{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3EZMOF5PYZDUW6OZXWE6KRYYLS","short_pith_number":"pith:3EZMOF5P","canonical_record":{"source":{"id":"2506.02557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:44:43Z","cross_cats_sorted":[],"title_canon_sha256":"11cb1030d460c3afdd04eedf8740c2c56b0f10deb23fe6c8f71345d81c5890e1","abstract_canon_sha256":"a8546c2ceb3f5d9f5df7d27cda1024eb849e167b914e5e9a85199eda4f72d6d8"},"schema_version":"1.0"},"canonical_sha256":"d932c717afc6474b79d9bd89e547185c98a48783245a1d73ab5ad7176f1cd9ad","source":{"kind":"arxiv","id":"2506.02557","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02557","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02557v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02557","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"3EZMOF5PYZDU","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"3EZMOF5PYZDUW6OZ","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"3EZMOF5P","created_at":"2026-07-05T11:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3EZMOF5PYZDUW6OZXWE6KRYYLS","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:44:43Z","cross_cats_sorted":[],"title_canon_sha256":"11cb1030d460c3afdd04eedf8740c2c56b0f10deb23fe6c8f71345d81c5890e1","abstract_canon_sha256":"a8546c2ceb3f5d9f5df7d27cda1024eb849e167b914e5e9a85199eda4f72d6d8"},"schema_version":"1.0"},"canonical_sha256":"d932c717afc6474b79d9bd89e547185c98a48783245a1d73ab5ad7176f1cd9ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:04.078670Z","signature_b64":"UE9gNH3qc3Iyhim6Y6HGoQQ4fF2hFcwwvPeUF0Zd/PlaW1vWn28L9b5dCTvJKzeyLLT+cnEYiTl9NgTlqleyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d932c717afc6474b79d9bd89e547185c98a48783245a1d73ab5ad7176f1cd9ad","last_reissued_at":"2026-07-05T11:15:04.078125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:04.078125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02557","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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqZt5WvNjOyXVrJEPrRazSQbO+TknuUUuOHW644+nS7fs/bUGg+h5lxPIX6ujZP1NCq9BhECp+e4wOsci3rxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:19:34.109233Z"},"content_sha256":"d52a1a9a4b1ab32fb69165a754da9a03262351f00e62a3a094ec63353ca90151","schema_version":"1.0","event_id":"sha256:d52a1a9a4b1ab32fb69165a754da9a03262351f00e62a3a094ec63353ca90151"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3EZMOF5PYZDUW6OZXWE6KRYYLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Farzan Farnia, Qi Dou, Shizhan Gong, Yankai Jiang","submitted_at":"2025-06-03T07:44:43Z","abstract_excerpt":"Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However, numerous studies have identified CLIP's limited fine-grained perception as a critical drawback, leading to substantial failures in downstream MLLMs. In contrast, vision-centric foundation models like DINOv2 demonstrate remarkable capabilities in capturing fine details from images. In this work, we propose a novel kernel-based method to align CLIP's visual repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02557","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/2506.02557/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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ld6NXYl3fm4Uq+FHrwF/U32cZoZi1f7JR9DYmxSz2DN7oDE59q064OapavYIKBiK331RiiUFeDRtsdd+iJH/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:19:34.109737Z"},"content_sha256":"f093bd4eb603569862938e4eb183d3320a0880332a7fc56231e36471d2646c25","schema_version":"1.0","event_id":"sha256:f093bd4eb603569862938e4eb183d3320a0880332a7fc56231e36471d2646c25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/bundle.json","state_url":"https://pith.science/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/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":"2026-08-09T02:19:34Z","links":{"resolver":"https://pith.science/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS","bundle":"https://pith.science/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/bundle.json","state":"https://pith.science/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EZMOF5PYZDUW6OZXWE6KRYYLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3EZMOF5PYZDUW6OZXWE6KRYYLS","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":"a8546c2ceb3f5d9f5df7d27cda1024eb849e167b914e5e9a85199eda4f72d6d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:44:43Z","title_canon_sha256":"11cb1030d460c3afdd04eedf8740c2c56b0f10deb23fe6c8f71345d81c5890e1"},"schema_version":"1.0","source":{"id":"2506.02557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02557","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02557v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02557","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"3EZMOF5PYZDU","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"3EZMOF5PYZDUW6OZ","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"3EZMOF5P","created_at":"2026-07-05T11:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:f093bd4eb603569862938e4eb183d3320a0880332a7fc56231e36471d2646c25","target":"graph","created_at":"2026-07-05T11:15:04Z","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/2506.02557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However, numerous studies have identified CLIP's limited fine-grained perception as a critical drawback, leading to substantial failures in downstream MLLMs. In contrast, vision-centric foundation models like DINOv2 demonstrate remarkable capabilities in capturing fine details from images. In this work, we propose a novel kernel-based method to align CLIP's visual repr","authors_text":"Farzan Farnia, Qi Dou, Shizhan Gong, Yankai Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:44:43Z","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02557","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:d52a1a9a4b1ab32fb69165a754da9a03262351f00e62a3a094ec63353ca90151","target":"record","created_at":"2026-07-05T11:15:04Z","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":"a8546c2ceb3f5d9f5df7d27cda1024eb849e167b914e5e9a85199eda4f72d6d8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T07:44:43Z","title_canon_sha256":"11cb1030d460c3afdd04eedf8740c2c56b0f10deb23fe6c8f71345d81c5890e1"},"schema_version":"1.0","source":{"id":"2506.02557","kind":"arxiv","version":1}},"canonical_sha256":"d932c717afc6474b79d9bd89e547185c98a48783245a1d73ab5ad7176f1cd9ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d932c717afc6474b79d9bd89e547185c98a48783245a1d73ab5ad7176f1cd9ad","first_computed_at":"2026-07-05T11:15:04.078125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:04.078125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UE9gNH3qc3Iyhim6Y6HGoQQ4fF2hFcwwvPeUF0Zd/PlaW1vWn28L9b5dCTvJKzeyLLT+cnEYiTl9NgTlqleyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:04.078670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d52a1a9a4b1ab32fb69165a754da9a03262351f00e62a3a094ec63353ca90151","sha256:f093bd4eb603569862938e4eb183d3320a0880332a7fc56231e36471d2646c25"],"state_sha256":"6c21a49fda95e08a7f3c58f9583661c26fb2137304a6ada74f54742fd53e345a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/b2F6U8q+BKGUUBLc9l5c4MtKK47iSQKmp1EsLH4K2N3nvBwiNruQWztGLTmoygoVtnAu9NteudJhsxydQ7YCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:19:34.114547Z","bundle_sha256":"84592f2569a24f74376816593419e0ef4ef58a2ec0443e99c37f6e3ce8bbb7e8"}}