{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUDWJVJ7HFYEEI6S2P5SU352JC","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":"4064176fb00b3543f10f7c0df260f80cdcdab43570fb900e2dabf9b07dc47f62","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T13:52:29Z","title_canon_sha256":"475c451c9a30ec9ef7addac105d4213e2f11afb8e9d9bce976a6678a1a1e0cb3"},"schema_version":"1.0","source":{"id":"2406.07268","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07268","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07268v2","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07268","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"BUDWJVJ7HFYE","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"BUDWJVJ7HFYEEI6S","created_at":"2026-07-05T12:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"BUDWJVJ7","created_at":"2026-07-05T12:01:53Z"}],"graph_snapshots":[{"event_id":"sha256:6c7bc05dee0e90593a7e3cc12844e5be6c53c6ea92f4c9be407f1342db3e0696","target":"graph","created_at":"2026-07-05T12:01:53Z","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/2406.07268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounded Multimodal Named Entity Recognition (GMNER) task aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging attributes: 1) The tenuous correlation between images and text on social media contributes to a notable proportion of named entities being ungroundable. 2) There exists a distinction between coarse-grained noun phrases used in similar tasks (e.g., phrase localization) and fine-grained named entities. In this paper, we propose RiVEG, a unified framework that reformulates GMNER into a joint MNER-VE-VG task by leveragin","authors_text":"Di Sun, Gang Pan, Han Li, Jianfei Yu, Jinyuan Li, Rui Xia, Ziyan Li","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T13:52:29Z","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07268","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:edf4c575871c6b2758c0a03110f46f1baf32557aa2da2cfe583d9ce16d7f9be3","target":"record","created_at":"2026-07-05T12:01:53Z","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":"4064176fb00b3543f10f7c0df260f80cdcdab43570fb900e2dabf9b07dc47f62","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T13:52:29Z","title_canon_sha256":"475c451c9a30ec9ef7addac105d4213e2f11afb8e9d9bce976a6678a1a1e0cb3"},"schema_version":"1.0","source":{"id":"2406.07268","kind":"arxiv","version":2}},"canonical_sha256":"0d0764d53f39704223d2d3fb2a6fba48a392680b7ed07d0303bf38dfc75304a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0764d53f39704223d2d3fb2a6fba48a392680b7ed07d0303bf38dfc75304a3","first_computed_at":"2026-07-05T12:01:53.931168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:53.931168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tjNINnbS+jx9RXiFYoQu7iM475xg4K9jJoALBFF1uUPlOxZasvarGYR+YdYpBC29bAseq53Lo/NSjKbxN9f1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:53.931714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07268","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edf4c575871c6b2758c0a03110f46f1baf32557aa2da2cfe583d9ce16d7f9be3","sha256:6c7bc05dee0e90593a7e3cc12844e5be6c53c6ea92f4c9be407f1342db3e0696"],"state_sha256":"880a31705525ad0c5d45f1ecfbcbbe010c8a2e233824ebb524a6969f237de4ef"}