{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VPD5CK4BOSC7F42P62HO5EMLK5","short_pith_number":"pith:VPD5CK4B","schema_version":"1.0","canonical_sha256":"abc7d12b817485f2f34ff68eee918b576ccef14e64ee6da92271320207b3fb37","source":{"kind":"arxiv","id":"2507.20536","version":2},"attestation_state":"computed","paper":{"title":"T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chieh-Yun Chen, Gong Zhang, Humphrey Shi, Min Shi","submitted_at":"2025-07-28T05:41:22Z","abstract_excerpt":"Text-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While techniques such as automatic prompt engineering, controlled text embeddings, denoising, and multi-turn generation mitigate these issues, they offer limited controllability, or often necessitate additional training, restricting the generalization abilities. Thus, we introduce T2I-Copilot, a training-free multi-agent system that leverages collaboration between (Multimodal) Large L"},"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":"2507.20536","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T05:41:22Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"7e6905fa346c98399985549f14565c5c624ea39416e9cd5f984cfb498d976009","abstract_canon_sha256":"13d3e3a1042609935e1f25930429c927776c57a4f232f7dc4f54ae175936d255"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:53.773636Z","signature_b64":"U1qxkcsRiPPHJ4i45sh354Vg72zdVBRt4AGGWiJMoWZbSy1ZkK/52Nz8CsS1dHkOgpyIE/U5l08qrmDmfQSqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abc7d12b817485f2f34ff68eee918b576ccef14e64ee6da92271320207b3fb37","last_reissued_at":"2026-07-05T11:44:53.773247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:53.773247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Chieh-Yun Chen, Gong Zhang, Humphrey Shi, Min Shi","submitted_at":"2025-07-28T05:41:22Z","abstract_excerpt":"Text-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While techniques such as automatic prompt engineering, controlled text embeddings, denoising, and multi-turn generation mitigate these issues, they offer limited controllability, or often necessitate additional training, restricting the generalization abilities. Thus, we introduce T2I-Copilot, a training-free multi-agent system that leverages collaboration between (Multimodal) Large L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20536","kind":"arxiv","version":2},"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/2507.20536/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":"2507.20536","created_at":"2026-07-05T11:44:53.773303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20536v2","created_at":"2026-07-05T11:44:53.773303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20536","created_at":"2026-07-05T11:44:53.773303+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPD5CK4BOSC7","created_at":"2026-07-05T11:44:53.773303+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPD5CK4BOSC7F42P","created_at":"2026-07-05T11:44:53.773303+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPD5CK4B","created_at":"2026-07-05T11:44:53.773303+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/VPD5CK4BOSC7F42P62HO5EMLK5","json":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5.json","graph_json":"https://pith.science/api/pith-number/VPD5CK4BOSC7F42P62HO5EMLK5/graph.json","events_json":"https://pith.science/api/pith-number/VPD5CK4BOSC7F42P62HO5EMLK5/events.json","paper":"https://pith.science/paper/VPD5CK4B"},"agent_actions":{"view_html":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5","download_json":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5.json","view_paper":"https://pith.science/paper/VPD5CK4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20536&json=true","fetch_graph":"https://pith.science/api/pith-number/VPD5CK4BOSC7F42P62HO5EMLK5/graph.json","fetch_events":"https://pith.science/api/pith-number/VPD5CK4BOSC7F42P62HO5EMLK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5/action/storage_attestation","attest_author":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5/action/author_attestation","sign_citation":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5/action/citation_signature","submit_replication":"https://pith.science/pith/VPD5CK4BOSC7F42P62HO5EMLK5/action/replication_record"}},"created_at":"2026-07-05T11:44:53.773303+00:00","updated_at":"2026-07-05T11:44:53.773303+00:00"}