{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GSHM7C4IIHC2PILSYEKYRVK6IH","short_pith_number":"pith:GSHM7C4I","schema_version":"1.0","canonical_sha256":"348ecf8b8841c5a7a172c11588d55e41df32914a8a267bff7ebca8c9e0cb9f52","source":{"kind":"arxiv","id":"2607.24353","version":1},"attestation_state":"computed","paper":{"title":"PRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Tang, Hao Wang, Hongjie Luo, Tianxu Wang, Ying Zhang","submitted_at":"2026-07-27T12:31:32Z","abstract_excerpt":"Text-to-image generation models can synthesize high-quality images from natural language descriptions, but their performance remains highly sensitive to prompt formulation. Existing prompt optimization methods mainly rely on text-side rewriting, prompt expansion, or external reward signals, offering limited image-grounded diagnosis and weak support for learning reusable optimisation policies. In this paper, we propose PRISM, a Prompt Refinement framework via Image-grounded Self-rewarding Mechanism. PRISM closes the prompt-image-feedback loop by interpreting generated images with structured vis"},"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":"2607.24353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T12:31:32Z","cross_cats_sorted":[],"title_canon_sha256":"757eab3d61642b9fdfa9715699c4146aefd714f07d499ad0ffa39400c0ed3db9","abstract_canon_sha256":"db7ee3fdb5943e145f36abfd348fe91ff14e92a03839afbcdfd895170b80aa1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:58.829903Z","signature_b64":"/cMez5yw9+NnzThRorQEhautWb98W/1aDb3YCZzUsGSs7/BBCGW2XsP+AfLXlVQPG5fvtTR6sQR+eRzgNwuNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348ecf8b8841c5a7a172c11588d55e41df32914a8a267bff7ebca8c9e0cb9f52","last_reissued_at":"2026-07-28T02:23:58.829060Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:58.829060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Tang, Hao Wang, Hongjie Luo, Tianxu Wang, Ying Zhang","submitted_at":"2026-07-27T12:31:32Z","abstract_excerpt":"Text-to-image generation models can synthesize high-quality images from natural language descriptions, but their performance remains highly sensitive to prompt formulation. Existing prompt optimization methods mainly rely on text-side rewriting, prompt expansion, or external reward signals, offering limited image-grounded diagnosis and weak support for learning reusable optimisation policies. In this paper, we propose PRISM, a Prompt Refinement framework via Image-grounded Self-rewarding Mechanism. PRISM closes the prompt-image-feedback loop by interpreting generated images with structured vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24353","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/2607.24353/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":"2607.24353","created_at":"2026-07-28T02:23:58.829504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24353v1","created_at":"2026-07-28T02:23:58.829504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24353","created_at":"2026-07-28T02:23:58.829504+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSHM7C4IIHC2","created_at":"2026-07-28T02:23:58.829504+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSHM7C4IIHC2PILS","created_at":"2026-07-28T02:23:58.829504+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSHM7C4I","created_at":"2026-07-28T02:23:58.829504+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/GSHM7C4IIHC2PILSYEKYRVK6IH","json":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH.json","graph_json":"https://pith.science/api/pith-number/GSHM7C4IIHC2PILSYEKYRVK6IH/graph.json","events_json":"https://pith.science/api/pith-number/GSHM7C4IIHC2PILSYEKYRVK6IH/events.json","paper":"https://pith.science/paper/GSHM7C4I"},"agent_actions":{"view_html":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH","download_json":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH.json","view_paper":"https://pith.science/paper/GSHM7C4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24353&json=true","fetch_graph":"https://pith.science/api/pith-number/GSHM7C4IIHC2PILSYEKYRVK6IH/graph.json","fetch_events":"https://pith.science/api/pith-number/GSHM7C4IIHC2PILSYEKYRVK6IH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH/action/storage_attestation","attest_author":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH/action/author_attestation","sign_citation":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH/action/citation_signature","submit_replication":"https://pith.science/pith/GSHM7C4IIHC2PILSYEKYRVK6IH/action/replication_record"}},"created_at":"2026-07-28T02:23:58.829504+00:00","updated_at":"2026-07-28T02:23:58.829504+00:00"}