{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KO42CD763Z2VH6F6L7U53Q6SRS","short_pith_number":"pith:KO42CD76","schema_version":"1.0","canonical_sha256":"53b9a10ffede7553f8be5fe9ddc3d28cbec81b3dcdc09ebbe84d5381de3b4991","source":{"kind":"arxiv","id":"2607.18237","version":1},"attestation_state":"computed","paper":{"title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Hertzmann, Alexei A. Efros, Eli Shechtman, Jun-Yan Zhu, Richard Zhang, Sheng-Yu Wang, Yotam Nitzan","submitted_at":"2026-07-20T17:59:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.18237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T17:59:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"38fb2e5544671aca9db16279f8eadbeb3956ec66f6e3f08eaeb63828e7a777ae","abstract_canon_sha256":"4e54c6ea3418cc603959f61d8ae48e3cb5dbc8a37e52bc749c223ef1b48f5989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:29.533167Z","signature_b64":"aByjeDSujDr6oEfbMriKiIQBBo7o04EGyeN9RBHeskATciLMUETBpyGUMEb5GR70dyCBibcXW7ygqaYa6RtaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53b9a10ffede7553f8be5fe9ddc3d28cbec81b3dcdc09ebbe84d5381de3b4991","last_reissued_at":"2026-07-21T02:22:29.532309Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:29.532309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Hertzmann, Alexei A. Efros, Eli Shechtman, Jun-Yan Zhu, Richard Zhang, Sheng-Yu Wang, Yotam Nitzan","submitted_at":"2026-07-20T17:59:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18237","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/2607.18237/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.18237","created_at":"2026-07-21T02:22:29.532754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18237v1","created_at":"2026-07-21T02:22:29.532754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18237","created_at":"2026-07-21T02:22:29.532754+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO42CD763Z2V","created_at":"2026-07-21T02:22:29.532754+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO42CD763Z2VH6F6","created_at":"2026-07-21T02:22:29.532754+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO42CD76","created_at":"2026-07-21T02:22:29.532754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03826","citing_title":"Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS","json":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS.json","graph_json":"https://pith.science/api/pith-number/KO42CD763Z2VH6F6L7U53Q6SRS/graph.json","events_json":"https://pith.science/api/pith-number/KO42CD763Z2VH6F6L7U53Q6SRS/events.json","paper":"https://pith.science/paper/KO42CD76"},"agent_actions":{"view_html":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS","download_json":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS.json","view_paper":"https://pith.science/paper/KO42CD76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18237&json=true","fetch_graph":"https://pith.science/api/pith-number/KO42CD763Z2VH6F6L7U53Q6SRS/graph.json","fetch_events":"https://pith.science/api/pith-number/KO42CD763Z2VH6F6L7U53Q6SRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS/action/storage_attestation","attest_author":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS/action/author_attestation","sign_citation":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS/action/citation_signature","submit_replication":"https://pith.science/pith/KO42CD763Z2VH6F6L7U53Q6SRS/action/replication_record"}},"created_at":"2026-07-21T02:22:29.532754+00:00","updated_at":"2026-07-21T02:22:29.532754+00:00"}