{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VLGJEVMT5D3UAYWXTUE2BPEBPI","short_pith_number":"pith:VLGJEVMT","schema_version":"1.0","canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","source":{"kind":"arxiv","id":"1812.07627","version":1},"attestation_state":"computed","paper":{"title":"Clustering-Oriented Representation Learning with Attractive-Repulsive Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Cianflone, Doina Precup, Guillaume Rabusseau, Jackie Chi Kit Cheung, Kian Kenyon-Dean, Lucas Page-Caccia","submitted_at":"2018-12-18T20:07:56Z","abstract_excerpt":"The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an alternative to CCE in the context of a generalized attractive-repulsive loss framework. COREL has the consequence of building latent representations that collectively exhibit the quality of natural clustering within the latent space of the final hidden layer, according to a predefined "},"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":"1812.07627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T20:07:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5012da61291895c5d2d78a0fcbea5f86dd3079143c36c882ef35451206ae2ef2","abstract_canon_sha256":"6f88c0931affbea0b0954e29fe67e2930a0536f1ed1659e2284048d8b74642b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.506706Z","signature_b64":"XLG5Jw2bhSz/i+Yw95eYGa3eYRxdznkd1fDHKHssUzV4yAiaJPGFZxxwpQQTBqsxHuuv0jVcNzOwvFqd5k1KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aacc925593e8f74062d79d09a0bc817a36b521504df2ed2c69dfb48911deace8","last_reissued_at":"2026-05-17T23:57:56.505981Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.505981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering-Oriented Representation Learning with Attractive-Repulsive Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andre Cianflone, Doina Precup, Guillaume Rabusseau, Jackie Chi Kit Cheung, Kian Kenyon-Dean, Lucas Page-Caccia","submitted_at":"2018-12-18T20:07:56Z","abstract_excerpt":"The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this work, we propose clustering-oriented representation learning (COREL) as an alternative to CCE in the context of a generalized attractive-repulsive loss framework. COREL has the consequence of building latent representations that collectively exhibit the quality of natural clustering within the latent space of the final hidden layer, according to a predefined "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07627","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":""},"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":"1812.07627","created_at":"2026-05-17T23:57:56.506093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07627v1","created_at":"2026-05-17T23:57:56.506093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07627","created_at":"2026-05-17T23:57:56.506093+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLGJEVMT5D3U","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLGJEVMT5D3UAYWX","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLGJEVMT","created_at":"2026-05-18T12:32:59.047623+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/VLGJEVMT5D3UAYWXTUE2BPEBPI","json":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI.json","graph_json":"https://pith.science/api/pith-number/VLGJEVMT5D3UAYWXTUE2BPEBPI/graph.json","events_json":"https://pith.science/api/pith-number/VLGJEVMT5D3UAYWXTUE2BPEBPI/events.json","paper":"https://pith.science/paper/VLGJEVMT"},"agent_actions":{"view_html":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI","download_json":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI.json","view_paper":"https://pith.science/paper/VLGJEVMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07627&json=true","fetch_graph":"https://pith.science/api/pith-number/VLGJEVMT5D3UAYWXTUE2BPEBPI/graph.json","fetch_events":"https://pith.science/api/pith-number/VLGJEVMT5D3UAYWXTUE2BPEBPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/action/storage_attestation","attest_author":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/action/author_attestation","sign_citation":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/action/citation_signature","submit_replication":"https://pith.science/pith/VLGJEVMT5D3UAYWXTUE2BPEBPI/action/replication_record"}},"created_at":"2026-05-17T23:57:56.506093+00:00","updated_at":"2026-05-17T23:57:56.506093+00:00"}