{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FCUMCXKBMF2L6RJF3ESLSO7J2P","short_pith_number":"pith:FCUMCXKB","canonical_record":{"source":{"id":"2502.08134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T05:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"a9e9e7a17df5022eddfcd39a00627f13a63fb69e906997c4e17227c680566e55","abstract_canon_sha256":"45c2ccc4f315c5679fb17787bd53fe60c97496390c1528a0aa165a83e7e8411c"},"schema_version":"1.0"},"canonical_sha256":"28a8c15d416174bf4525d924b93be9d3d01b1645d6c28d7e0af81c5266744353","source":{"kind":"arxiv","id":"2502.08134","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08134","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08134v1","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08134","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"FCUMCXKBMF2L","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCUMCXKBMF2L6RJF","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCUMCXKB","created_at":"2026-07-05T10:13:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FCUMCXKBMF2L6RJF3ESLSO7J2P","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08134","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T05:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"a9e9e7a17df5022eddfcd39a00627f13a63fb69e906997c4e17227c680566e55","abstract_canon_sha256":"45c2ccc4f315c5679fb17787bd53fe60c97496390c1528a0aa165a83e7e8411c"},"schema_version":"1.0"},"canonical_sha256":"28a8c15d416174bf4525d924b93be9d3d01b1645d6c28d7e0af81c5266744353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:15.958633Z","signature_b64":"CDcsQHvxxoeqYgGmSU6dfhTlA2/FOGNMjrka2QaQbr1fedFBiO6RKnBFzR+pP9pbLksLxDpY9Y77ksSU40bwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a8c15d416174bf4525d924b93be9d3d01b1645d6c28d7e0af81c5266744353","last_reissued_at":"2026-07-05T10:13:15.958125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:15.958125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08134","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3rsGoZfMhSN8iVP3SCOaj5xFpGNG7z1sQR3Te7w801QH2u5R9rVo0xdLmB+Z13y9HkPffS9xamqmEJbpTHpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:10.187726Z"},"content_sha256":"15a78600b6d56528b7338a436bb4af171111cdb33fd20b85f6cef141f063e4ee","schema_version":"1.0","event_id":"sha256:15a78600b6d56528b7338a436bb4af171111cdb33fd20b85f6cef141f063e4ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FCUMCXKBMF2L6RJF3ESLSO7J2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Data Curation for Visual Contrastive Learning: Why Crafting Effective Positive and Negative Pairs Matters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Debasmita Ghose, Deep Chakraborty, Shasvat Desai","submitted_at":"2025-02-12T05:34:48Z","abstract_excerpt":"Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly impacts representation quality, training efficiency, and computational cost. A well-curated set of pairs leads to stronger representations and faster convergence. As contrastive pre-training sees wider adoption for solving downstream tasks, data curation becomes essential for optimizing its effectiveness. In this survey, we attempt to create a taxonomy of existing techniques for positive and negative pair curation i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08134","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/2502.08134/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgWqoHeeEfIQmC3ucC8SIjZk9Bo/davj8Ug45wELUGEkh09JL0McAWFyv2+9zgq/dLPkoT2FhODJb0R9zzcOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:10.188708Z"},"content_sha256":"ed977c6214d79fe5373057fdec25f4f04d13ccc0b74fef0e5a055f418fa904d5","schema_version":"1.0","event_id":"sha256:ed977c6214d79fe5373057fdec25f4f04d13ccc0b74fef0e5a055f418fa904d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/bundle.json","state_url":"https://pith.science/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T20:06:10Z","links":{"resolver":"https://pith.science/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P","bundle":"https://pith.science/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/bundle.json","state":"https://pith.science/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FCUMCXKBMF2L6RJF3ESLSO7J2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FCUMCXKBMF2L6RJF3ESLSO7J2P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"45c2ccc4f315c5679fb17787bd53fe60c97496390c1528a0aa165a83e7e8411c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T05:34:48Z","title_canon_sha256":"a9e9e7a17df5022eddfcd39a00627f13a63fb69e906997c4e17227c680566e55"},"schema_version":"1.0","source":{"id":"2502.08134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08134","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08134v1","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08134","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"FCUMCXKBMF2L","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCUMCXKBMF2L6RJF","created_at":"2026-07-05T10:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCUMCXKB","created_at":"2026-07-05T10:13:15Z"}],"graph_snapshots":[{"event_id":"sha256:ed977c6214d79fe5373057fdec25f4f04d13ccc0b74fef0e5a055f418fa904d5","target":"graph","created_at":"2026-07-05T10:13:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.08134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual contrastive learning aims to learn representations by contrasting similar (positive) and dissimilar (negative) pairs of data samples. The design of these pairs significantly impacts representation quality, training efficiency, and computational cost. A well-curated set of pairs leads to stronger representations and faster convergence. As contrastive pre-training sees wider adoption for solving downstream tasks, data curation becomes essential for optimizing its effectiveness. In this survey, we attempt to create a taxonomy of existing techniques for positive and negative pair curation i","authors_text":"Debasmita Ghose, Deep Chakraborty, Shasvat Desai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T05:34:48Z","title":"A Survey on Data Curation for Visual Contrastive Learning: Why Crafting Effective Positive and Negative Pairs Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08134","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:15a78600b6d56528b7338a436bb4af171111cdb33fd20b85f6cef141f063e4ee","target":"record","created_at":"2026-07-05T10:13:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"45c2ccc4f315c5679fb17787bd53fe60c97496390c1528a0aa165a83e7e8411c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T05:34:48Z","title_canon_sha256":"a9e9e7a17df5022eddfcd39a00627f13a63fb69e906997c4e17227c680566e55"},"schema_version":"1.0","source":{"id":"2502.08134","kind":"arxiv","version":1}},"canonical_sha256":"28a8c15d416174bf4525d924b93be9d3d01b1645d6c28d7e0af81c5266744353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28a8c15d416174bf4525d924b93be9d3d01b1645d6c28d7e0af81c5266744353","first_computed_at":"2026-07-05T10:13:15.958125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:15.958125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CDcsQHvxxoeqYgGmSU6dfhTlA2/FOGNMjrka2QaQbr1fedFBiO6RKnBFzR+pP9pbLksLxDpY9Y77ksSU40bwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:15.958633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15a78600b6d56528b7338a436bb4af171111cdb33fd20b85f6cef141f063e4ee","sha256:ed977c6214d79fe5373057fdec25f4f04d13ccc0b74fef0e5a055f418fa904d5"],"state_sha256":"f027e32befc21961567c6186eb65592db91e5570f2d548e4291badd8fcf1f5b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRjiisZR4LSOaSXafJocfUWItH01Ar2E7cu/e/nDRxA4eU0e52DOEpwOSdGUTd7ScnzzlUFoB3FUa6lm8d2sCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:06:10.256136Z","bundle_sha256":"e5711bd110b6ff54cefea57f89627eae56022864c346609f7a1fe5d2831c3ebe"}}