{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MVGOTCZZRI73WDYLSA2TNYB4V7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c2d149372d43dca7c77b34f2b336971f86d28fcae4940a580b4428ca22d3aebd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T22:29:56Z","title_canon_sha256":"abde29c0c4e541d9226707a64899a9201f6cd4055c03b33c2497dc149c12abb8"},"schema_version":"1.0","source":{"id":"2412.06089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06089","created_at":"2026-07-05T10:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06089v2","created_at":"2026-07-05T10:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06089","created_at":"2026-07-05T10:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"MVGOTCZZRI73","created_at":"2026-07-05T10:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"MVGOTCZZRI73WDYL","created_at":"2026-07-05T10:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"MVGOTCZZ","created_at":"2026-07-05T10:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:4bffa2bba23f9247925d2f47c21e2696a13486fe9f4d645bf28c11d8e630917d","target":"graph","created_at":"2026-07-05T10:28:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.06089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image (T2I) generation has seen significant progress with diffusion models, enabling generation of photo-realistic images from text prompts. Despite this progress, existing methods still face challenges in following complex text prompts, especially those requiring compositional and multi-step reasoning. Given such complex instructions, SOTA models often make mistakes in faithfully modeling object attributes, and relationships among them. In this work, we present an alternate paradigm for T2I synthesis, decomposing the task of complex multi-step generation into three steps, (a) Generate","authors_text":"Ashish Goswami, Harman Singh, Parag Singla, Prathosh A. P, Santhosh Rishi Deshineni, Satyam Kumar Modi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T22:29:56Z","title":"GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06089","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:86fad98cbef22c6fb8156caf7e761e93eea1fdabb04d6373eda3278f702b2635","target":"record","created_at":"2026-07-05T10:28:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c2d149372d43dca7c77b34f2b336971f86d28fcae4940a580b4428ca22d3aebd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T22:29:56Z","title_canon_sha256":"abde29c0c4e541d9226707a64899a9201f6cd4055c03b33c2497dc149c12abb8"},"schema_version":"1.0","source":{"id":"2412.06089","kind":"arxiv","version":2}},"canonical_sha256":"654ce98b398a3fbb0f0b903536e03cafd5a1449ae068539a8c15dae23c81909e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"654ce98b398a3fbb0f0b903536e03cafd5a1449ae068539a8c15dae23c81909e","first_computed_at":"2026-07-05T10:28:30.379571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:30.379571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hK72uYTGmqguyatI6eEH/D5gqAsbuxAOdgzYB9jQP+jWGA7hHR30pn6EKTnBGNnJ9yaMSm1PmNdUhV/jY7v4BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:30.380369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86fad98cbef22c6fb8156caf7e761e93eea1fdabb04d6373eda3278f702b2635","sha256:4bffa2bba23f9247925d2f47c21e2696a13486fe9f4d645bf28c11d8e630917d"],"state_sha256":"0dd104e170c0b3ecf7b42244347b8f8c4469b7a34ebcf8bc75c7cdfae27eaa47"}