{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QPYHCV7PXVOREMEAKO3SRVXVFH","short_pith_number":"pith:QPYHCV7P","canonical_record":{"source":{"id":"2404.09387","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T00:12:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bae7625089838d25fc24b4de391da4c9242e2f0dbf6307a15ea1ec974149ad4d","abstract_canon_sha256":"25cc7e6aa28bccc721708e3c48641dd0af6b03d9292af3e01e1bae09d38f679f"},"schema_version":"1.0"},"canonical_sha256":"83f07157efbd5d12308053b728d6f529cbdd634faaa9cc8e08920f394faabbfb","source":{"kind":"arxiv","id":"2404.09387","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QPYHCV7PXVOREMEAKO3SRVXVFH","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09387","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T00:12:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bae7625089838d25fc24b4de391da4c9242e2f0dbf6307a15ea1ec974149ad4d","abstract_canon_sha256":"25cc7e6aa28bccc721708e3c48641dd0af6b03d9292af3e01e1bae09d38f679f"},"schema_version":"1.0"},"canonical_sha256":"83f07157efbd5d12308053b728d6f529cbdd634faaa9cc8e08920f394faabbfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:20.640639Z","signature_b64":"gCcgCce5QTS03fWTVmbkCfOhBpVb7Zfg8W/jtX404vhrk0VLEV7w1LTTJroiMIHFXZikHVgKTeroF/mDqvWHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83f07157efbd5d12308053b728d6f529cbdd634faaa9cc8e08920f394faabbfb","last_reissued_at":"2026-07-05T10:38:20.640156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:20.640156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09387","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eq7TzHLgoPkP+yv6gASAWdf05HL/tsnY1g4fEZqrPbCy91UooM+Y3bJxuTPZuonMrMVUPvYlYphnbuu0Hq2FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:33:08.888628Z"},"content_sha256":"03d30f960af05b905810c414929ed372bafcbd8f3a181ba2527495318d45f674","schema_version":"1.0","event_id":"sha256:03d30f960af05b905810c414929ed372bafcbd8f3a181ba2527495318d45f674"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QPYHCV7PXVOREMEAKO3SRVXVFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Yiming Zhang, Yining Sun, Zenghui Ding, Zhaorun Chen, Zhili Feng, Zhuokai Zhao","submitted_at":"2024-04-15T00:12:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09387","kind":"arxiv","version":3},"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/2404.09387/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":"2026-07-05T10:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LpUzJ0zIwTlIoN3K9f/e6f6jaljDEYqoG8E2gfIhG6BK5OUHlOFDSbtZbR52wNeeuyKMPgGkJp/3SZcUXlzgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:33:08.889388Z"},"content_sha256":"01224742fcdee1bfa3336c2484545be7f6d60df95838c7aca54d353801f7ddb8","schema_version":"1.0","event_id":"sha256:01224742fcdee1bfa3336c2484545be7f6d60df95838c7aca54d353801f7ddb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/bundle.json","state_url":"https://pith.science/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/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":"2026-08-09T09:33:08Z","links":{"resolver":"https://pith.science/pith/QPYHCV7PXVOREMEAKO3SRVXVFH","bundle":"https://pith.science/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/bundle.json","state":"https://pith.science/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPYHCV7PXVOREMEAKO3SRVXVFH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rout6NfXGzB1EKHUY+LZbNGUmW5Ffh79gDqmO+sOhNsdtAO3zUwvl2RWzE/Rxkr196GPGQWaajLWierYopj0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:33:08.894283Z","bundle_sha256":"3adbfc54531f574d221af781a5b5e6bf2376f50e16e4bd83957c0bf044af99f5"}}