{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KO42CD763Z2VH6F6L7U53Q6SRS","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":"4e54c6ea3418cc603959f61d8ae48e3cb5dbc8a37e52bc749c223ef1b48f5989","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T17:59:51Z","title_canon_sha256":"38fb2e5544671aca9db16279f8eadbeb3956ec66f6e3f08eaeb63828e7a777ae"},"schema_version":"1.0","source":{"id":"2607.18237","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18237","created_at":"2026-07-21T02:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18237v1","created_at":"2026-07-21T02:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18237","created_at":"2026-07-21T02:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"KO42CD763Z2V","created_at":"2026-07-21T02:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"KO42CD763Z2VH6F6","created_at":"2026-07-21T02:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"KO42CD76","created_at":"2026-07-21T02:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:702f5f629f1ee1a5c5381b89c362da62c82040fe736591a82c6c508d5c4d7f60","target":"graph","created_at":"2026-07-21T02:22:29Z","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/2607.18237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human visual similarity judgments are context-dependent. For example, two images may be similar in shape but distinct in color. Existing perceptual similarity metrics, however, collapse these nuances into a single scalar value, offering no mechanism to condition on specific aspects. To bridge this gap, we introduce a large-scale dataset of human similarity judgments over image triplets, where each triplet is annotated across multiple, free-form semantic aspects of similarity. Benchmarking a broad range of frontier vision-language models (VLMs) reveals a considerable performance gap compared to","authors_text":"Aaron Hertzmann, Alexei A. Efros, Eli Shechtman, Jun-Yan Zhu, Richard Zhang, Sheng-Yu Wang, Yotam Nitzan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T17:59:51Z","title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18237","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":"sha256:5380092987acb9a7f764a21ea07a80d0f1588898fc0f12bf54c84b9298397120","target":"record","created_at":"2026-07-21T02:22:29Z","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":"4e54c6ea3418cc603959f61d8ae48e3cb5dbc8a37e52bc749c223ef1b48f5989","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T17:59:51Z","title_canon_sha256":"38fb2e5544671aca9db16279f8eadbeb3956ec66f6e3f08eaeb63828e7a777ae"},"schema_version":"1.0","source":{"id":"2607.18237","kind":"arxiv","version":1}},"canonical_sha256":"53b9a10ffede7553f8be5fe9ddc3d28cbec81b3dcdc09ebbe84d5381de3b4991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53b9a10ffede7553f8be5fe9ddc3d28cbec81b3dcdc09ebbe84d5381de3b4991","first_computed_at":"2026-07-21T02:22:29.532309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:29.532309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aByjeDSujDr6oEfbMriKiIQBBo7o04EGyeN9RBHeskATciLMUETBpyGUMEb5GR70dyCBibcXW7ygqaYa6RtaDQ==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:29.533167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18237","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5380092987acb9a7f764a21ea07a80d0f1588898fc0f12bf54c84b9298397120","sha256:702f5f629f1ee1a5c5381b89c362da62c82040fe736591a82c6c508d5c4d7f60"],"state_sha256":"4bd416f17e9d107d78b93f07a2908376385a7fc666f8ac1d3b2404c7d59120c4"}