{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7XMYVWFBJSJKY2II64KLM2E6UU","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":"ec963c85910f4893c7a4d6cbb6c000a4b61279fd8d929fa2c36eb51b9dbe8775","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T07:37:09Z","title_canon_sha256":"70115d659623bef8360f48c86fd7491eb290afba6764e416b5a58a06558a8256"},"schema_version":"1.0","source":{"id":"2503.10127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10127","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10127v2","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10127","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"7XMYVWFBJSJK","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"7XMYVWFBJSJKY2II","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"7XMYVWFB","created_at":"2026-07-05T10:41:21Z"}],"graph_snapshots":[{"event_id":"sha256:4b772df355ad4c03eff25c17b51a3db1cf667154a796e380b2fbe9f1980de07a","target":"graph","created_at":"2026-07-05T10:41:21Z","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/2503.10127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a unified layout planning and image generation model, PlanGen, which can pre-plan spatial layout conditions before generating images. Unlike previous diffusion-based models that treat layout planning and layout-to-image as two separate models, PlanGen jointly models the two tasks into one autoregressive transformer using only next-token prediction. PlanGen integrates layout conditions into the model as context without requiring specialized encoding of local captions and bounding box coordinates, which provides significant advantages over the previous embed-and-pool op","authors_text":"Ao Ma, Bo Cheng, Dawei Leng, Liebucha Wu, Qingxiang Jia, Runze He, Shanyuan Liu, Xiaoyu Wu, Yuhang Ma, Yuhui Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T07:37:09Z","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10127","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:e84ded23f5f36b6b3b87cc8866d62a9f7046d29a92e142b48abf7e5a35d841cd","target":"record","created_at":"2026-07-05T10:41:21Z","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":"ec963c85910f4893c7a4d6cbb6c000a4b61279fd8d929fa2c36eb51b9dbe8775","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T07:37:09Z","title_canon_sha256":"70115d659623bef8360f48c86fd7491eb290afba6764e416b5a58a06558a8256"},"schema_version":"1.0","source":{"id":"2503.10127","kind":"arxiv","version":2}},"canonical_sha256":"fdd98ad8a14c92ac6908f714b6689ea505705a799cbb6c2f0522c939451c3c2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdd98ad8a14c92ac6908f714b6689ea505705a799cbb6c2f0522c939451c3c2b","first_computed_at":"2026-07-05T10:41:21.482452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:21.482452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MjlDi5fv0eEI7Aja/CzYuctF6nPpFAUBrCUP2LUj7047MfcwJdnjP0KS6ZjXKmWrDcZxTEUiLwim8bncCJ1rDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:21.482948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e84ded23f5f36b6b3b87cc8866d62a9f7046d29a92e142b48abf7e5a35d841cd","sha256:4b772df355ad4c03eff25c17b51a3db1cf667154a796e380b2fbe9f1980de07a"],"state_sha256":"e261b430e5793fbb8ff25e15de99855b0f8f1e5bd05677e6fc231a9673d1fb00"}