{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CYX5P2KNXUPWAUPCOVI2NY4FQ7","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":"e25242975e85a45fc242ecda804d972f53a0dd954935a7967229869aaeaf963b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T13:42:01Z","title_canon_sha256":"4e904f781921724d841735ef285ae2c6172b56b1f99ea2a17c3c7d4135a5895a"},"schema_version":"1.0","source":{"id":"2401.16157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16157","created_at":"2026-07-05T07:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16157v1","created_at":"2026-07-05T07:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16157","created_at":"2026-07-05T07:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"CYX5P2KNXUPW","created_at":"2026-07-05T07:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"CYX5P2KNXUPWAUPC","created_at":"2026-07-05T07:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"CYX5P2KN","created_at":"2026-07-05T07:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:f56b82704a53538193e2dcce69eee8046e8c64b578a3d1fdb96bf023c1a1d960","target":"graph","created_at":"2026-07-05T07:38:44Z","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/2401.16157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, text-to-image diffusion models have demonstrated impressive ability to generate high-quality images conditioned on the textual input. However, these models struggle to accurately adhere to textual instructions regarding spatial layout information. While previous research has primarily focused on aligning cross-attention maps with layout conditions, they overlook the impact of the initialization noise on the layout guidance. To achieve better layout control, we propose leveraging a spatial-aware initialization noise during the denoising process. Specifically, we find that the inverted","authors_text":"Jun Zhang, Teng Li, Wenqiang Sun, Zehong Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T13:42:01Z","title":"Spatial-Aware Latent Initialization for Controllable Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16157","kind":"arxiv","version":1},"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:f0e7fc829be42154774d824779dc4bacba9249e9e20b696d76d79af2b180dd39","target":"record","created_at":"2026-07-05T07:38:44Z","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":"e25242975e85a45fc242ecda804d972f53a0dd954935a7967229869aaeaf963b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T13:42:01Z","title_canon_sha256":"4e904f781921724d841735ef285ae2c6172b56b1f99ea2a17c3c7d4135a5895a"},"schema_version":"1.0","source":{"id":"2401.16157","kind":"arxiv","version":1}},"canonical_sha256":"162fd7e94dbd1f6051e27551a6e38587e44ffa2abfa81a542328291f8180cf2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"162fd7e94dbd1f6051e27551a6e38587e44ffa2abfa81a542328291f8180cf2b","first_computed_at":"2026-07-05T07:38:44.908988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:44.908988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toPXFjM8yXF30djlEUk5yOgYX5uXhRdMn39HdK7sqbgc1TrOt8+JbV6s6CwhGMWUmwO58s9aLDsLJtYXiaMsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:44.909408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0e7fc829be42154774d824779dc4bacba9249e9e20b696d76d79af2b180dd39","sha256:f56b82704a53538193e2dcce69eee8046e8c64b578a3d1fdb96bf023c1a1d960"],"state_sha256":"e7e38675db9e1777338a805105a5c431921821776ead889337716729ef9f5fba"}