{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TDAI6VTJLNAR3GR4KQ3ASO22P6","short_pith_number":"pith:TDAI6VTJ","canonical_record":{"source":{"id":"2605.13856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T11:38:12Z","cross_cats_sorted":[],"title_canon_sha256":"f6e94dab6d19a53b80c861c8194834b2a3d8aae7013b517bd6b4c5aa78847f78","abstract_canon_sha256":"387524f043397af914da8e60ce3e37996bdf4bd8044b6e43690c7d6155da4d70"},"schema_version":"1.0"},"canonical_sha256":"98c08f56695b411d9a3c5436093b5a7f891175ed9262ebc9fb496c299264bc60","source":{"kind":"arxiv","id":"2605.13856","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13856","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13856v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13856","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"TDAI6VTJLNAR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TDAI6VTJLNAR3GR4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TDAI6VTJ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TDAI6VTJLNAR3GR4KQ3ASO22P6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T11:38:12Z","cross_cats_sorted":[],"title_canon_sha256":"f6e94dab6d19a53b80c861c8194834b2a3d8aae7013b517bd6b4c5aa78847f78","abstract_canon_sha256":"387524f043397af914da8e60ce3e37996bdf4bd8044b6e43690c7d6155da4d70"},"schema_version":"1.0"},"canonical_sha256":"98c08f56695b411d9a3c5436093b5a7f891175ed9262ebc9fb496c299264bc60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.547236Z","signature_b64":"vf5vC20OfWvqCMTuNTjq4UATnCCiZ8hXzIuCeJGPeb6UrvKZ/ImQcrQPuO3aO4HFG0CDyZGy1mCAaX1T1sKLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98c08f56695b411d9a3c5436093b5a7f891175ed9262ebc9fb496c299264bc60","last_reissued_at":"2026-05-17T23:39:19.546565Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.546565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13856","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"745lBnxmEUZP40KCHLtHt3uzLqh4cNR7orDn6vIPCXfnRxGfYv+/JzGho8l7K/sgM7ENvpIEytl34Uj8g95tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:15:05.889040Z"},"content_sha256":"6eaa1fdf7168bb11cd533e1ff6225d4c46493a02004564d11ace79fe23c653d8","schema_version":"1.0","event_id":"sha256:6eaa1fdf7168bb11cd533e1ff6225d4c46493a02004564d11ace79fe23c653d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TDAI6VTJLNAR3GR4KQ3ASO22P6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image-aware Layout Generation with User Constraints for Poster Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image.","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Chenchen Xu, Kaixin Han, Weiwei Xu","submitted_at":"2026-04-08T11:38:12Z","abstract_excerpt":"Graphic layout is essential in poster generation. Professionals often need to design different layouts for a product image, to ensure they meet specific user requirements. This paper focuses on utilizing a deep-learning model to automatically generate image-aware layouts with user-defined constraints, including layout attributes and partial layouts. Layout attribute constraints require generated layouts to include and exclude elements of specified classes, such as text, logos, underlays, and embellishments. Our model represents different attributes by sampling multidimensional Gaussian noise w"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Both quantitative and qualitative evaluations demonstrate that our model can generate different image-aware layouts according to various user constraints while achieving state-of-the-art performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That sampling multidimensional Gaussian noise with different means plus the attribute-consistent, attribute-disentangled, and partial-constraint losses will reliably enforce the specified constraints without degrading image awareness or layout quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"239b73f2777c2db2141aaff7fa7559583bc1b60947bb8896a8b9e549f41b9737"},"source":{"id":"2605.13856","kind":"arxiv","version":1},"verdict":{"id":"7cd74fec-6faf-4ddf-b921-7b6ea373050f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:54:32.180781Z","strongest_claim":"Both quantitative and qualitative evaluations demonstrate that our model can generate different image-aware layouts according to various user constraints while achieving state-of-the-art performance.","one_line_summary":"A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That sampling multidimensional Gaussian noise with different means plus the attribute-consistent, attribute-disentangled, and partial-constraint losses will reliably enforce the specified constraints without degrading image awareness or layout quality.","pith_extraction_headline":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image."},"references":{"count":88,"sample":[{"doi":"","year":1985,"title":"Structure and Interpretation of Computer Programs","work_id":"01a14db6-7d1d-4607-868a-f7393285bd98","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2001,"title":"Visual Information Extraction with Lixto","work_id":"70a0bb1e-35f7-444f-b12d-bd6dcd37cc57","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1985,"title":"Brachman and James G","work_id":"0dc6cf5e-34e0-4f51-b711-0498f8e618ec","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1992,"title":"Complexity results for nonmonotonic logics","work_id":"d0459553-e996-400d-b3ca-0618c3da598c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"Hypertree Decompositions and Tractable Queries","work_id":"97611438-476f-473e-b229-ee75292c4fac","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":88,"snapshot_sha256":"452d8734d69b59a662269e7d227d8bf86ed0d035cc0bfce44d176d6e2ffad579","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":"7cd74fec-6faf-4ddf-b921-7b6ea373050f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A7Z7DY2uPYcgw0TYMk2TqIP+5ocfUkfFOgYNg4jbS8QTz93lCuUnkqBQa4eh1WMNh8xUvXcfv/09Nz9X/hpGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T06:15:05.889595Z"},"content_sha256":"c2a87c4b6f7bb24245c75c31b685356db96bcf46debc5bb32f5b5545a6c14464","schema_version":"1.0","event_id":"sha256:c2a87c4b6f7bb24245c75c31b685356db96bcf46debc5bb32f5b5545a6c14464"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/bundle.json","state_url":"https://pith.science/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/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":"2026-05-21T06:15:05Z","links":{"resolver":"https://pith.science/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