{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CKIUD6O6WP3EIVUYEODCCJOQOI","short_pith_number":"pith:CKIUD6O6","schema_version":"1.0","canonical_sha256":"129141f9deb3f644569823862125d0721a29d10a35b4f4bbb7f9feadcaa6f588","source":{"kind":"arxiv","id":"2502.10478","version":1},"attestation_state":"computed","paper":{"title":"SinSim: Sinkhorn-Regularized SimCLR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"M.Hadi Sepanj, Paul Fiegth","submitted_at":"2025-02-13T19:49:25Z","abstract_excerpt":"Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit regularization to enforce a globally structured latent space. This limitation often leads to suboptimal generalization. We propose SinSim, a novel extension of SimCLR that integrates Sinkhorn regularization from optimal transport theory to enhance representation structure. The Sinkhorn loss, an entropy-regularized Wasserstein distance, encourages a well-dispersed a"},"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":"2502.10478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T19:49:25Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"3dea6a227f9e11873461fdcbac9980cf62bb6c74c66f2f0eede3381aa47ca34c","abstract_canon_sha256":"be34917784216a9fd9d2c6df6809dfe0c9d8af58ef13b249d2f229078a13e2ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:53.303508Z","signature_b64":"tTi7dZ2panpTL9KvPLF/9YoMhMqFsYUgJNiKB2nj+DXW+d6z9LlrR0ZLKlnEv7W5joPujeYoAEviydDQZ9dLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"129141f9deb3f644569823862125d0721a29d10a35b4f4bbb7f9feadcaa6f588","last_reissued_at":"2026-07-05T10:14:53.303028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:53.303028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SinSim: Sinkhorn-Regularized SimCLR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"M.Hadi Sepanj, Paul Fiegth","submitted_at":"2025-02-13T19:49:25Z","abstract_excerpt":"Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit regularization to enforce a globally structured latent space. This limitation often leads to suboptimal generalization. We propose SinSim, a novel extension of SimCLR that integrates Sinkhorn regularization from optimal transport theory to enhance representation structure. The Sinkhorn loss, an entropy-regularized Wasserstein distance, encourages a well-dispersed a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10478","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.10478/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":"2502.10478","created_at":"2026-07-05T10:14:53.303084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10478v1","created_at":"2026-07-05T10:14:53.303084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10478","created_at":"2026-07-05T10:14:53.303084+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKIUD6O6WP3E","created_at":"2026-07-05T10:14:53.303084+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKIUD6O6WP3EIVUY","created_at":"2026-07-05T10:14:53.303084+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKIUD6O6","created_at":"2026-07-05T10:14:53.303084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.17426","citing_title":"Self-Supervised Learning by Curvature Alignment","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI","json":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI.json","graph_json":"https://pith.science/api/pith-number/CKIUD6O6WP3EIVUYEODCCJOQOI/graph.json","events_json":"https://pith.science/api/pith-number/CKIUD6O6WP3EIVUYEODCCJOQOI/events.json","paper":"https://pith.science/paper/CKIUD6O6"},"agent_actions":{"view_html":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI","download_json":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI.json","view_paper":"https://pith.science/paper/CKIUD6O6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10478&json=true","fetch_graph":"https://pith.science/api/pith-number/CKIUD6O6WP3EIVUYEODCCJOQOI/graph.json","fetch_events":"https://pith.science/api/pith-number/CKIUD6O6WP3EIVUYEODCCJOQOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI/action/storage_attestation","attest_author":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI/action/author_attestation","sign_citation":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI/action/citation_signature","submit_replication":"https://pith.science/pith/CKIUD6O6WP3EIVUYEODCCJOQOI/action/replication_record"}},"created_at":"2026-07-05T10:14:53.303084+00:00","updated_at":"2026-07-05T10:14:53.303084+00:00"}