{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XVLIHGZXMRABFRMMN4QGVSVD4R","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":"910414d91ae7ed8a24f3280116477c93a89429796a7df5937230a3b791ae3252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T08:14:40Z","title_canon_sha256":"20b762a7e38934986eef94789e60b34b82c96e46169d36d0859de63b75b61180"},"schema_version":"1.0","source":{"id":"2410.20823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20823","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20823v1","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20823","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"XVLIHGZXMRAB","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"XVLIHGZXMRABFRMM","created_at":"2026-07-05T09:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"XVLIHGZX","created_at":"2026-07-05T09:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:1f6b0c3593ff5f05fafe22e2357a2af897bf087736308414a4785cc526c03b54","target":"graph","created_at":"2026-07-05T09:27:11Z","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/2410.20823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \\textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve","authors_text":"Gan Sun, Jian Yang, Jun Li, Shuo Chen, Xiang Li, Zedong Zhang, Zeren Xiong, Zikun Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T08:14:40Z","title":"Novel Object Synthesis via Adaptive Text-Image Harmony"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20823","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:b51596d55e5cb792e5249e361904cf851d70342c2fa0ae31e9e7e43b5a0ea625","target":"record","created_at":"2026-07-05T09:27:11Z","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":"910414d91ae7ed8a24f3280116477c93a89429796a7df5937230a3b791ae3252","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T08:14:40Z","title_canon_sha256":"20b762a7e38934986eef94789e60b34b82c96e46169d36d0859de63b75b61180"},"schema_version":"1.0","source":{"id":"2410.20823","kind":"arxiv","version":1}},"canonical_sha256":"bd56839b37644012c58c6f206acaa3e4558896524634b4f6d55aa45b971f28ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd56839b37644012c58c6f206acaa3e4558896524634b4f6d55aa45b971f28ae","first_computed_at":"2026-07-05T09:27:11.717889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:11.717889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4uaaWn7to6UIzw/kKiWIKWsukDq4ZRKk6MEQksvFQAASFxBuQNLDnxK8te3fvozE6HjabGb4agAI40G2218GCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:11.718279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b51596d55e5cb792e5249e361904cf851d70342c2fa0ae31e9e7e43b5a0ea625","sha256:1f6b0c3593ff5f05fafe22e2357a2af897bf087736308414a4785cc526c03b54"],"state_sha256":"8864b0ac934de2c3843428763f1046ba74a1ffaa8749b4e2045219ea1b857091"}