{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KGHMTST3WJY7O3ALUR3ZKC6CIK","short_pith_number":"pith:KGHMTST3","schema_version":"1.0","canonical_sha256":"518ec9ca7bb271f76c0ba477950bc242aef3959a83100a8b54abbc9d910b6bd4","source":{"kind":"arxiv","id":"2605.24702","version":1},"attestation_state":"computed","paper":{"title":"Do Image-Text Metrics Respect Semantic Invariances?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Agarwal, Dan Roth, Hansa Meghwani, Hitesh Laxmichand Patel, Jyotika Singh, Karan Dua, Matthew Rowe, Meizhu Liu, Michael Avendi, Sujith Ravi, Tao Sheng, Yassi Abbasi","submitted_at":"2026-05-23T18:53:51Z","abstract_excerpt":"Reference-free image-to-text evaluators are now standard for scoring image-caption alignment, yet it is unclear whether they respect semantic invariances. We present an invariance probe on five popular evaluators (CLIPScore, PAC-S, UMIC, FLEUR, and a deterministic LLM judge) under semantics-preserving perturbations along three axes -- spatial (flips, context-preserving repositioning, light rotations), object (scale, category), and socio-linguistic framing (cultural/economic adjectives with neutral and length-matched controls). Across curated slices of three detection datasets and three caption"},"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":"2605.24702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-23T18:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"d5afd1c33b51622015342856817de1eb0bc88f72bd9086157c8a769267dd32d0","abstract_canon_sha256":"e0ffc590a05435f2f447f665548499153b59af5e0f85f3151caebb100fc5355f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:54.079614Z","signature_b64":"39ZyeIiTH8wzILT5ewb4bsUD++BvPHidQ/XCSr5Gfc8dVMPnJScFjvDwjj8swyEy46mmHqhbCckFuL3wqxPNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"518ec9ca7bb271f76c0ba477950bc242aef3959a83100a8b54abbc9d910b6bd4","last_reissued_at":"2026-05-26T01:03:54.078741Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:54.078741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Image-Text Metrics Respect Semantic Invariances?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit Agarwal, Dan Roth, Hansa Meghwani, Hitesh Laxmichand Patel, Jyotika Singh, Karan Dua, Matthew Rowe, Meizhu Liu, Michael Avendi, Sujith Ravi, Tao Sheng, Yassi Abbasi","submitted_at":"2026-05-23T18:53:51Z","abstract_excerpt":"Reference-free image-to-text evaluators are now standard for scoring image-caption alignment, yet it is unclear whether they respect semantic invariances. We present an invariance probe on five popular evaluators (CLIPScore, PAC-S, UMIC, FLEUR, and a deterministic LLM judge) under semantics-preserving perturbations along three axes -- spatial (flips, context-preserving repositioning, light rotations), object (scale, category), and socio-linguistic framing (cultural/economic adjectives with neutral and length-matched controls). Across curated slices of three detection datasets and three caption"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24702","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/2605.24702/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":"2605.24702","created_at":"2026-05-26T01:03:54.078880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24702v1","created_at":"2026-05-26T01:03:54.078880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24702","created_at":"2026-05-26T01:03:54.078880+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGHMTST3WJY7","created_at":"2026-05-26T01:03:54.078880+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGHMTST3WJY7O3AL","created_at":"2026-05-26T01:03:54.078880+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGHMTST3","created_at":"2026-05-26T01:03:54.078880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK","json":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK.json","graph_json":"https://pith.science/api/pith-number/KGHMTST3WJY7O3ALUR3ZKC6CIK/graph.json","events_json":"https://pith.science/api/pith-number/KGHMTST3WJY7O3ALUR3ZKC6CIK/events.json","paper":"https://pith.science/paper/KGHMTST3"},"agent_actions":{"view_html":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK","download_json":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK.json","view_paper":"https://pith.science/paper/KGHMTST3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24702&json=true","fetch_graph":"https://pith.science/api/pith-number/KGHMTST3WJY7O3ALUR3ZKC6CIK/graph.json","fetch_events":"https://pith.science/api/pith-number/KGHMTST3WJY7O3ALUR3ZKC6CIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK/action/storage_attestation","attest_author":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK/action/author_attestation","sign_citation":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK/action/citation_signature","submit_replication":"https://pith.science/pith/KGHMTST3WJY7O3ALUR3ZKC6CIK/action/replication_record"}},"created_at":"2026-05-26T01:03:54.078880+00:00","updated_at":"2026-05-26T01:03:54.078880+00:00"}