{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DBSS6P224BXQEGDJXAX6MXESJA","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":"1cb48b9a145d889da69725b87ef8e6a995b366a6a3b5a750fe7bf732acb3d0fb","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T12:56:30Z","title_canon_sha256":"b992985715b5c50636d6fc16931e25eda854aaecc240e1bccbe9dff06ed3bd16"},"schema_version":"1.0","source":{"id":"2307.16620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16620","created_at":"2026-07-05T06:36:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16620v2","created_at":"2026-07-05T06:36:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16620","created_at":"2026-07-05T06:36:13Z"},{"alias_kind":"pith_short_12","alias_value":"DBSS6P224BXQ","created_at":"2026-07-05T06:36:13Z"},{"alias_kind":"pith_short_16","alias_value":"DBSS6P224BXQEGDJ","created_at":"2026-07-05T06:36:13Z"},{"alias_kind":"pith_short_8","alias_value":"DBSS6P22","created_at":"2026-07-05T06:36:13Z"}],"graph_snapshots":[{"event_id":"sha256:86190366af8e41c8578aebb6f6fe6d2c9a7e138a54e45cb70c13a274102f486b","target":"graph","created_at":"2026-07-05T06:36:13Z","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/2307.16620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The audio-visual segmentation (AVS) task aims to segment sounding objects from a given video. Existing works mainly focus on fusing audio and visual features of a given video to achieve sounding object masks. However, we observed that prior arts are prone to segment a certain salient object in a video regardless of the audio information. This is because sounding objects are often the most salient ones in the AVS dataset. Thus, current AVS methods might fail to localize genuine sounding objects due to the dataset bias. In this work, we present an audio-visual instance-aware segmentation approac","authors_text":"Chen Liu, Dadong Wang, Hu Zhang, Lincheng Li, Peike Li, Xingqun Qi, Xin Yu","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T12:56:30Z","title":"Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16620","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:cfeb78590d2fd7a1e300daa6d8d2de064fd0f5a9c20ce13ae1aca029672b62d2","target":"record","created_at":"2026-07-05T06:36:13Z","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":"1cb48b9a145d889da69725b87ef8e6a995b366a6a3b5a750fe7bf732acb3d0fb","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T12:56:30Z","title_canon_sha256":"b992985715b5c50636d6fc16931e25eda854aaecc240e1bccbe9dff06ed3bd16"},"schema_version":"1.0","source":{"id":"2307.16620","kind":"arxiv","version":2}},"canonical_sha256":"18652f3f5ae06f021869b82fe65c9248027901699e4a0f6fb9042cdafeb12bef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18652f3f5ae06f021869b82fe65c9248027901699e4a0f6fb9042cdafeb12bef","first_computed_at":"2026-07-05T06:36:13.032310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:13.032310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfT3YkrTFeD44Jyp9KtpZK8/2pTsPVSuYNWAB2wxpV3K7yR/VmVLaEkYLwbzx0lVDoT8NP6VcMtq10hc/NTXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:13.032853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfeb78590d2fd7a1e300daa6d8d2de064fd0f5a9c20ce13ae1aca029672b62d2","sha256:86190366af8e41c8578aebb6f6fe6d2c9a7e138a54e45cb70c13a274102f486b"],"state_sha256":"610fa53c68f6072fa0d4093bf101d5b414232e2bda8bde20bafb8cb51a97995f"}