{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WL6H63HWM4RGC7UPGWIS6HNVY7","short_pith_number":"pith:WL6H63HW","canonical_record":{"source":{"id":"2412.10594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T22:38:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9ca4dc923f36439f541bb7f1b70f726b53e52f5b3c8fbb16b2d5be4a39c92975","abstract_canon_sha256":"e065d4edfd6b3474df2441339327346e1bc9dd87212f74db9262a55933475515"},"schema_version":"1.0"},"canonical_sha256":"b2fc7f6cf66722617e8f35912f1db5c7fbd7aff2711f2541c1ac91b46325a02d","source":{"kind":"arxiv","id":"2412.10594","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10594","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10594v1","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10594","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"WL6H63HWM4RG","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"WL6H63HWM4RGC7UP","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"WL6H63HW","created_at":"2026-07-05T09:49:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WL6H63HWM4RGC7UPGWIS6HNVY7","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T22:38:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9ca4dc923f36439f541bb7f1b70f726b53e52f5b3c8fbb16b2d5be4a39c92975","abstract_canon_sha256":"e065d4edfd6b3474df2441339327346e1bc9dd87212f74db9262a55933475515"},"schema_version":"1.0"},"canonical_sha256":"b2fc7f6cf66722617e8f35912f1db5c7fbd7aff2711f2541c1ac91b46325a02d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:18.184190Z","signature_b64":"dQfLhPGSSCyZ74S3uGuhxRyZFSJw4S2zUmcId92uX02hFt0sYdQunvumHbOfkO3K/9FADy5dIb5W9pEABG8pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2fc7f6cf66722617e8f35912f1db5c7fbd7aff2711f2541c1ac91b46325a02d","last_reissued_at":"2026-07-05T09:49:18.183693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:18.183693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10594","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":"2026-07-05T09:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WaWhw/jZR14YyziyJUl4nlHw1u6mZUmYxL5q+AKiFwoFGblfANAPr0h/j83BpUoZNnKpVw3GPiQue7aFi6BCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:40:53.168029Z"},"content_sha256":"f89372f730e5f08dcda12e3f8dbdc8ce01b3a1eafd2c3aa546c2745d0bd4ab56","schema_version":"1.0","event_id":"sha256:f89372f730e5f08dcda12e3f8dbdc8ce01b3a1eafd2c3aa546c2745d0bd4ab56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WL6H63HWM4RGC7UPGWIS6HNVY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Farshad Khorrami, Francesco Croce, Nicolas Flammarion, Prashanth Krishnamurthy, Sara Ghazanfari, Siddharth Garg","submitted_at":"2024-12-13T22:38:09Z","abstract_excerpt":"Human perception of similarity across uni- and multimodal inputs is highly complex, making it challenging to develop automated metrics that accurately mimic it. General purpose vision-language models, such as CLIP and large multi-modal models (LMMs), can be applied as zero-shot perceptual metrics, and several recent works have developed models specialized in narrow perceptual tasks. However, the extent to which existing perceptual metrics align with human perception remains unclear. To investigate this question, we introduce UniSim-Bench, a benchmark encompassing 7 multi-modal perceptual simil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10594","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/2412.10594/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":"2026-07-05T09:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6RvuddiC8NpfJUGtwVnQZONwTY5yPvI+nkTkOul++HGBeLloB1/2gW58VAmUptSy88O6c5dN7vk506+rXGMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:40:53.168872Z"},"content_sha256":"477170afdb61921bf3fc009b1d30e54cda18a586cdde8f94e960e34a4f4ec6e6","schema_version":"1.0","event_id":"sha256:477170afdb61921bf3fc009b1d30e54cda18a586cdde8f94e960e34a4f4ec6e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/bundle.json","state_url":"https://pith.science/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/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":"2026-08-13T15:40:53Z","links":{"resolver":"https://pith.science/pith/WL6H63HWM4RGC7UPGWIS6HNVY7","bundle":"https://pith.science/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/bundle.json","state":"https://pith.science/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL6H63HWM4RGC7UPGWIS6HNVY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WL6H63HWM4RGC7UPGWIS6HNVY7","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":"e065d4edfd6b3474df2441339327346e1bc9dd87212f74db9262a55933475515","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T22:38:09Z","title_canon_sha256":"9ca4dc923f36439f541bb7f1b70f726b53e52f5b3c8fbb16b2d5be4a39c92975"},"schema_version":"1.0","source":{"id":"2412.10594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10594","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10594v1","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10594","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"WL6H63HWM4RG","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"WL6H63HWM4RGC7UP","created_at":"2026-07-05T09:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"WL6H63HW","created_at":"2026-07-05T09:49:18Z"}],"graph_snapshots":[{"event_id":"sha256:477170afdb61921bf3fc009b1d30e54cda18a586cdde8f94e960e34a4f4ec6e6","target":"graph","created_at":"2026-07-05T09:49:18Z","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/2412.10594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human perception of similarity across uni- and multimodal inputs is highly complex, making it challenging to develop automated metrics that accurately mimic it. General purpose vision-language models, such as CLIP and large multi-modal models (LMMs), can be applied as zero-shot perceptual metrics, and several recent works have developed models specialized in narrow perceptual tasks. However, the extent to which existing perceptual metrics align with human perception remains unclear. To investigate this question, we introduce UniSim-Bench, a benchmark encompassing 7 multi-modal perceptual simil","authors_text":"Farshad Khorrami, Francesco Croce, Nicolas Flammarion, Prashanth Krishnamurthy, Sara Ghazanfari, Siddharth Garg","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T22:38:09Z","title":"Towards Unified Benchmark and Models for Multi-Modal Perceptual Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10594","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:f89372f730e5f08dcda12e3f8dbdc8ce01b3a1eafd2c3aa546c2745d0bd4ab56","target":"record","created_at":"2026-07-05T09:49:18Z","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":"e065d4edfd6b3474df2441339327346e1bc9dd87212f74db9262a55933475515","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T22:38:09Z","title_canon_sha256":"9ca4dc923f36439f541bb7f1b70f726b53e52f5b3c8fbb16b2d5be4a39c92975"},"schema_version":"1.0","source":{"id":"2412.10594","kind":"arxiv","version":1}},"canonical_sha256":"b2fc7f6cf66722617e8f35912f1db5c7fbd7aff2711f2541c1ac91b46325a02d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2fc7f6cf66722617e8f35912f1db5c7fbd7aff2711f2541c1ac91b46325a02d","first_computed_at":"2026-07-05T09:49:18.183693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:18.183693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dQfLhPGSSCyZ74S3uGuhxRyZFSJw4S2zUmcId92uX02hFt0sYdQunvumHbOfkO3K/9FADy5dIb5W9pEABG8pDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:18.184190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f89372f730e5f08dcda12e3f8dbdc8ce01b3a1eafd2c3aa546c2745d0bd4ab56","sha256:477170afdb61921bf3fc009b1d30e54cda18a586cdde8f94e960e34a4f4ec6e6"],"state_sha256":"adea9949a2ed59b742a994b6f6c9d4067e0fc50f944f48c9715bac9d1dfd143b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xgskT+ewhe4ZJukQFWCjuqYAPOcBhbqutiD+ErTheiKl6Loa1ktW7H9J1qGJXhqvw7TFymkZ3hlxlR4bNSH0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:40:53.178033Z","bundle_sha256":"49566ef36fc0e3e5579ef24a8cea22c1f52a27977f17b3fc6027d7fc0b780d63"}}