{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BUDWJVJ7HFYEEI6S2P5SU352JC","short_pith_number":"pith:BUDWJVJ7","schema_version":"1.0","canonical_sha256":"0d0764d53f39704223d2d3fb2a6fba48a392680b7ed07d0303bf38dfc75304a3","source":{"kind":"arxiv","id":"2406.07268","version":2},"attestation_state":"computed","paper":{"title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.MM","authors_text":"Di Sun, Gang Pan, Han Li, Jianfei Yu, Jinyuan Li, Rui Xia, Ziyan Li","submitted_at":"2024-06-11T13:52:29Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.07268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-06-11T13:52:29Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"475c451c9a30ec9ef7addac105d4213e2f11afb8e9d9bce976a6678a1a1e0cb3","abstract_canon_sha256":"4064176fb00b3543f10f7c0df260f80cdcdab43570fb900e2dabf9b07dc47f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:53.931714Z","signature_b64":"tjNINnbS+jx9RXiFYoQu7iM475xg4K9jJoALBFF1uUPlOxZasvarGYR+YdYpBC29bAseq53Lo/NSjKbxN9f1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0764d53f39704223d2d3fb2a6fba48a392680b7ed07d0303bf38dfc75304a3","last_reissued_at":"2026-07-05T12:01:53.931168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:53.931168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.MM","authors_text":"Di Sun, Gang Pan, Han Li, Jianfei Yu, Jinyuan Li, Rui Xia, Ziyan Li","submitted_at":"2024-06-11T13:52:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07268","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.07268/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.07268","created_at":"2026-07-05T12:01:53.931222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07268v2","created_at":"2026-07-05T12:01:53.931222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07268","created_at":"2026-07-05T12:01:53.931222+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUDWJVJ7HFYE","created_at":"2026-07-05T12:01:53.931222+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUDWJVJ7HFYEEI6S","created_at":"2026-07-05T12:01:53.931222+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUDWJVJ7","created_at":"2026-07-05T12:01:53.931222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04844","citing_title":"REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC","json":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC.json","graph_json":"https://pith.science/api/pith-number/BUDWJVJ7HFYEEI6S2P5SU352JC/graph.json","events_json":"https://pith.science/api/pith-number/BUDWJVJ7HFYEEI6S2P5SU352JC/events.json","paper":"https://pith.science/paper/BUDWJVJ7"},"agent_actions":{"view_html":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC","download_json":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC.json","view_paper":"https://pith.science/paper/BUDWJVJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07268&json=true","fetch_graph":"https://pith.science/api/pith-number/BUDWJVJ7HFYEEI6S2P5SU352JC/graph.json","fetch_events":"https://pith.science/api/pith-number/BUDWJVJ7HFYEEI6S2P5SU352JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC/action/storage_attestation","attest_author":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC/action/author_attestation","sign_citation":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC/action/citation_signature","submit_replication":"https://pith.science/pith/BUDWJVJ7HFYEEI6S2P5SU352JC/action/replication_record"}},"created_at":"2026-07-05T12:01:53.931222+00:00","updated_at":"2026-07-05T12:01:53.931222+00:00"}