{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BKLET5AOBY572CSJNSLO3V7FKE","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":"6902285eae3bd1200f906eff7fe170a840539b7f90ed5222ce63ed640d4699d5","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T11:29:50Z","title_canon_sha256":"e9c17e1b12b623e9427060cf3f53ee7e499b6416bd4d5b6057296db1a1f8d91a"},"schema_version":"1.0","source":{"id":"2307.16579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16579","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16579v2","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16579","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"BKLET5AOBY57","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"BKLET5AOBY572CSJ","created_at":"2026-07-05T11:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"BKLET5AO","created_at":"2026-07-05T11:29:46Z"}],"graph_snapshots":[{"event_id":"sha256:bc0f8b3034ff7c28fac7cff6d6d25ea64e409efdbcc317c3e69f2260d0cc98ba","target":"graph","created_at":"2026-07-05T11:29:46Z","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/2307.16579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a contrastive conditional latent diffusion model for audio-visual segmentation (AVS) to thoroughly investigate the impact of audio, where the correlation between audio and the final segmentation map is modeled to guarantee the strong correlation between them. To achieve semantic-correlated representation learning, our framework incorporates a latent diffusion model. The diffusion model learns the conditional generation process of the ground-truth segmentation map, resulting in ground-truth aware inference during the denoising process at the test stage. As our model is conditional, i","authors_text":"Dong Li, Jing Zhang, Mochu Xiang, Yiran Zhong, Yuchao Dai, Yunqiu Lv, Yuxin Mao","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T11:29:50Z","title":"Contrastive Conditional Latent Diffusion for Audio-visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16579","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":"sha256:9314f6ea91936c84e5261529162bbe068fc549ac01d91f1658e684ba9f644039","target":"record","created_at":"2026-07-05T11:29:46Z","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":"6902285eae3bd1200f906eff7fe170a840539b7f90ed5222ce63ed640d4699d5","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T11:29:50Z","title_canon_sha256":"e9c17e1b12b623e9427060cf3f53ee7e499b6416bd4d5b6057296db1a1f8d91a"},"schema_version":"1.0","source":{"id":"2307.16579","kind":"arxiv","version":2}},"canonical_sha256":"0a9649f40e0e3bfd0a496c96edd7e55130cdb41d5ae100152dbb180672ad391a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a9649f40e0e3bfd0a496c96edd7e55130cdb41d5ae100152dbb180672ad391a","first_computed_at":"2026-07-05T11:29:46.147305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:46.147305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DUrRIUSh+fw9RLukU3FpYXJPf5rzFOuHqs1R/jgIV4rMTeQq/JOlZrcmb4p/9iMGkClZJLToU5H1qbGApfpSBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:46.147746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9314f6ea91936c84e5261529162bbe068fc549ac01d91f1658e684ba9f644039","sha256:bc0f8b3034ff7c28fac7cff6d6d25ea64e409efdbcc317c3e69f2260d0cc98ba"],"state_sha256":"20fbb652b5463ce71771478d2d92a709f17bfbc20b6da6f861d1cf5b2efe425f"}