{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:62QLRS4DIL2ZPYGNFOD74GD6YZ","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":"dfd512252ba7cd145b388a951fae872152f8663346bf53b77efd7867171e3e27","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T07:57:27Z","title_canon_sha256":"fc891d31f0be473ab47e254ba4a6201f93a5ea70d2f9f83a501b0e611c704eda"},"schema_version":"1.0","source":{"id":"2508.05123","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05123","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05123v2","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05123","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_12","alias_value":"62QLRS4DIL2Z","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_16","alias_value":"62QLRS4DIL2ZPYGN","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_8","alias_value":"62QLRS4D","created_at":"2026-07-05T11:55:21Z"}],"graph_snapshots":[{"event_id":"sha256:1157bce99ff900437bc704a37bcd5e0dbaecfb897d599ad7e25110ac9258d1b6","target":"graph","created_at":"2026-07-05T11:55:21Z","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/2508.05123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in multiple ways, reflecting diverse attributes such as color, position, and more. However, most existing methods rely on a single textual input, which captures only a fraction of the rich information available in the visual domain. This mismatch between rich visual details and sparse textual cues can lead to the misidentification of similar objects. To address this, ","authors_text":"Jeany Son, Joonseok Lee, Junbeom Hong, Seonghoon Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T07:57:27Z","title":"Latent Expression Generation for Referring Image Segmentation and Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05123","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:ceedbbdb0713d7d588ca4479b8b3273dd4abd7c52ea45b875671c0762644767e","target":"record","created_at":"2026-07-05T11:55:21Z","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":"dfd512252ba7cd145b388a951fae872152f8663346bf53b77efd7867171e3e27","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T07:57:27Z","title_canon_sha256":"fc891d31f0be473ab47e254ba4a6201f93a5ea70d2f9f83a501b0e611c704eda"},"schema_version":"1.0","source":{"id":"2508.05123","kind":"arxiv","version":2}},"canonical_sha256":"f6a0b8cb8342f597e0cd2b87fe187ec65235d9435bfb060661ec7e169a8f64fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6a0b8cb8342f597e0cd2b87fe187ec65235d9435bfb060661ec7e169a8f64fa","first_computed_at":"2026-07-05T11:55:21.087921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:21.087921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V0av+6agJWGlIWde3W/pqm3I9f0WH3uzxg5Ig4wByt1zr4OM49cZ2oKj8HpZz7sfFZYyq9XHjEYq5YEWPpcvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:21.088361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05123","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceedbbdb0713d7d588ca4479b8b3273dd4abd7c52ea45b875671c0762644767e","sha256:1157bce99ff900437bc704a37bcd5e0dbaecfb897d599ad7e25110ac9258d1b6"],"state_sha256":"951c042af3e8ef9c137af73e816383bb2c83560615719d827f0040241f095e04"}