{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BE3KPUQVJS5ZR6KTKLCRD2FR32","short_pith_number":"pith:BE3KPUQV","schema_version":"1.0","canonical_sha256":"0936a7d2154cbb98f95352c511e8b1de8df9aabfcf6a150890d02b5058262a6d","source":{"kind":"arxiv","id":"2408.16965","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Learning with Synthetic Positives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zeng, Xiaowei Xu, Xinrong Hu, Yawen Wu, Yiyu Shi","submitted_at":"2024-08-30T01:47:43Z","abstract_excerpt":"Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is constrained as the nearest neighbor algorithm primarily identifies \"easy\" positive pairs, where the representations are already closely located in the embedding space. In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional "},"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":"2408.16965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-30T01:47:43Z","cross_cats_sorted":[],"title_canon_sha256":"0b1fa72df4e2a7a10a6532ea3766dbd7eb81280ae3d939d8a29736ce884f22a3","abstract_canon_sha256":"7bafb1954f9e82799359f72f4ae98b0c6519e965f2af6924d5965c3b25aa94e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:11.508096Z","signature_b64":"kREoaY2Oo/unHwtVXBTt8mkClxTj7+Iyx0rK6eKs8gjCXi4beLnDPyw6NbCmeFOxR1qklDmvnJvOArz9DnucBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0936a7d2154cbb98f95352c511e8b1de8df9aabfcf6a150890d02b5058262a6d","last_reissued_at":"2026-07-05T10:53:11.507612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:11.507612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning with Synthetic Positives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dewen Zeng, Xiaowei Xu, Xinrong Hu, Yawen Wu, Yiyu Shi","submitted_at":"2024-08-30T01:47:43Z","abstract_excerpt":"Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is constrained as the nearest neighbor algorithm primarily identifies \"easy\" positive pairs, where the representations are already closely located in the embedding space. In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16965","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.16965/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":"2408.16965","created_at":"2026-07-05T10:53:11.507672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16965v2","created_at":"2026-07-05T10:53:11.507672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16965","created_at":"2026-07-05T10:53:11.507672+00:00"},{"alias_kind":"pith_short_12","alias_value":"BE3KPUQVJS5Z","created_at":"2026-07-05T10:53:11.507672+00:00"},{"alias_kind":"pith_short_16","alias_value":"BE3KPUQVJS5ZR6KT","created_at":"2026-07-05T10:53:11.507672+00:00"},{"alias_kind":"pith_short_8","alias_value":"BE3KPUQV","created_at":"2026-07-05T10:53:11.507672+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/BE3KPUQVJS5ZR6KTKLCRD2FR32","json":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32.json","graph_json":"https://pith.science/api/pith-number/BE3KPUQVJS5ZR6KTKLCRD2FR32/graph.json","events_json":"https://pith.science/api/pith-number/BE3KPUQVJS5ZR6KTKLCRD2FR32/events.json","paper":"https://pith.science/paper/BE3KPUQV"},"agent_actions":{"view_html":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32","download_json":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32.json","view_paper":"https://pith.science/paper/BE3KPUQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16965&json=true","fetch_graph":"https://pith.science/api/pith-number/BE3KPUQVJS5ZR6KTKLCRD2FR32/graph.json","fetch_events":"https://pith.science/api/pith-number/BE3KPUQVJS5ZR6KTKLCRD2FR32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32/action/storage_attestation","attest_author":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32/action/author_attestation","sign_citation":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32/action/citation_signature","submit_replication":"https://pith.science/pith/BE3KPUQVJS5ZR6KTKLCRD2FR32/action/replication_record"}},"created_at":"2026-07-05T10:53:11.507672+00:00","updated_at":"2026-07-05T10:53:11.507672+00:00"}