{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ENXUEW7XF4LMJ3FFEMZVSVGX5Y","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":"9f0a2bb191eb19159272c0bace9eb9ae2685d47f3d96596bc27f979cb325af4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T02:51:11Z","title_canon_sha256":"d874974e15fc42cdab71d62c63bc37de95d195a40a32d1cf303b36cc43ff3beb"},"schema_version":"1.0","source":{"id":"2504.14467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14467","created_at":"2026-07-05T10:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14467v2","created_at":"2026-07-05T10:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14467","created_at":"2026-07-05T10:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"ENXUEW7XF4LM","created_at":"2026-07-05T10:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"ENXUEW7XF4LMJ3FF","created_at":"2026-07-05T10:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"ENXUEW7X","created_at":"2026-07-05T10:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:907c20f558a39298590bf6c681d9acae327b05f820dbdd7e6ec0b5e51f7212b8","target":"graph","created_at":"2026-07-05T10:57:21Z","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/2504.14467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot referring image segmentation aims to locate and segment the target region based on a referring expression, with the primary challenge of aligning and matching semantics across visual and textual modalities without training. Previous works address this challenge by utilizing Vision-Language Models and mask proposal networks for region-text matching. However, this paradigm may lead to incorrect target localization due to the inherent ambiguity and diversity of free-form referring expressions. To alleviate this issue, we present LGD (Leveraging Generative Descriptions), a framework that","authors_text":"Jiachen Li, Jinyu Xu, Qing Xie, Renshu Gu, Xiaohan Yu, Yongjian Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T02:51:11Z","title":"LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14467","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:c2935fdae7b7e62ff6700da7061dc41221ffa1c11ee21c1abbbf6ae412bcc15f","target":"record","created_at":"2026-07-05T10:57:21Z","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":"9f0a2bb191eb19159272c0bace9eb9ae2685d47f3d96596bc27f979cb325af4d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T02:51:11Z","title_canon_sha256":"d874974e15fc42cdab71d62c63bc37de95d195a40a32d1cf303b36cc43ff3beb"},"schema_version":"1.0","source":{"id":"2504.14467","kind":"arxiv","version":2}},"canonical_sha256":"236f425bf72f16c4eca523335954d7ee1af1595904437d37303e3ebf2050a1b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"236f425bf72f16c4eca523335954d7ee1af1595904437d37303e3ebf2050a1b6","first_computed_at":"2026-07-05T10:57:21.679526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:21.679526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c6G7NamLZJwjOKiVAcUSBc1+dEv0MHHC2zyCZdp6CVewQzIhQciSfbDXCJIcunRNLaRON/2TteVHpqJKSHPuDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:21.680013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2935fdae7b7e62ff6700da7061dc41221ffa1c11ee21c1abbbf6ae412bcc15f","sha256:907c20f558a39298590bf6c681d9acae327b05f820dbdd7e6ec0b5e51f7212b8"],"state_sha256":"ec5f9af8ce5fd08b01972faecf372446b06d7d2b865cb9e7e2eecb14593e52d8"}