{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KJJTJDROBXZPXLYLGAA6O5326I","short_pith_number":"pith:KJJTJDRO","canonical_record":{"source":{"id":"2401.15688","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"01b43af2bc496775480e37125b015760d28b4743865273d5d2f49d4e652abb3d","abstract_canon_sha256":"538e2c80e2427a32c56a02b88705d7bd47f13de046ab5b766ec40c5aae2cb868"},"schema_version":"1.0"},"canonical_sha256":"5253348e2e0df2fbaf0b3001e7777af2014bcd1968cf613ff6f12a2cd65300dc","source":{"kind":"arxiv","id":"2401.15688","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15688","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15688v2","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15688","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"KJJTJDROBXZP","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"KJJTJDROBXZPXLYL","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"KJJTJDRO","created_at":"2026-07-05T07:39:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KJJTJDROBXZPXLYLGAA6O5326I","target":"record","payload":{"canonical_record":{"source":{"id":"2401.15688","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:18:39Z","cross_cats_sorted":[],"title_canon_sha256":"01b43af2bc496775480e37125b015760d28b4743865273d5d2f49d4e652abb3d","abstract_canon_sha256":"538e2c80e2427a32c56a02b88705d7bd47f13de046ab5b766ec40c5aae2cb868"},"schema_version":"1.0"},"canonical_sha256":"5253348e2e0df2fbaf0b3001e7777af2014bcd1968cf613ff6f12a2cd65300dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:13.900773Z","signature_b64":"N7uZI6fhH9rVTjCYwh5aANSBlcFRmi5ETe5V1DwnW9X+GO8+988CUzutH+JMLCGdn9ZOkCJJC0eHun+8NFhUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5253348e2e0df2fbaf0b3001e7777af2014bcd1968cf613ff6f12a2cd65300dc","last_reissued_at":"2026-07-05T07:39:13.900286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:13.900286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.15688","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Y/NslUC/UzAXmGcm222U39oU9aYlY/EVnuTVeSQK56yki5qSaESz33Ma/037BXIyaqINnn8yL+8/Cz+Z+dZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:56:04.483120Z"},"content_sha256":"6a35baf16a96efd871294357503971e73c8d79f7eab1fcbb98f3cf5b5188f3de","schema_version":"1.0","event_id":"sha256:6a35baf16a96efd871294357503971e73c8d79f7eab1fcbb98f3cf5b5188f3de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KJJTJDROBXZPXLYLGAA6O5326I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoxue Li, Enze Xie, Xihui Liu, Zhenguo Li, Zhenyu Wang, Zhongdao Wang","submitted_at":"2024-01-28T16:18:39Z","abstract_excerpt":"Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it comes to retaining object attributes and relationships. In this paper, we propose CompAgent, a training-free approach for compositional text-to-image generation, with a large language model (LLM) agent as its core. The fundamental idea underlying CompAgent is premised on a divide-and-conquer methodology. Given a complex text prompt containing multiple concept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15688","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/2401.15688/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"muqwZ+BslEF4RjTp8aKXAWJ1su1v/HozbqSa2ECdQl2nKBRQGbM0yIZFuWRNfjOJSNsJYNA9GNCdh4FBmKSFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:56:04.484170Z"},"content_sha256":"ccb56d974fb78d3630732c4cb380ddfd96c461c6cdbb841b8c60b8af0a5f3dd1","schema_version":"1.0","event_id":"sha256:ccb56d974fb78d3630732c4cb380ddfd96c461c6cdbb841b8c60b8af0a5f3dd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJJTJDROBXZPXLYLGAA6O5326I/bundle.json","state_url":"https://pith.science/pith/KJJTJDROBXZPXLYLGAA6O5326I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJJTJDROBXZPXLYLGAA6O5326I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T01:56:04Z","links":{"resolver":"https://pith.science/pith/KJJTJDROBXZPXLYLGAA6O5326I","bundle":"https://pith.science/pith/KJJTJDROBXZPXLYLGAA6O5326I/bundle.json","state":"https://pith.science/pith/KJJTJDROBXZPXLYLGAA6O5326I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJJTJDROBXZPXLYLGAA6O5326I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJJTJDROBXZPXLYLGAA6O5326I","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":"538e2c80e2427a32c56a02b88705d7bd47f13de046ab5b766ec40c5aae2cb868","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:18:39Z","title_canon_sha256":"01b43af2bc496775480e37125b015760d28b4743865273d5d2f49d4e652abb3d"},"schema_version":"1.0","source":{"id":"2401.15688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15688","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15688v2","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15688","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"KJJTJDROBXZP","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_16","alias_value":"KJJTJDROBXZPXLYL","created_at":"2026-07-05T07:39:13Z"},{"alias_kind":"pith_short_8","alias_value":"KJJTJDRO","created_at":"2026-07-05T07:39:13Z"}],"graph_snapshots":[{"event_id":"sha256:ccb56d974fb78d3630732c4cb380ddfd96c461c6cdbb841b8c60b8af0a5f3dd1","target":"graph","created_at":"2026-07-05T07:39:13Z","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/2401.15688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, especially when it comes to retaining object attributes and relationships. In this paper, we propose CompAgent, a training-free approach for compositional text-to-image generation, with a large language model (LLM) agent as its core. The fundamental idea underlying CompAgent is premised on a divide-and-conquer methodology. Given a complex text prompt containing multiple concept","authors_text":"Aoxue Li, Enze Xie, Xihui Liu, Zhenguo Li, Zhenyu Wang, Zhongdao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:18:39Z","title":"Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15688","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":"sha256:6a35baf16a96efd871294357503971e73c8d79f7eab1fcbb98f3cf5b5188f3de","target":"record","created_at":"2026-07-05T07:39:13Z","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":"538e2c80e2427a32c56a02b88705d7bd47f13de046ab5b766ec40c5aae2cb868","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-28T16:18:39Z","title_canon_sha256":"01b43af2bc496775480e37125b015760d28b4743865273d5d2f49d4e652abb3d"},"schema_version":"1.0","source":{"id":"2401.15688","kind":"arxiv","version":2}},"canonical_sha256":"5253348e2e0df2fbaf0b3001e7777af2014bcd1968cf613ff6f12a2cd65300dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5253348e2e0df2fbaf0b3001e7777af2014bcd1968cf613ff6f12a2cd65300dc","first_computed_at":"2026-07-05T07:39:13.900286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:13.900286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N7uZI6fhH9rVTjCYwh5aANSBlcFRmi5ETe5V1DwnW9X+GO8+988CUzutH+JMLCGdn9ZOkCJJC0eHun+8NFhUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:13.900773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a35baf16a96efd871294357503971e73c8d79f7eab1fcbb98f3cf5b5188f3de","sha256:ccb56d974fb78d3630732c4cb380ddfd96c461c6cdbb841b8c60b8af0a5f3dd1"],"state_sha256":"d3adbf6cfed6357d347b6234a34158ed5d02eeba0b81d797c0b38d4b95377466"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jH2wwsU6MV8Z0atBHWrkReFNnT6seaQlTiYVVFxNuOusJPHOtjslde+E+Sqz0NPrxKpnpo/mhSfS9UG6ZrDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:56:04.490681Z","bundle_sha256":"48643572d1bb7e6d6fdebb87252aba87dd4a70f4e34a75f3f53beb86b7df44d6"}}