{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4WS2LK7I7FDKUR7NUZHVADCGTJ","short_pith_number":"pith:4WS2LK7I","schema_version":"1.0","canonical_sha256":"e5a5a5abe8f946aa47eda64f500c469a7a8519785287bef33c6b366820414a17","source":{"kind":"arxiv","id":"2302.01409","version":1},"attestation_state":"computed","paper":{"title":"Hyperbolic Contrastive Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fangzhou Lin, Kazunori D Yamada, Yun Yue, Ziming Zhang","submitted_at":"2023-02-02T20:47:45Z","abstract_excerpt":"Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has shown competitive performance on several benchmark datasets. The embeddings of contrastive learning are arranged on a hypersphere that results in using the inner (dot) product as a distance measurement in Euclidean space. However, the underlying structure of many scientific fields like social networks, brain imaging, and computer graphics data exhibit highly n"},"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":"2302.01409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-02T20:47:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bde6bab907793af7325957abab954eecfdf8e225a99bb3f3f6978ad5d14f45e0","abstract_canon_sha256":"c8e9d119ee42307d3e3ed66cd265ad1163c490e21d03d38338c9d05417bc7f0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:31.972020Z","signature_b64":"ZSYqB5BvSkJVlODv/dzBYdWakOXCdX+Pv8rznjUk6yX1agbbQAtFcF8Kdxe1uD5ZFraGz6sECI17ZE6KLxFlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5a5a5abe8f946aa47eda64f500c469a7a8519785287bef33c6b366820414a17","last_reissued_at":"2026-07-05T05:38:31.971622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:31.971622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Contrastive Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fangzhou Lin, Kazunori D Yamada, Yun Yue, Ziming Zhang","submitted_at":"2023-02-02T20:47:45Z","abstract_excerpt":"Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has shown competitive performance on several benchmark datasets. The embeddings of contrastive learning are arranged on a hypersphere that results in using the inner (dot) product as a distance measurement in Euclidean space. However, the underlying structure of many scientific fields like social networks, brain imaging, and computer graphics data exhibit highly n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01409","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/2302.01409/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":"2302.01409","created_at":"2026-07-05T05:38:31.971676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01409v1","created_at":"2026-07-05T05:38:31.971676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01409","created_at":"2026-07-05T05:38:31.971676+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WS2LK7I7FDK","created_at":"2026-07-05T05:38:31.971676+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WS2LK7I7FDKUR7N","created_at":"2026-07-05T05:38:31.971676+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WS2LK7I","created_at":"2026-07-05T05:38:31.971676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.23058","citing_title":"GeoWorld: Geometric World Models","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ","json":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ.json","graph_json":"https://pith.science/api/pith-number/4WS2LK7I7FDKUR7NUZHVADCGTJ/graph.json","events_json":"https://pith.science/api/pith-number/4WS2LK7I7FDKUR7NUZHVADCGTJ/events.json","paper":"https://pith.science/paper/4WS2LK7I"},"agent_actions":{"view_html":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ","download_json":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ.json","view_paper":"https://pith.science/paper/4WS2LK7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01409&json=true","fetch_graph":"https://pith.science/api/pith-number/4WS2LK7I7FDKUR7NUZHVADCGTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4WS2LK7I7FDKUR7NUZHVADCGTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ/action/storage_attestation","attest_author":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ/action/author_attestation","sign_citation":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ/action/citation_signature","submit_replication":"https://pith.science/pith/4WS2LK7I7FDKUR7NUZHVADCGTJ/action/replication_record"}},"created_at":"2026-07-05T05:38:31.971676+00:00","updated_at":"2026-07-05T05:38:31.971676+00:00"}