{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2PTPGFTNZZSUS7MQLWDLF722N7","short_pith_number":"pith:2PTPGFTN","schema_version":"1.0","canonical_sha256":"d3e6f3166dce65497d905d86b2ff5a6fe412dd8346d78fa30f3c633f5d8fa88b","source":{"kind":"arxiv","id":"2502.05153","version":2},"attestation_state":"computed","paper":{"title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A S M Iftekhar, Barun Patra, Dimitris Samaras, Gaurav Mittal, Mei Chen, Minh-Quan Le, Tianjian Meng, Vishwas Suryanarayanan","submitted_at":"2025-02-07T18:32:51Z","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"},"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":"2502.05153","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T18:32:51Z","cross_cats_sorted":[],"title_canon_sha256":"64bacd11c1b3debf54a9a8176e94b7d4eef7262d93bf274ccd111bfb8fe7d3ce","abstract_canon_sha256":"6d629a822b8ed6c23b04901659992a933320309669d27740dfcaac767ecbf559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:17.683252Z","signature_b64":"lw9B2YdJuH8p8S4NTy0/Mu6KvM3IZxKgSzpKWdfmJcKWb+B0qX64aDG0dS/xFvTZzwnBv0OIHLOOEQHjVUtZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e6f3166dce65497d905d86b2ff5a6fe412dd8346d78fa30f3c633f5d8fa88b","last_reissued_at":"2026-07-05T11:18:17.682767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:17.682767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"A S M Iftekhar, Barun Patra, Dimitris Samaras, Gaurav Mittal, Mei Chen, Minh-Quan Le, Tianjian Meng, Vishwas Suryanarayanan","submitted_at":"2025-02-07T18:32:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05153","kind":"arxiv","version":2},"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/2502.05153/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":"2502.05153","created_at":"2026-07-05T11:18:17.682825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05153v2","created_at":"2026-07-05T11:18:17.682825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05153","created_at":"2026-07-05T11:18:17.682825+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PTPGFTNZZSU","created_at":"2026-07-05T11:18:17.682825+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PTPGFTNZZSUS7MQ","created_at":"2026-07-05T11:18:17.682825+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PTPGFTN","created_at":"2026-07-05T11:18:17.682825+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/2PTPGFTNZZSUS7MQLWDLF722N7","json":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7.json","graph_json":"https://pith.science/api/pith-number/2PTPGFTNZZSUS7MQLWDLF722N7/graph.json","events_json":"https://pith.science/api/pith-number/2PTPGFTNZZSUS7MQLWDLF722N7/events.json","paper":"https://pith.science/paper/2PTPGFTN"},"agent_actions":{"view_html":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7","download_json":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7.json","view_paper":"https://pith.science/paper/2PTPGFTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05153&json=true","fetch_graph":"https://pith.science/api/pith-number/2PTPGFTNZZSUS7MQLWDLF722N7/graph.json","fetch_events":"https://pith.science/api/pith-number/2PTPGFTNZZSUS7MQLWDLF722N7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7/action/storage_attestation","attest_author":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7/action/author_attestation","sign_citation":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7/action/citation_signature","submit_replication":"https://pith.science/pith/2PTPGFTNZZSUS7MQLWDLF722N7/action/replication_record"}},"created_at":"2026-07-05T11:18:17.682825+00:00","updated_at":"2026-07-05T11:18:17.682825+00:00"}