{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3HMQXG4WPXVZEHV3JWMFC53NB4","short_pith_number":"pith:3HMQXG4W","schema_version":"1.0","canonical_sha256":"d9d90b9b967deb921ebb4d9851776d0f173c12eef81eb444cd1764dceacae713","source":{"kind":"arxiv","id":"2507.03275","version":1},"attestation_state":"computed","paper":{"title":"ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Berk Tinaz, Haosheng Gan, Mahdi Soltanolkotabi, Mohammad Shahab Sepehri, Zalan Fabian","submitted_at":"2025-07-04T03:27:04Z","abstract_excerpt":"Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We introduce ConceptMix++, a framework that disentangles prompt phrasing from visual generation capabilities by applying iterative prompt optimization. Building on ConceptMix, our approach incorporates a multimodal optimization pipeline that leverages vision-language model feedback to refine prompts systematically. Through extensive experiments across multiple diffus"},"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":"2507.03275","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-04T03:27:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d21b2cd94d7f885debba86e8b4b91dbca893dd7ce4c2eaf5cc621ef8419c3b19","abstract_canon_sha256":"08f44f1cc710f984f31ffbebc00546e0848422b8b2fbe4164d7a38b1b834e571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:55.967748Z","signature_b64":"UmfSPJZlgr4ufxO26d0K//8KseEcmY/XLtRkGzGsUlDAtnHoM4WZIZ61mIjadP+twhKMQJeD9IuWDXqGaWm8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9d90b9b967deb921ebb4d9851776d0f173c12eef81eb444cd1764dceacae713","last_reissued_at":"2026-07-05T11:31:55.967102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:55.967102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Berk Tinaz, Haosheng Gan, Mahdi Soltanolkotabi, Mohammad Shahab Sepehri, Zalan Fabian","submitted_at":"2025-07-04T03:27:04Z","abstract_excerpt":"Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We introduce ConceptMix++, a framework that disentangles prompt phrasing from visual generation capabilities by applying iterative prompt optimization. Building on ConceptMix, our approach incorporates a multimodal optimization pipeline that leverages vision-language model feedback to refine prompts systematically. Through extensive experiments across multiple diffus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03275","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/2507.03275/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":"2507.03275","created_at":"2026-07-05T11:31:55.967176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03275v1","created_at":"2026-07-05T11:31:55.967176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03275","created_at":"2026-07-05T11:31:55.967176+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HMQXG4WPXVZ","created_at":"2026-07-05T11:31:55.967176+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HMQXG4WPXVZEHV3","created_at":"2026-07-05T11:31:55.967176+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HMQXG4W","created_at":"2026-07-05T11:31:55.967176+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/3HMQXG4WPXVZEHV3JWMFC53NB4","json":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4.json","graph_json":"https://pith.science/api/pith-number/3HMQXG4WPXVZEHV3JWMFC53NB4/graph.json","events_json":"https://pith.science/api/pith-number/3HMQXG4WPXVZEHV3JWMFC53NB4/events.json","paper":"https://pith.science/paper/3HMQXG4W"},"agent_actions":{"view_html":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4","download_json":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4.json","view_paper":"https://pith.science/paper/3HMQXG4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03275&json=true","fetch_graph":"https://pith.science/api/pith-number/3HMQXG4WPXVZEHV3JWMFC53NB4/graph.json","fetch_events":"https://pith.science/api/pith-number/3HMQXG4WPXVZEHV3JWMFC53NB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4/action/storage_attestation","attest_author":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4/action/author_attestation","sign_citation":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4/action/citation_signature","submit_replication":"https://pith.science/pith/3HMQXG4WPXVZEHV3JWMFC53NB4/action/replication_record"}},"created_at":"2026-07-05T11:31:55.967176+00:00","updated_at":"2026-07-05T11:31:55.967176+00:00"}