6","bundle":"https://pith.science/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/bundle.json","state":"https://pith.science/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDAI6VTJLNAR3GR4KQ3ASO22P6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TDAI6VTJLNAR3GR4KQ3ASO22P6","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":"387524f043397af914da8e60ce3e37996bdf4bd8044b6e43690c7d6155da4d70","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T11:38:12Z","title_canon_sha256":"f6e94dab6d19a53b80c861c8194834b2a3d8aae7013b517bd6b4c5aa78847f78"},"schema_version":"1.0","source":{"id":"2605.13856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13856","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13856v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13856","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"TDAI6VTJLNAR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TDAI6VTJLNAR3GR4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TDAI6VTJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c2a87c4b6f7bb24245c75c31b685356db96bcf46debc5bb32f5b5545a6c14464","target":"graph","created_at":"2026-05-17T23:39:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Both quantitative and qualitative evaluations demonstrate that our model can generate different image-aware layouts according to various user constraints while achieving state-of-the-art performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That sampling multidimensional Gaussian noise with different means plus the attribute-consistent, attribute-disentangled, and partial-constraint losses will reliably enforce the specified constraints without degrading image awareness or layout quality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image."}],"snapshot_sha256":"239b73f2777c2db2141aaff7fa7559583bc1b60947bb8896a8b9e549f41b9737"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Graphic layout is essential in poster generation. Professionals often need to design different layouts for a product image, to ensure they meet specific user requirements. This paper focuses on utilizing a deep-learning model to automatically generate image-aware layouts with user-defined constraints, including layout attributes and partial layouts. Layout attribute constraints require generated layouts to include and exclude elements of specified classes, such as text, logos, underlays, and embellishments. Our model represents different attributes by sampling multidimensional Gaussian noise w","authors_text":"Chenchen Xu, Kaixin Han, Weiwei Xu","cross_cats":[],"headline":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T11:38:12Z","title":"Image-aware Layout Generation with User Constraints for Poster Design"},"references":{"count":88,"internal_anchors":0,"resolved_work":88,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Structure and Interpretation of Computer Programs","work_id":"01a14db6-7d1d-4607-868a-f7393285bd98","year":1985},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Visual Information Extraction with Lixto","work_id":"70a0bb1e-35f7-444f-b12d-bd6dcd37cc57","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Brachman and James G","work_id":"0dc6cf5e-34e0-4f51-b711-0498f8e618ec","year":1985},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Complexity results for nonmonotonic logics","work_id":"d0459553-e996-400d-b3ca-0618c3da598c","year":1992},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Hypertree Decompositions and Tractable Queries","work_id":"97611438-476f-473e-b229-ee75292c4fac","year":2002}],"snapshot_sha256":"452d8734d69b59a662269e7d227d8bf86ed0d035cc0bfce44d176d6e2ffad579"},"source":{"id":"2605.13856","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T06:54:32.180781Z","id":"7cd74fec-6faf-4ddf-b921-7b6ea373050f","model_set":{"reader":"grok-4.3"},"one_line_summary":"A deep learning model generates image-aware poster layouts that satisfy user-specified attribute constraints via Gaussian noise sampling and partial layout constraints via a dedicated loss and random mask, reaching state-of-the-art performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A neural model generates poster layouts that respect user constraints on element types and partial designs while remaining aware of the product image.","strongest_claim":"Both quantitative and qualitative evaluations demonstrate that our model can generate different image-aware layouts according to various user constraints while achieving state-of-the-art performance.","weakest_assumption":"That sampling multidimensional Gaussian noise with different means plus the attribute-consistent, attribute-disentangled, and partial-constraint losses will reliably enforce the specified constraints without degrading image awareness or layout quality."}},"verdict_id":"7cd74fec-6faf-4ddf-b921-7b6ea373050f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6eaa1fdf7168bb11cd533e1ff6225d4c46493a02004564d11ace79fe23c653d8","target":"record","created_at":"2026-05-17T23:39:19Z","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":"387524f043397af914da8e60ce3e37996bdf4bd8044b6e43690c7d6155da4d70","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T11:38:12Z","title_canon_sha256":"f6e94dab6d19a53b80c861c8194834b2a3d8aae7013b517bd6b4c5aa78847f78"},"schema_version":"1.0","source":{"id":"2605.13856","kind":"arxiv","version":1}},"canonical_sha256":"98c08f56695b411d9a3c5436093b5a7f891175ed9262ebc9fb496c299264bc60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98c08f56695b411d9a3c5436093b5a7f891175ed9262ebc9fb496c299264bc60","first_computed_at":"2026-05-17T23:39:19.546565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:19.546565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vf5vC20OfWvqCMTuNTjq4UATnCCiZ8hXzIuCeJGPeb6UrvKZ/ImQcrQPuO3aO4HFG0CDyZGy1mCAaX1T1sKLAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:19.547236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eaa1fdf7168bb11cd533e1ff6225d4c46493a02004564d11ace79fe23c653d8","sha256:c2a87c4b6f7bb24245c75c31b685356db96bcf46debc5bb32f5b5545a6c14464"],"state_sha256":"29c872e155a94efad416734e689b72050c2c6108ccc7ef21405e2780695fbc7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iE815opI5J7FS/RnteWFlG0V11rxNPRqPFVs6/hTM50rZr8X1fcxiS5YGebNkInJICy4s4v/YA9qSPQLn50UDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T06:15:05.892161Z","bundle_sha256":"017e7b5fc916ff0b3d9d26cd6be7a1b16089b4c22d8dd3ca972bd326ca10431a"}}