{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YHXBUCGD3KITFIDX4IX766HP42","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":"714e58897c9d2256fb2e246b7c50e7808869292cc27728c4a949f04b12196cbe","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-10-10T02:04:38Z","title_canon_sha256":"e54c3b5fabfaa9cd2ec7b0b96e49a8ad1ce0ebf8b8873a3cf80ee6ceb519e35f"},"schema_version":"1.0","source":{"id":"2310.06259","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06259","created_at":"2026-07-05T09:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06259v5","created_at":"2026-07-05T09:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06259","created_at":"2026-07-05T09:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"YHXBUCGD3KIT","created_at":"2026-07-05T09:53:39Z"},{"alias_kind":"pith_short_16","alias_value":"YHXBUCGD3KITFIDX","created_at":"2026-07-05T09:53:39Z"},{"alias_kind":"pith_short_8","alias_value":"YHXBUCGD","created_at":"2026-07-05T09:53:39Z"}],"graph_snapshots":[{"event_id":"sha256:8d8dcd3028b3b8028003f2c4de0bdd37220e231a728556c43d62038e657dbe73","target":"graph","created_at":"2026-07-05T09:53:39Z","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/2310.06259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to extract the sounding object from a video frame, which is represented by a pixel-wise segmentation mask for application scenarios such as multi-modal video editing, augmented reality, and intelligent robot systems. The pioneering work conducts this task through dense feature-level audio-visual interaction, which ignores the dimension gap between different modalities. More specifically, the audio clip could only provide a Global semantic label in each sequence, but the video frame covers multiple semantic objects across different Local regions, which leads","authors_text":"Fanman Meng, Hongliang Li, Linfeng Xu, Qingbo Wu, Zhaofeng Shi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-10-10T02:04:38Z","title":"Cross-modal Cognitive Consensus guided Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06259","kind":"arxiv","version":5},"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:fc372742c89672946fc45922a6be3ad4665a3043d11553951f5793a5cc9072ee","target":"record","created_at":"2026-07-05T09:53:39Z","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":"714e58897c9d2256fb2e246b7c50e7808869292cc27728c4a949f04b12196cbe","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-10-10T02:04:38Z","title_canon_sha256":"e54c3b5fabfaa9cd2ec7b0b96e49a8ad1ce0ebf8b8873a3cf80ee6ceb519e35f"},"schema_version":"1.0","source":{"id":"2310.06259","kind":"arxiv","version":5}},"canonical_sha256":"c1ee1a08c3da9132a077e22fff78efe68f1def313557fe9070cda68e8d7cd39e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1ee1a08c3da9132a077e22fff78efe68f1def313557fe9070cda68e8d7cd39e","first_computed_at":"2026-07-05T09:53:39.277610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:39.277610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QIg0y81TlPZwoA28FOsisfq+9tiy+py70+JSs5GszyVfxdiCGnzYRbAtvJWxVhqoLXCZ81BaiEXt7PoGgZy4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:39.277992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06259","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc372742c89672946fc45922a6be3ad4665a3043d11553951f5793a5cc9072ee","sha256:8d8dcd3028b3b8028003f2c4de0bdd37220e231a728556c43d62038e657dbe73"],"state_sha256":"209bca327fef55a85bc030c3e3dbc235e909a25e9ca92611bd1248632b0f3c29"}