{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B4XTHMRVNCARYQSMX6ZRL5OYSQ","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":"95a464e7c0c304bfa9c2545119e6d28a9f9491c586a3127f21791720bca63e0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:53:32Z","title_canon_sha256":"19ff4421b11fefa64999006542888d77cab37057e779933aacb82bc71dc5b9e0"},"schema_version":"1.0","source":{"id":"2301.13190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13190","created_at":"2026-07-05T05:37:01Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13190v1","created_at":"2026-07-05T05:37:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13190","created_at":"2026-07-05T05:37:01Z"},{"alias_kind":"pith_short_12","alias_value":"B4XTHMRVNCAR","created_at":"2026-07-05T05:37:01Z"},{"alias_kind":"pith_short_16","alias_value":"B4XTHMRVNCARYQSM","created_at":"2026-07-05T05:37:01Z"},{"alias_kind":"pith_short_8","alias_value":"B4XTHMRV","created_at":"2026-07-05T05:37:01Z"}],"graph_snapshots":[{"event_id":"sha256:14ad645a1e413314e765ca4791e8de77ebf5db5d0441534b5e33326dc5e1cff6","target":"graph","created_at":"2026-07-05T05:37:01Z","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/2301.13190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new problem called audio-visual segmentation (AVS), in which the goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame. To facilitate this research, we construct the first audio-visual segmentation benchmark, i.e., AVSBench, providing pixel-wise annotations for sounding objects in audible videos. It contains three subsets: AVSBench-object (Single-source subset, Multi-sources subset) and AVSBench-semantic (Semantic-labels subset). Accordingly, three settings are studied: 1) semi-supervised audio-visual segmentation with a single soun","authors_text":"Dan Guo, Jianyuan Wang, Jiayi Zhang, Jing Zhang, Jinxing Zhou, Lingpeng Kong, Meng Wang, Stan Birchfield, Weixuan Sun, Xuyang Shen, Yiran Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13190","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:a8c5c498207ff549ed816a6f66d001c0ac3055c028447006f9bda65d70f611e9","target":"record","created_at":"2026-07-05T05:37:01Z","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":"95a464e7c0c304bfa9c2545119e6d28a9f9491c586a3127f21791720bca63e0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T18:53:32Z","title_canon_sha256":"19ff4421b11fefa64999006542888d77cab37057e779933aacb82bc71dc5b9e0"},"schema_version":"1.0","source":{"id":"2301.13190","kind":"arxiv","version":1}},"canonical_sha256":"0f2f33b23568811c424cbfb315f5d894179b0d96689ae1dab2b827137159eb95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f2f33b23568811c424cbfb315f5d894179b0d96689ae1dab2b827137159eb95","first_computed_at":"2026-07-05T05:37:01.737699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:37:01.737699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEcDpFLr7+FwGsuls3EoUXjNTFH3vCGvD7wg1wh2n82DudvzKHzUXSvK3BtjkjHBx1lmjmAAmTbPm9BjbwNGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:37:01.738198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8c5c498207ff549ed816a6f66d001c0ac3055c028447006f9bda65d70f611e9","sha256:14ad645a1e413314e765ca4791e8de77ebf5db5d0441534b5e33326dc5e1cff6"],"state_sha256":"5e0c3492f0344b21f1e8dedc73a90645693c24d36bd60007912c44b504b18c24"}