{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T562MNJBFITMXPVQ7LB26VWYID","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":"8b2ee99096a0bf387c9c86988b4377f106fbdb295673ecb1481c084a20ee3bd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T02:14:00Z","title_canon_sha256":"20b12cca78b25b6b8d61131d04ebb3242956ef2262fce4e17a19df1742ffd23a"},"schema_version":"1.0","source":{"id":"2508.00265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00265","created_at":"2026-07-05T11:48:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00265v2","created_at":"2026-07-05T11:48:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00265","created_at":"2026-07-05T11:48:52Z"},{"alias_kind":"pith_short_12","alias_value":"T562MNJBFITM","created_at":"2026-07-05T11:48:52Z"},{"alias_kind":"pith_short_16","alias_value":"T562MNJBFITMXPVQ","created_at":"2026-07-05T11:48:52Z"},{"alias_kind":"pith_short_8","alias_value":"T562MNJB","created_at":"2026-07-05T11:48:52Z"}],"graph_snapshots":[{"event_id":"sha256:166f9cb0d4749fd4792610d70be6ae440ca4291265f7a9888fdd6d2b91240ae2","target":"graph","created_at":"2026-07-05T11:48:52Z","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/2508.00265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal referring segmentation aims to segment target objects in visual scenes, such as images, videos, and 3D scenes, based on referring expressions in text or audio format. This task plays a crucial role in practical applications requiring accurate object perception based on user instructions. Over the past decade, it has gained significant attention in the multimodal community, driven by advances in convolutional neural networks, transformers, and large language models, all of which have substantially improved multimodal perception capabilities. This paper provides a comprehensive survey","authors_text":"Chang Liu, Henghui Ding, Shuting He, Song Tang, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T02:14:00Z","title":"Multimodal Referring Segmentation: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00265","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":"sha256:3b05c1d25f4305538d15f336f9c6d90e17440ea6cf3e115f03412435f8213aef","target":"record","created_at":"2026-07-05T11:48:52Z","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":"8b2ee99096a0bf387c9c86988b4377f106fbdb295673ecb1481c084a20ee3bd2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T02:14:00Z","title_canon_sha256":"20b12cca78b25b6b8d61131d04ebb3242956ef2262fce4e17a19df1742ffd23a"},"schema_version":"1.0","source":{"id":"2508.00265","kind":"arxiv","version":2}},"canonical_sha256":"9f7da635212a26cbbeb0fac3af56d840c02d7a2649e568d7f3dda1ade9042c49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f7da635212a26cbbeb0fac3af56d840c02d7a2649e568d7f3dda1ade9042c49","first_computed_at":"2026-07-05T11:48:52.174515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:52.174515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JFjMYpQiBfDpXXACn/sfZZcO1Dr3/A9g+6RaU5HdPwx/p3vHeOkWDB+Q05aiQaZ7HDw3Jr5wg6y6Rn6w148CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:52.175000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b05c1d25f4305538d15f336f9c6d90e17440ea6cf3e115f03412435f8213aef","sha256:166f9cb0d4749fd4792610d70be6ae440ca4291265f7a9888fdd6d2b91240ae2"],"state_sha256":"899e0ccbc0811624963f6bf434ac529c955cc374b0b243f5be66bbcfaf70f4b3"}