{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CENNDUFQ3WCLWPXZ4UHGSNSNPE","short_pith_number":"pith:CENNDUFQ","schema_version":"1.0","canonical_sha256":"111ad1d0b0dd84bb3ef9e50e69364d791bb231118e4170021c4d1c6eae926cd0","source":{"kind":"arxiv","id":"2608.04750","version":1},"attestation_state":"computed","paper":{"title":"Simile Understanding in Text-to-Image Models: An Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hidetaka Kamigaito, Jingun Kwon, Katsuhiko Hayashi, Luecheng Wang, Manabu Okumura, Shintaro Ozaki, Taro Watanabe","submitted_at":"2026-08-05T12:18:28Z","abstract_excerpt":"Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce visually compelling outputs from simile prompts, yet even frontier models frequently misinterpret the metaphorical vehicle and confuse it with the object. These systematic failures reveal a gap between figurative language and object-level visual grounding in t2i models. To investigate this issue, we propose a scalable evaluation framework for simile understanding. Our framework includes (1) a controlled simile dataset in which metaphorical vehicl"},"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":"2608.04750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T12:18:28Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"e04689f2b6176bd0f3edbb1c9a085ed72e9a7ccb1fc1329a4414b31f8caa50db","abstract_canon_sha256":"4a4bca7c14f16c34727cb2a8cd0ffbc98383c7203fd2dd20f20bc0b5280f442c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:01.852058Z","signature_b64":"141t/N6Na4kbUzYhtNV8fWStmTHDRP3zACdTVLuItfhUgBrYU2XEuMrcAuy2MDt9ec4oGaJ1gjv58kGQY0hEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111ad1d0b0dd84bb3ef9e50e69364d791bb231118e4170021c4d1c6eae926cd0","last_reissued_at":"2026-08-06T01:47:01.850413Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:01.850413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simile Understanding in Text-to-Image Models: An Evaluation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Hidetaka Kamigaito, Jingun Kwon, Katsuhiko Hayashi, Luecheng Wang, Manabu Okumura, Shintaro Ozaki, Taro Watanabe","submitted_at":"2026-08-05T12:18:28Z","abstract_excerpt":"Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce visually compelling outputs from simile prompts, yet even frontier models frequently misinterpret the metaphorical vehicle and confuse it with the object. These systematic failures reveal a gap between figurative language and object-level visual grounding in t2i models. To investigate this issue, we propose a scalable evaluation framework for simile understanding. Our framework includes (1) a controlled simile dataset in which metaphorical vehicl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04750","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/2608.04750/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":"2608.04750","created_at":"2026-08-06T01:47:01.852321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04750v1","created_at":"2026-08-06T01:47:01.852321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04750","created_at":"2026-08-06T01:47:01.852321+00:00"},{"alias_kind":"pith_short_12","alias_value":"CENNDUFQ3WCL","created_at":"2026-08-06T01:47:01.852321+00:00"},{"alias_kind":"pith_short_16","alias_value":"CENNDUFQ3WCLWPXZ","created_at":"2026-08-06T01:47:01.852321+00:00"},{"alias_kind":"pith_short_8","alias_value":"CENNDUFQ","created_at":"2026-08-06T01:47:01.852321+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/CENNDUFQ3WCLWPXZ4UHGSNSNPE","json":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE.json","graph_json":"https://pith.science/api/pith-number/CENNDUFQ3WCLWPXZ4UHGSNSNPE/graph.json","events_json":"https://pith.science/api/pith-number/CENNDUFQ3WCLWPXZ4UHGSNSNPE/events.json","paper":"https://pith.science/paper/CENNDUFQ"},"agent_actions":{"view_html":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE","download_json":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE.json","view_paper":"https://pith.science/paper/CENNDUFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04750&json=true","fetch_graph":"https://pith.science/api/pith-number/CENNDUFQ3WCLWPXZ4UHGSNSNPE/graph.json","fetch_events":"https://pith.science/api/pith-number/CENNDUFQ3WCLWPXZ4UHGSNSNPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE/action/storage_attestation","attest_author":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE/action/author_attestation","sign_citation":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE/action/citation_signature","submit_replication":"https://pith.science/pith/CENNDUFQ3WCLWPXZ4UHGSNSNPE/action/replication_record"}},"created_at":"2026-08-06T01:47:01.852321+00:00","updated_at":"2026-08-06T01:47:01.852321+00:00"}