{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SWRK5UVL2EVJVMLAMXUPYLSSK7","short_pith_number":"pith:SWRK5UVL","canonical_record":{"source":{"id":"2505.14664","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:52:03Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"e15237bd96df9e436ffa4ae76c9cdbcaa50956c30c65c382f8aebd4094e22730","abstract_canon_sha256":"5fe9fcc8af3381c5d960e6d30c7073d7f3f338895fa1f709c803c7d1def1795e"},"schema_version":"1.0"},"canonical_sha256":"95a2aed2abd12a9ab16065e8fc2e5257d3832872ba91bf2a390f14edcb9700d7","source":{"kind":"arxiv","id":"2505.14664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14664","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14664v2","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14664","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"SWRK5UVL2EVJ","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"SWRK5UVL2EVJVMLA","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"SWRK5UVL","created_at":"2026-07-05T11:10:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SWRK5UVL2EVJVMLAMXUPYLSSK7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14664","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:52:03Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"e15237bd96df9e436ffa4ae76c9cdbcaa50956c30c65c382f8aebd4094e22730","abstract_canon_sha256":"5fe9fcc8af3381c5d960e6d30c7073d7f3f338895fa1f709c803c7d1def1795e"},"schema_version":"1.0"},"canonical_sha256":"95a2aed2abd12a9ab16065e8fc2e5257d3832872ba91bf2a390f14edcb9700d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:57.229913Z","signature_b64":"Nm3TzEUo97wjVtyhypNwRZYEMIqCxZVkGFMaPwqnDVi+Fv6CZzQNbU72HI67SThKdq/H4iurnRJl72yVylJ1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a2aed2abd12a9ab16065e8fc2e5257d3832872ba91bf2a390f14edcb9700d7","last_reissued_at":"2026-07-05T11:10:57.229422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:57.229422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14664","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xlO7iNgFGWQrRn2s4ohtqeJfQ8EPtlgt9Ck7g6nujepIZ5dsEUzisyDcB2wL24Kca8jbknYA/IHv7B0LZHYJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:45:23.252643Z"},"content_sha256":"e23265f94f9b4226d93590eaf9f3acbd4e061e9ddc7a7c88bc14591b6b5bb0ff","schema_version":"1.0","event_id":"sha256:e23265f94f9b4226d93590eaf9f3acbd4e061e9ddc7a7c88bc14591b6b5bb0ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SWRK5UVL2EVJVMLAMXUPYLSSK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiazhi Xia, Junchao Huang, Wei Zeng, Xingchen Zeng, Yilin Ye","submitted_at":"2025-05-20T17:52:03Z","abstract_excerpt":"Cross-modal embeddings form the foundation for multi-modal models. However, visualization methods for interpreting cross-modal embeddings have been primarily confined to traditional dimensionality reduction (DR) techniques like PCA and t-SNE. These DR methods primarily focus on feature distributions within a single modality, whilst failing to incorporate metrics (e.g., CLIPScore) across multiple modalities. This paper introduces AKRMap, a new DR technique designed to visualize cross-modal embeddings metric with enhanced accuracy by learning kernel regression of the metric landscape in the proj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14664","kind":"arxiv","version":2},"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/2505.14664/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":"2026-07-05T11:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDhDs54k/HLOkDHhP4CUb/Q91BecN8qfjhcrFMRlt96v+n1T16vPy/MSb+AuCOrZwoujqL8Rfb3Ta41sKE2iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:45:23.253141Z"},"content_sha256":"3127d15d51df2c88222b57af79526e10038725d6f177d1e6cf0048bde3c13495","schema_version":"1.0","event_id":"sha256:3127d15d51df2c88222b57af79526e10038725d6f177d1e6cf0048bde3c13495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/bundle.json","state_url":"https://pith.science/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/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":"2026-08-08T23:45:23Z","links":{"resolver":"https://pith.science/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7","bundle":"https://pith.science/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/bundle.json","state":"https://pith.science/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWRK5UVL2EVJVMLAMXUPYLSSK7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SWRK5UVL2EVJVMLAMXUPYLSSK7","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":"5fe9fcc8af3381c5d960e6d30c7073d7f3f338895fa1f709c803c7d1def1795e","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:52:03Z","title_canon_sha256":"e15237bd96df9e436ffa4ae76c9cdbcaa50956c30c65c382f8aebd4094e22730"},"schema_version":"1.0","source":{"id":"2505.14664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14664","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14664v2","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14664","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"SWRK5UVL2EVJ","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"SWRK5UVL2EVJVMLA","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"SWRK5UVL","created_at":"2026-07-05T11:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:3127d15d51df2c88222b57af79526e10038725d6f177d1e6cf0048bde3c13495","target":"graph","created_at":"2026-07-05T11:10:57Z","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/2505.14664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal embeddings form the foundation for multi-modal models. However, visualization methods for interpreting cross-modal embeddings have been primarily confined to traditional dimensionality reduction (DR) techniques like PCA and t-SNE. These DR methods primarily focus on feature distributions within a single modality, whilst failing to incorporate metrics (e.g., CLIPScore) across multiple modalities. This paper introduces AKRMap, a new DR technique designed to visualize cross-modal embeddings metric with enhanced accuracy by learning kernel regression of the metric landscape in the proj","authors_text":"Jiazhi Xia, Junchao Huang, Wei Zeng, Xingchen Zeng, Yilin Ye","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:52:03Z","title":"AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14664","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:e23265f94f9b4226d93590eaf9f3acbd4e061e9ddc7a7c88bc14591b6b5bb0ff","target":"record","created_at":"2026-07-05T11:10:57Z","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":"5fe9fcc8af3381c5d960e6d30c7073d7f3f338895fa1f709c803c7d1def1795e","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T17:52:03Z","title_canon_sha256":"e15237bd96df9e436ffa4ae76c9cdbcaa50956c30c65c382f8aebd4094e22730"},"schema_version":"1.0","source":{"id":"2505.14664","kind":"arxiv","version":2}},"canonical_sha256":"95a2aed2abd12a9ab16065e8fc2e5257d3832872ba91bf2a390f14edcb9700d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95a2aed2abd12a9ab16065e8fc2e5257d3832872ba91bf2a390f14edcb9700d7","first_computed_at":"2026-07-05T11:10:57.229422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:57.229422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nm3TzEUo97wjVtyhypNwRZYEMIqCxZVkGFMaPwqnDVi+Fv6CZzQNbU72HI67SThKdq/H4iurnRJl72yVylJ1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:57.229913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e23265f94f9b4226d93590eaf9f3acbd4e061e9ddc7a7c88bc14591b6b5bb0ff","sha256:3127d15d51df2c88222b57af79526e10038725d6f177d1e6cf0048bde3c13495"],"state_sha256":"ca89ecf03f802cce31a829c3802cd4efebadf5a6d997a536657ed58da60fc1e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJfVbKhLKbp9xDasHaoke71YjmzskMg+RCAI+etfQXdBoGWeFpS0UUyj8H6wa/NOdIyAMDZnSroL8H8BOwcaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:45:23.256954Z","bundle_sha256":"85602d980d4cf3a1a446da861c88324d2f645915b005e0e143867369311786dd"}}