{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHDCKI22OCMSHA7UMIIWI3SKP6","short_pith_number":"pith:NHDCKI22","schema_version":"1.0","canonical_sha256":"69c625235a70992383f46211646e4a7fb6c3cab8ccddd9ee6152159932874365","source":{"kind":"arxiv","id":"2507.16877","version":1},"attestation_state":"computed","paper":{"title":"ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bingkun Yang, Chen Su, Junhui Yin, Man Zhang, Muyi Sun, Xingqun Qi, Yizhi Hu, Zezhao Tian, Zhenan Sun","submitted_at":"2025-07-22T11:23:48Z","abstract_excerpt":"Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity relationships in multi-entity scenes, limiting their accuracy and reliability. Additionally, the lack of high-quality datasets with fine-grained, paired image-text-relation annotations hinders further progress. To address this challenge, we first construct a relation-aware, multi-entity REC dataset called ReMeX, which includes detailed relationship and textual "},"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":"2507.16877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T11:23:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"97213157b042e8c01d854893fb46e4debc7b3e86e06fdcccba5d5ad19f88da0a","abstract_canon_sha256":"d03235cf6d29d0e44420b6f58e1a817457d0d89e7ef0bb05fd0fff9d938c57bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:57.626637Z","signature_b64":"IgsJ73S2l401s7ilPFdJw/Bs+p7T+KK3JV8TrySCB4L58mL3F7ZsiIt88J886ZHi+KwLmKEqE3O5N3h8PwwnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69c625235a70992383f46211646e4a7fb6c3cab8ccddd9ee6152159932874365","last_reissued_at":"2026-07-05T11:41:57.625943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:57.625943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReMeREC: Relation-aware and Multi-entity Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bingkun Yang, Chen Su, Junhui Yin, Man Zhang, Muyi Sun, Xingqun Qi, Yizhi Hu, Zezhao Tian, Zhenan Sun","submitted_at":"2025-07-22T11:23:48Z","abstract_excerpt":"Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity relationships in multi-entity scenes, limiting their accuracy and reliability. Additionally, the lack of high-quality datasets with fine-grained, paired image-text-relation annotations hinders further progress. To address this challenge, we first construct a relation-aware, multi-entity REC dataset called ReMeX, which includes detailed relationship and textual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16877","kind":"arxiv","version":1},"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/2507.16877/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":"2507.16877","created_at":"2026-07-05T11:41:57.626038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16877v1","created_at":"2026-07-05T11:41:57.626038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16877","created_at":"2026-07-05T11:41:57.626038+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHDCKI22OCMS","created_at":"2026-07-05T11:41:57.626038+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHDCKI22OCMSHA7U","created_at":"2026-07-05T11:41:57.626038+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHDCKI22","created_at":"2026-07-05T11:41:57.626038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6","json":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6.json","graph_json":"https://pith.science/api/pith-number/NHDCKI22OCMSHA7UMIIWI3SKP6/graph.json","events_json":"https://pith.science/api/pith-number/NHDCKI22OCMSHA7UMIIWI3SKP6/events.json","paper":"https://pith.science/paper/NHDCKI22"},"agent_actions":{"view_html":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6","download_json":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6.json","view_paper":"https://pith.science/paper/NHDCKI22","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16877&json=true","fetch_graph":"https://pith.science/api/pith-number/NHDCKI22OCMSHA7UMIIWI3SKP6/graph.json","fetch_events":"https://pith.science/api/pith-number/NHDCKI22OCMSHA7UMIIWI3SKP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6/action/storage_attestation","attest_author":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6/action/author_attestation","sign_citation":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6/action/citation_signature","submit_replication":"https://pith.science/pith/NHDCKI22OCMSHA7UMIIWI3SKP6/action/replication_record"}},"created_at":"2026-07-05T11:41:57.626038+00:00","updated_at":"2026-07-05T11:41:57.626038+00:00"}