{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:53UQ4TZB5LFYYT66DLVU2CRNPD","short_pith_number":"pith:53UQ4TZB","schema_version":"1.0","canonical_sha256":"eee90e4f21eacb8c4fde1aeb4d0a2d78eee8c1de8c360178bec368c9178002ef","source":{"kind":"arxiv","id":"2502.01309","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Image GNN: Graph-Conditioned Diffusion for Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Margadji, Rupert Menneer, Sebastian W. Pattinson","submitted_at":"2025-02-03T12:36:14Z","abstract_excerpt":"We introduce a novel method for conditioning diffusion-based image synthesis models with heterogeneous graph data. Existing approaches typically incorporate conditioning variables directly into model architectures, either through cross-attention layers that attend to text latents or image concatenation that spatially restrict generation. However, these methods struggle to handle complex scenarios involving diverse, relational conditioning variables, which are more naturally represented as unstructured graphs. This paper presents Heterogeneous Image Graphs (HIG), a novel representation that mod"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.01309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-03T12:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"a0ea9cf03fcde6faa0a70fb9db7343a0af91c7b3a44d7a7edf7ac274a7def2cc","abstract_canon_sha256":"5157f70e0e9af0cf3f824d2782ab621f403aa4f36be92352194a7911b2989400"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:45.630869Z","signature_b64":"a9sLCzD2Hf76qD82PeGHwT5r0+tpOASTBCotOSM2U/mt4qoEdYJZDL7dsN7xW/N2eT8aUWijarEm6iwe2y+yBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eee90e4f21eacb8c4fde1aeb4d0a2d78eee8c1de8c360178bec368c9178002ef","last_reissued_at":"2026-07-05T10:08:45.630410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:45.630410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Image GNN: Graph-Conditioned Diffusion for Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Margadji, Rupert Menneer, Sebastian W. Pattinson","submitted_at":"2025-02-03T12:36:14Z","abstract_excerpt":"We introduce a novel method for conditioning diffusion-based image synthesis models with heterogeneous graph data. Existing approaches typically incorporate conditioning variables directly into model architectures, either through cross-attention layers that attend to text latents or image concatenation that spatially restrict generation. However, these methods struggle to handle complex scenarios involving diverse, relational conditioning variables, which are more naturally represented as unstructured graphs. This paper presents Heterogeneous Image Graphs (HIG), a novel representation that mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01309","kind":"arxiv","version":1},"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/2502.01309/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.01309","created_at":"2026-07-05T10:08:45.630467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01309v1","created_at":"2026-07-05T10:08:45.630467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01309","created_at":"2026-07-05T10:08:45.630467+00:00"},{"alias_kind":"pith_short_12","alias_value":"53UQ4TZB5LFY","created_at":"2026-07-05T10:08:45.630467+00:00"},{"alias_kind":"pith_short_16","alias_value":"53UQ4TZB5LFYYT66","created_at":"2026-07-05T10:08:45.630467+00:00"},{"alias_kind":"pith_short_8","alias_value":"53UQ4TZB","created_at":"2026-07-05T10:08:45.630467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD","json":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD.json","graph_json":"https://pith.science/api/pith-number/53UQ4TZB5LFYYT66DLVU2CRNPD/graph.json","events_json":"https://pith.science/api/pith-number/53UQ4TZB5LFYYT66DLVU2CRNPD/events.json","paper":"https://pith.science/paper/53UQ4TZB"},"agent_actions":{"view_html":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD","download_json":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD.json","view_paper":"https://pith.science/paper/53UQ4TZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01309&json=true","fetch_graph":"https://pith.science/api/pith-number/53UQ4TZB5LFYYT66DLVU2CRNPD/graph.json","fetch_events":"https://pith.science/api/pith-number/53UQ4TZB5LFYYT66DLVU2CRNPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD/action/storage_attestation","attest_author":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD/action/author_attestation","sign_citation":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD/action/citation_signature","submit_replication":"https://pith.science/pith/53UQ4TZB5LFYYT66DLVU2CRNPD/action/replication_record"}},"created_at":"2026-07-05T10:08:45.630467+00:00","updated_at":"2026-07-05T10:08:45.630467+00:00"}