{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P37EIKSRQEH2CQCPCYOPIVZL4M","short_pith_number":"pith:P37EIKSR","schema_version":"1.0","canonical_sha256":"7efe442a51810fa1404f161cf4572be3119e81e52730806bfafac86be17e3c43","source":{"kind":"arxiv","id":"2508.18569","version":1},"attestation_state":"computed","paper":{"title":"The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Diptesh Kanojia, Fatemeh Nazarieh, Girish A. Koushik, Katherine Birch, Shenbin Qian","submitted_at":"2025-08-26T00:04:01Z","abstract_excerpt":"Visual metaphor generation is a challenging task that aims to generate an image given an input text metaphor. Inherently, it needs language understanding to bind a source concept with a target concept, in a way that preserves meaning while ensuring visual coherence. We propose a self-evaluating visual metaphor generation framework that focuses on metaphor alignment. Our self-evaluation approach combines existing metrics with our newly proposed metaphor decomposition score and a meaning alignment (MA) metric. Within this setup, we explore two novel approaches: a training-free pipeline that expl"},"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":"2508.18569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T00:04:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5004f9c776563776d2eba340281e935d70bcfce74876e40c39a489f92a12f133","abstract_canon_sha256":"fb0fccd7831fc927d480949a8feea1fee8b0086d6c17772072bde77f233f7207"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:26.873171Z","signature_b64":"1/QvViVGu5hsKrP/eIJn6BkvPe46gyZv59ztf3mooH5g+mfEYXhSnUlTqiht55DisDVivIEeMrrOsXJberAbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7efe442a51810fa1404f161cf4572be3119e81e52730806bfafac86be17e3c43","last_reissued_at":"2026-07-05T11:59:26.872595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:26.872595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Mind's Eye: A Multi-Faceted Reward Framework for Guiding Visual Metaphor Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Diptesh Kanojia, Fatemeh Nazarieh, Girish A. Koushik, Katherine Birch, Shenbin Qian","submitted_at":"2025-08-26T00:04:01Z","abstract_excerpt":"Visual metaphor generation is a challenging task that aims to generate an image given an input text metaphor. Inherently, it needs language understanding to bind a source concept with a target concept, in a way that preserves meaning while ensuring visual coherence. We propose a self-evaluating visual metaphor generation framework that focuses on metaphor alignment. Our self-evaluation approach combines existing metrics with our newly proposed metaphor decomposition score and a meaning alignment (MA) metric. Within this setup, we explore two novel approaches: a training-free pipeline that expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18569","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/2508.18569/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":"2508.18569","created_at":"2026-07-05T11:59:26.872678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18569v1","created_at":"2026-07-05T11:59:26.872678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18569","created_at":"2026-07-05T11:59:26.872678+00:00"},{"alias_kind":"pith_short_12","alias_value":"P37EIKSRQEH2","created_at":"2026-07-05T11:59:26.872678+00:00"},{"alias_kind":"pith_short_16","alias_value":"P37EIKSRQEH2CQCP","created_at":"2026-07-05T11:59:26.872678+00:00"},{"alias_kind":"pith_short_8","alias_value":"P37EIKSR","created_at":"2026-07-05T11:59:26.872678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04750","citing_title":"Simile Understanding in Text-to-Image Models: An Evaluation Framework","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M","json":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M.json","graph_json":"https://pith.science/api/pith-number/P37EIKSRQEH2CQCPCYOPIVZL4M/graph.json","events_json":"https://pith.science/api/pith-number/P37EIKSRQEH2CQCPCYOPIVZL4M/events.json","paper":"https://pith.science/paper/P37EIKSR"},"agent_actions":{"view_html":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M","download_json":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M.json","view_paper":"https://pith.science/paper/P37EIKSR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18569&json=true","fetch_graph":"https://pith.science/api/pith-number/P37EIKSRQEH2CQCPCYOPIVZL4M/graph.json","fetch_events":"https://pith.science/api/pith-number/P37EIKSRQEH2CQCPCYOPIVZL4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M/action/storage_attestation","attest_author":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M/action/author_attestation","sign_citation":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M/action/citation_signature","submit_replication":"https://pith.science/pith/P37EIKSRQEH2CQCPCYOPIVZL4M/action/replication_record"}},"created_at":"2026-07-05T11:59:26.872678+00:00","updated_at":"2026-07-05T11:59:26.872678+00:00"}