{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFSS2CZQGYHVIMVX3RLR74BVC5","short_pith_number":"pith:PFSS2CZQ","schema_version":"1.0","canonical_sha256":"79652d0b30360f5432b7dc571ff035177822c81e37e8b9e7d088a2b05ede02ee","source":{"kind":"arxiv","id":"2505.04650","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.GR","authors_text":"Gaytri Jena, Kapil Wanaskar, Magdalini Eirinaki","submitted_at":"2025-05-06T18:53:34Z","abstract_excerpt":"This work presents an open-source unified benchmarking and evaluation framework for text-to-image generation models, with a particular focus on the impact of metadata augmented prompts. Leveraging the DeepFashion-MultiModal dataset, we assess generated outputs through a comprehensive set of quantitative metrics, including Weighted Score, CLIP (Contrastive Language Image Pre-training)-based similarity, LPIPS (Learned Perceptual Image Patch Similarity), FID (Frechet Inception Distance), and retrieval-based measures, as well as qualitative analysis. Our results demonstrate that structured metadat"},"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":"2505.04650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-05-06T18:53:34Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"f9afd72b0645c158e11fb24997c3e6c7e724e480189adaf2332804514eab7e4f","abstract_canon_sha256":"733d50d429b1345e97e481d3a7d82159b6ca4fd92e95bc539d2cbbaeec26eb92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:10.884792Z","signature_b64":"vJ04qUpCsoh+LPUev8YQqIT2sc4QUiJ/a0HEObvck7fD1u0msi9wFEGCUZZqXJe3kjFV+MMS/+9bIQGpljecAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79652d0b30360f5432b7dc571ff035177822c81e37e8b9e7d088a2b05ede02ee","last_reissued_at":"2026-07-05T11:00:10.884293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:10.884293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.GR","authors_text":"Gaytri Jena, Kapil Wanaskar, Magdalini Eirinaki","submitted_at":"2025-05-06T18:53:34Z","abstract_excerpt":"This work presents an open-source unified benchmarking and evaluation framework for text-to-image generation models, with a particular focus on the impact of metadata augmented prompts. Leveraging the DeepFashion-MultiModal dataset, we assess generated outputs through a comprehensive set of quantitative metrics, including Weighted Score, CLIP (Contrastive Language Image Pre-training)-based similarity, LPIPS (Learned Perceptual Image Patch Similarity), FID (Frechet Inception Distance), and retrieval-based measures, as well as qualitative analysis. Our results demonstrate that structured metadat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04650","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/2505.04650/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":"2505.04650","created_at":"2026-07-05T11:00:10.884365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04650v1","created_at":"2026-07-05T11:00:10.884365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04650","created_at":"2026-07-05T11:00:10.884365+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFSS2CZQGYHV","created_at":"2026-07-05T11:00:10.884365+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFSS2CZQGYHVIMVX","created_at":"2026-07-05T11:00:10.884365+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFSS2CZQ","created_at":"2026-07-05T11:00:10.884365+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/PFSS2CZQGYHVIMVX3RLR74BVC5","json":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5.json","graph_json":"https://pith.science/api/pith-number/PFSS2CZQGYHVIMVX3RLR74BVC5/graph.json","events_json":"https://pith.science/api/pith-number/PFSS2CZQGYHVIMVX3RLR74BVC5/events.json","paper":"https://pith.science/paper/PFSS2CZQ"},"agent_actions":{"view_html":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5","download_json":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5.json","view_paper":"https://pith.science/paper/PFSS2CZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04650&json=true","fetch_graph":"https://pith.science/api/pith-number/PFSS2CZQGYHVIMVX3RLR74BVC5/graph.json","fetch_events":"https://pith.science/api/pith-number/PFSS2CZQGYHVIMVX3RLR74BVC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5/action/storage_attestation","attest_author":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5/action/author_attestation","sign_citation":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5/action/citation_signature","submit_replication":"https://pith.science/pith/PFSS2CZQGYHVIMVX3RLR74BVC5/action/replication_record"}},"created_at":"2026-07-05T11:00:10.884365+00:00","updated_at":"2026-07-05T11:00:10.884365+00:00"}