{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GL247SBXETWHPMBV3LDGHYHUCJ","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":"b1ce1df7a26e2d829bb9b16d209f4de56a8afd033daee6d85c3d0642985f9ab6","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T09:54:06Z","title_canon_sha256":"7ecc66ae26a533b2635349ab8538b3af7149827793a96b2dcfde900c25ccd3df"},"schema_version":"1.0","source":{"id":"2304.02970","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02970","created_at":"2026-07-05T08:55:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02970v7","created_at":"2026-07-05T08:55:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02970","created_at":"2026-07-05T08:55:20Z"},{"alias_kind":"pith_short_12","alias_value":"GL247SBXETWH","created_at":"2026-07-05T08:55:20Z"},{"alias_kind":"pith_short_16","alias_value":"GL247SBXETWHPMBV","created_at":"2026-07-05T08:55:20Z"},{"alias_kind":"pith_short_8","alias_value":"GL247SBX","created_at":"2026-07-05T08:55:20Z"}],"graph_snapshots":[{"event_id":"sha256:a67874840c5de85dba1fe8cf01f98922e68622070179dd9af9b57e7c6f48091f","target":"graph","created_at":"2026-07-05T08:55:20Z","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/2304.02970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment between sound and visual objects. Successful audio-visual learning requires two essential components: 1) a challenging dataset with high-quality pixel-level multi-class annotated images associated with audio files, and 2) a model that can establish strong links between audio information and its corresponding visual object. However, these requirements are on","authors_text":"Chong Wang, Fengbei Liu, Gustavo Carneiro, Helen Frazer, Hu Wang, Yuanhong Chen, Yuyuan Liu","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T09:54:06Z","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02970","kind":"arxiv","version":7},"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:e3db7989bd59febbcd0e595972e4af71d3b41c17409f6081c82759d188acfc6b","target":"record","created_at":"2026-07-05T08:55:20Z","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":"b1ce1df7a26e2d829bb9b16d209f4de56a8afd033daee6d85c3d0642985f9ab6","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T09:54:06Z","title_canon_sha256":"7ecc66ae26a533b2635349ab8538b3af7149827793a96b2dcfde900c25ccd3df"},"schema_version":"1.0","source":{"id":"2304.02970","kind":"arxiv","version":7}},"canonical_sha256":"32f5cfc83724ec77b035dac663e0f41254a53150b8d17e89b0778c677174d6d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32f5cfc83724ec77b035dac663e0f41254a53150b8d17e89b0778c677174d6d3","first_computed_at":"2026-07-05T08:55:20.055599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:20.055599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TcSswM28FKpy//HqjwKZ2v2M88Rw3Y5xWVelLCbEUBpaJbsxp76NU0PN1cUfC5hibTdN+kp+z+17LHYk1uFSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:20.056081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02970","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3db7989bd59febbcd0e595972e4af71d3b41c17409f6081c82759d188acfc6b","sha256:a67874840c5de85dba1fe8cf01f98922e68622070179dd9af9b57e7c6f48091f"],"state_sha256":"530c24b853ead13ed5f76ce6b3154465b77ff0e5da1b794b7d556487e9ed4631"}