and show that it outperforms all of t"},"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":"1612.00775","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-02T17:57:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f3a798656518bcfbc5e74d5504110a0e29e1598de54742c41c088059045ffa0","abstract_canon_sha256":"b8612d60957d1e9f17f04fc7ce18fea7e2d144d4ac340d3c2b66db540edb678d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:11.939005Z","signature_b64":"diDzHBAF83rjhDylCym+g6V3ygRxbyGfO2bWIs29UzZ6dEJjXSqBaa/nGdj3lPbcl4TgVpWtpPj70usuj77HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fefabc021e2020503bc286ed522286f099de939b241cf552b45cec248ec1aee","last_reissued_at":"2026-05-18T00:53:11.938613Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:11.938613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A simple squared-error reformulation for ordinal classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christopher Beckham, Christopher Pal","submitted_at":"2016-12-02T17:57:04Z","abstract_excerpt":"In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes. Our formulation is based on the use of a softmax hidden layer, which has received relatively little attention in the literature. We empirically evaluate its performance on the Kaggle diabetic retinopathy dataset, an ordinal and high-resolution dataset and show that it outperforms all of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00775","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":""},"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":"1612.00775","created_at":"2026-05-18T00:53:11.938677+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00775v2","created_at":"2026-05-18T00:53:11.938677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00775","created_at":"2026-05-18T00:53:11.938677+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7X2XQBB4IBA","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7X2XQBB4IBAKA54","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7X2XQBB","created_at":"2026-05-18T12:30:19.053100+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/H7X2XQBB4IBAKA54FBXNKIRIN4","json":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4.json","graph_json":"https://pith.science/api/pith-number/H7X2XQBB4IBAKA54FBXNKIRIN4/graph.json","events_json":"https://pith.science/api/pith-number/H7X2XQBB4IBAKA54FBXNKIRIN4/events.json","paper":"https://pith.science/paper/H7X2XQBB"},"agent_actions":{"view_html":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4","download_json":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4.json","view_paper":"https://pith.science/paper/H7X2XQBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00775&json=true","fetch_graph":"https://pith.science/api/pith-number/H7X2XQBB4IBAKA54FBXNKIRIN4/graph.json","fetch_events":"https://pith.science/api/pith-number/H7X2XQBB4IBAKA54FBXNKIRIN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4/action/storage_attestation","attest_author":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4/action/author_attestation","sign_citation":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4/action/citation_signature","submit_replication":"https://pith.science/pith/H7X2XQBB4IBAKA54FBXNKIRIN4/action/replication_record"}},"created_at":"2026-05-18T00:53:11.938677+00:00","updated_at":"2026-05-18T00:53:11.938677+00:00"}