{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LXOY7CXCQWJETIAGDUZTL2IFCY","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":"93ce894e05c47bf3e087cdeaaaec2ad10011ce27d2fd0572d81421055261c31e","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:57:26Z","title_canon_sha256":"000529782725b5b379c7e45867c43a05949c4d0615fac7258107ebf057ba0d82"},"schema_version":"1.0","source":{"id":"2506.04214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04214","created_at":"2026-07-05T11:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04214v1","created_at":"2026-07-05T11:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04214","created_at":"2026-07-05T11:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"LXOY7CXCQWJE","created_at":"2026-07-05T11:15:59Z"},{"alias_kind":"pith_short_16","alias_value":"LXOY7CXCQWJETIAG","created_at":"2026-07-05T11:15:59Z"},{"alias_kind":"pith_short_8","alias_value":"LXOY7CXC","created_at":"2026-07-05T11:15:59Z"}],"graph_snapshots":[{"event_id":"sha256:27c928f9e0cee47d0bfedcb4ba3b1730bb0475151f606f7768478fa9ddaf95b5","target":"graph","created_at":"2026-07-05T11:15:59Z","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/2506.04214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an {\\em interactive object-aware audio generation} model that grounds sound generation in user-selected visual objects within images. Our method integrates object-centric learning into a conditional latent diffusion model, which learns to associate image regions with their corresponding sounds through multi-modal attention. At test time, our model employs image segmentation to allow users to interactively generate sounds at the {","authors_text":"Baihe Huang, Dongya Jia, Gopala Anumanchipalli, Jiawei Chen, Tingle Li, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang, Zhuo Chen","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:57:26Z","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04214","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":"sha256:466c709fcc03e58a6057861ee1066180758b51fb31c27d5adb5e324515ff3d21","target":"record","created_at":"2026-07-05T11:15:59Z","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":"93ce894e05c47bf3e087cdeaaaec2ad10011ce27d2fd0572d81421055261c31e","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T17:57:26Z","title_canon_sha256":"000529782725b5b379c7e45867c43a05949c4d0615fac7258107ebf057ba0d82"},"schema_version":"1.0","source":{"id":"2506.04214","kind":"arxiv","version":1}},"canonical_sha256":"5ddd8f8ae2859249a0061d3335e9051628242cebd53050febe2633f0abe863dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ddd8f8ae2859249a0061d3335e9051628242cebd53050febe2633f0abe863dc","first_computed_at":"2026-07-05T11:15:59.015238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:59.015238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K6gNfM0dqoRwsYYnAmeV4L35w8onDyUEZFAUDrcdug63V0NyssqziorbeFUvHoHmOS7v9/trG2+v3jSdwrYrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:59.015795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:466c709fcc03e58a6057861ee1066180758b51fb31c27d5adb5e324515ff3d21","sha256:27c928f9e0cee47d0bfedcb4ba3b1730bb0475151f606f7768478fa9ddaf95b5"],"state_sha256":"d9cd11d1878eedc0ffa28ca6795ca7bad2737367d15c38f97f7f93991a72219a"}