{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XOUA44CAGF3TNRCB5AIQZ7GOVB","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":"b805fcce5127a00098b55c69fe7cb3532c32e2da0f954f9d70f362ff3ef1fa05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T08:08:15Z","title_canon_sha256":"6e9acdc877e46577074e75c0dbc98c9bddb7db518edc6e0d6537b84e80b5762f"},"schema_version":"1.0","source":{"id":"2605.30968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30968","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30968v1","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30968","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"XOUA44CAGF3T","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"XOUA44CAGF3TNRCB","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"XOUA44CA","created_at":"2026-06-01T01:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:d62809fa180598443c5ac247b421af4dc93b19d2d1eb543967db32c2f44d31ea","target":"graph","created_at":"2026-06-01T01:03:27Z","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/2605.30968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-modal matching annotations, forcing the continuous similarity space into binary classification boundaries. This compression induces false negative samples and significantly impairs the generalization performance of cross-modal tasks. While prior research has attempted to mitigate this by modeling intra-modal ambiguity, it often overlooks inherent annotation flaws, leading to subo","authors_text":"Dehua Peng, Huayi Wu, Tiandi Ye, WenZhang Wei, Zhipeng Gui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T08:08:15Z","title":"Variational Adapter for Cross-modal Similarity Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30968","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:d09c15fa7441c9e2718f868bb384c20618cb836eae1f0520a52c58a13fe02f83","target":"record","created_at":"2026-06-01T01:03:27Z","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":"b805fcce5127a00098b55c69fe7cb3532c32e2da0f954f9d70f362ff3ef1fa05","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T08:08:15Z","title_canon_sha256":"6e9acdc877e46577074e75c0dbc98c9bddb7db518edc6e0d6537b84e80b5762f"},"schema_version":"1.0","source":{"id":"2605.30968","kind":"arxiv","version":1}},"canonical_sha256":"bba80e7040317736c441e8110cfccea865c5ae1408e5edbbc361ef996d481a50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bba80e7040317736c441e8110cfccea865c5ae1408e5edbbc361ef996d481a50","first_computed_at":"2026-06-01T01:03:27.888309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:27.888309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wP71AFlQYS0YgQghduDYqagiKj2Va9ykaDsaheYkpdpEqkatBs03FqQ8RqRe0BoZSZeKpE3LbeT12EZfchrNDg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:27.888864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d09c15fa7441c9e2718f868bb384c20618cb836eae1f0520a52c58a13fe02f83","sha256:d62809fa180598443c5ac247b421af4dc93b19d2d1eb543967db32c2f44d31ea"],"state_sha256":"67edf77310a5636e7be4244e2a8b4ed138e090b8900bfebeeaba80684d7346e1"}