{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2PTPGFTNZZSUS7MQLWDLF722N7","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":"6d629a822b8ed6c23b04901659992a933320309669d27740dfcaac767ecbf559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:32:51Z","title_canon_sha256":"64bacd11c1b3debf54a9a8176e94b7d4eef7262d93bf274ccd111bfb8fe7d3ce"},"schema_version":"1.0","source":{"id":"2502.05153","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05153","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05153v2","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05153","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"2PTPGFTNZZSU","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"2PTPGFTNZZSUS7MQ","created_at":"2026-07-05T11:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"2PTPGFTN","created_at":"2026-07-05T11:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:a789e65af2fae323e546e7b0744e15338cd0504bcd737e235afb9cafcbdd1007","target":"graph","created_at":"2026-07-05T11:18:17Z","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/2502.05153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While diffusion models are powerful in generating high-quality, diverse synthetic data for object-centric tasks, existing methods struggle with scene-aware tasks such as Visual Question Answering (VQA) and Human-Object Interaction (HOI) Reasoning, where it is critical to preserve scene attributes in generated images consistent with a multimodal context, i.e. a reference image with accompanying text guidance query. To address this, we introduce $\\textbf{Hummingbird}$, the first diffusion-based image generator which, given a multimodal context, generates highly diverse images w.r.t. the referenc","authors_text":"A S M Iftekhar, Barun Patra, Dimitris Samaras, Gaurav Mittal, Mei Chen, Minh-Quan Le, Tianjian Meng, Vishwas Suryanarayanan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:32:51Z","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05153","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":"sha256:4361e8f29ab6b73d7ae211d6fb0416dc24fb4504c8f53ca28055894a50ac4ec8","target":"record","created_at":"2026-07-05T11:18:17Z","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":"6d629a822b8ed6c23b04901659992a933320309669d27740dfcaac767ecbf559","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:32:51Z","title_canon_sha256":"64bacd11c1b3debf54a9a8176e94b7d4eef7262d93bf274ccd111bfb8fe7d3ce"},"schema_version":"1.0","source":{"id":"2502.05153","kind":"arxiv","version":2}},"canonical_sha256":"d3e6f3166dce65497d905d86b2ff5a6fe412dd8346d78fa30f3c633f5d8fa88b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e6f3166dce65497d905d86b2ff5a6fe412dd8346d78fa30f3c633f5d8fa88b","first_computed_at":"2026-07-05T11:18:17.682767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:17.682767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lw9B2YdJuH8p8S4NTy0/Mu6KvM3IZxKgSzpKWdfmJcKWb+B0qX64aDG0dS/xFvTZzwnBv0OIHLOOEQHjVUtZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:17.683252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05153","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4361e8f29ab6b73d7ae211d6fb0416dc24fb4504c8f53ca28055894a50ac4ec8","sha256:a789e65af2fae323e546e7b0744e15338cd0504bcd737e235afb9cafcbdd1007"],"state_sha256":"e4107398e2d9562dfd9d2df411e7697065bcca998b3841cd5a5c783eafdd3ceb"}