{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IVC6L2EPSEZ3XMBELJL6UZZ572","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":"67663fc70da771fc08d705993a9070b6525a6a3e2e74e421705c095c79b0ed3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:27:22Z","title_canon_sha256":"cc019d4582f9baa9fa3ffdde1923c03467f0727798625318419beab1b135e16c"},"schema_version":"1.0","source":{"id":"2303.17561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17561","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17561v2","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17561","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_12","alias_value":"IVC6L2EPSEZ3","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_16","alias_value":"IVC6L2EPSEZ3XMBE","created_at":"2026-07-05T07:24:49Z"},{"alias_kind":"pith_short_8","alias_value":"IVC6L2EP","created_at":"2026-07-05T07:24:49Z"}],"graph_snapshots":[{"event_id":"sha256:ed6961198414299004b50ea51db9d94703ae3e2cea22b934438ee6b7320f0ccc","target":"graph","created_at":"2026-07-05T07:24:49Z","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/2303.17561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to","authors_text":"Jie Yang, Jinfeng Liu, Ke Li, Tong Wu Enwei Zhang, Wei Liu, Xing Sun, Yuting Gao, Zihan Xu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:27:22Z","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17561","kind":"arxiv","version":2},"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":"sha256:9d5ac3807a365e58138dfa9faa72d795d0607d7f24f528b963f108175212a9ce","target":"record","created_at":"2026-07-05T07:24:49Z","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":"67663fc70da771fc08d705993a9070b6525a6a3e2e74e421705c095c79b0ed3e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T17:27:22Z","title_canon_sha256":"cc019d4582f9baa9fa3ffdde1923c03467f0727798625318419beab1b135e16c"},"schema_version":"1.0","source":{"id":"2303.17561","kind":"arxiv","version":2}},"canonical_sha256":"4545e5e88f9133bbb0245a57ea673dfe8c17a55c4043af7691088bfb683f4085","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4545e5e88f9133bbb0245a57ea673dfe8c17a55c4043af7691088bfb683f4085","first_computed_at":"2026-07-05T07:24:49.130189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:49.130189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dJNBo4/uC1uAT4IR+n6OErfOv8TuAWj0p2HTyqzWyy9qvQ92ay5hATZLyJPzckWnpM9Qsk2sKjBVrigCzTAICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:49.130637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d5ac3807a365e58138dfa9faa72d795d0607d7f24f528b963f108175212a9ce","sha256:ed6961198414299004b50ea51db9d94703ae3e2cea22b934438ee6b7320f0ccc"],"state_sha256":"b115321b09673669e6a7c0dceccda47854dc75eb4a579dbb1945602750d99e5d"}