{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LU3OBIFG5M2KYQ7QA5CPJADAJU","short_pith_number":"pith:LU3OBIFG","schema_version":"1.0","canonical_sha256":"5d36e0a0a6eb34ac43f00744f480604d2c46b34961a8f90270a7e8a4fd733b15","source":{"kind":"arxiv","id":"2412.18645","version":3},"attestation_state":"computed","paper":{"title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azim Ospanov, Farzan Farnia, Mohammad Jalali","submitted_at":"2024-12-24T18:07:57Z","abstract_excerpt":"The use of CLIP embeddings to assess the fidelity of samples produced by text-to-image generative models has been extensively explored in the literature. While the widely adopted CLIPScore, derived from the cosine similarity of text and image embeddings, effectively measures the alignment of a generated image, it does not quantify the diversity of images generated by a text-to-image model. In this work, we extend the application of CLIP embeddings to quantify and interpret the intrinsic diversity of text-to-image models, which are responsible for generating diverse images from similar text pro"},"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":"2412.18645","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:07:57Z","cross_cats_sorted":[],"title_canon_sha256":"5f745dc21c0ef70ec113fedc1c476f9f7c3474c0f89fe1d66c8f4c74bbe56231","abstract_canon_sha256":"60116ba5eb0baf47f3fe6513d4cdf939cba4e2023ee7eea1e2b3bb036aa4eb4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:17.008847Z","signature_b64":"q5GsmiIUxARhGef32u9MlMmN0Zp+MKeX6ZZIKAe3pJZ0T9fB19oP4Sak0FCEYvnZpwCP9Do+6UNYdUsSbr5EDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d36e0a0a6eb34ac43f00744f480604d2c46b34961a8f90270a7e8a4fd733b15","last_reissued_at":"2026-07-05T11:47:17.008348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:17.008348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azim Ospanov, Farzan Farnia, Mohammad Jalali","submitted_at":"2024-12-24T18:07:57Z","abstract_excerpt":"The use of CLIP embeddings to assess the fidelity of samples produced by text-to-image generative models has been extensively explored in the literature. While the widely adopted CLIPScore, derived from the cosine similarity of text and image embeddings, effectively measures the alignment of a generated image, it does not quantify the diversity of images generated by a text-to-image model. In this work, we extend the application of CLIP embeddings to quantify and interpret the intrinsic diversity of text-to-image models, which are responsible for generating diverse images from similar text pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18645","kind":"arxiv","version":3},"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/2412.18645/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":"2412.18645","created_at":"2026-07-05T11:47:17.008414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18645v3","created_at":"2026-07-05T11:47:17.008414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18645","created_at":"2026-07-05T11:47:17.008414+00:00"},{"alias_kind":"pith_short_12","alias_value":"LU3OBIFG5M2K","created_at":"2026-07-05T11:47:17.008414+00:00"},{"alias_kind":"pith_short_16","alias_value":"LU3OBIFG5M2KYQ7Q","created_at":"2026-07-05T11:47:17.008414+00:00"},{"alias_kind":"pith_short_8","alias_value":"LU3OBIFG","created_at":"2026-07-05T11:47:17.008414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02557","citing_title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU","json":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU.json","graph_json":"https://pith.science/api/pith-number/LU3OBIFG5M2KYQ7QA5CPJADAJU/graph.json","events_json":"https://pith.science/api/pith-number/LU3OBIFG5M2KYQ7QA5CPJADAJU/events.json","paper":"https://pith.science/paper/LU3OBIFG"},"agent_actions":{"view_html":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU","download_json":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU.json","view_paper":"https://pith.science/paper/LU3OBIFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18645&json=true","fetch_graph":"https://pith.science/api/pith-number/LU3OBIFG5M2KYQ7QA5CPJADAJU/graph.json","fetch_events":"https://pith.science/api/pith-number/LU3OBIFG5M2KYQ7QA5CPJADAJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU/action/storage_attestation","attest_author":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU/action/author_attestation","sign_citation":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU/action/citation_signature","submit_replication":"https://pith.science/pith/LU3OBIFG5M2KYQ7QA5CPJADAJU/action/replication_record"}},"created_at":"2026-07-05T11:47:17.008414+00:00","updated_at":"2026-07-05T11:47:17.008414+00:00"}