{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QPYHCV7PXVOREMEAKO3SRVXVFH","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":"25cc7e6aa28bccc721708e3c48641dd0af6b03d9292af3e01e1bae09d38f679f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T00:12:27Z","title_canon_sha256":"bae7625089838d25fc24b4de391da4c9242e2f0dbf6307a15ea1ec974149ad4d"},"schema_version":"1.0","source":{"id":"2404.09387","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09387","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09387v3","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09387","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"QPYHCV7PXVOR","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"QPYHCV7PXVOREMEA","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"QPYHCV7P","created_at":"2026-07-05T10:38:20Z"}],"graph_snapshots":[{"event_id":"sha256:01224742fcdee1bfa3336c2484545be7f6d60df95838c7aca54d353801f7ddb8","target":"graph","created_at":"2026-07-05T10:38:20Z","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/2404.09387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships between and within texts and images. To this end, we introduce RankCLIP, a novel pre-training method that extends beyond the rigid one-to-one matching framework of CLIP and its variants. By extending the traditional pair-wise loss to list-wise, and leveraging both in-modal and cross-modal ranking consistency, RankCLIP improves the alignment process","authors_text":"Yiming Zhang, Yining Sun, Zenghui Ding, Zhaorun Chen, Zhili Feng, Zhuokai Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T00:12:27Z","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09387","kind":"arxiv","version":3},"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":"sha256:03d30f960af05b905810c414929ed372bafcbd8f3a181ba2527495318d45f674","target":"record","created_at":"2026-07-05T10:38:20Z","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":"25cc7e6aa28bccc721708e3c48641dd0af6b03d9292af3e01e1bae09d38f679f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T00:12:27Z","title_canon_sha256":"bae7625089838d25fc24b4de391da4c9242e2f0dbf6307a15ea1ec974149ad4d"},"schema_version":"1.0","source":{"id":"2404.09387","kind":"arxiv","version":3}},"canonical_sha256":"83f07157efbd5d12308053b728d6f529cbdd634faaa9cc8e08920f394faabbfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83f07157efbd5d12308053b728d6f529cbdd634faaa9cc8e08920f394faabbfb","first_computed_at":"2026-07-05T10:38:20.640156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:20.640156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCcgCce5QTS03fWTVmbkCfOhBpVb7Zfg8W/jtX404vhrk0VLEV7w1LTTJroiMIHFXZikHVgKTeroF/mDqvWHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:20.640639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09387","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03d30f960af05b905810c414929ed372bafcbd8f3a181ba2527495318d45f674","sha256:01224742fcdee1bfa3336c2484545be7f6d60df95838c7aca54d353801f7ddb8"],"state_sha256":"f2235c1470f80c0bdb760f214a1e646a6097138b09607d393d0bb00ef4440758"}