{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BYXZK5L6KLLYWKWHPUZ7VZWP23","short_pith_number":"pith:BYXZK5L6","schema_version":"1.0","canonical_sha256":"0e2f95757e52d78b2ac77d33fae6cfd6df340d1b2eeefcacf0238d01057ab569","source":{"kind":"arxiv","id":"2308.16182","version":2},"attestation_state":"computed","paper":{"title":"GREC: Generalized Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Henghui Ding, Shuting He, Xudong Jiang","submitted_at":"2023-08-30T17:58:50Z","abstract_excerpt":"The objective of Classic Referring Expression Comprehension (REC) is to produce a bounding box corresponding to the object mentioned in a given textual description. Commonly, existing datasets and techniques in classic REC are tailored for expressions that pertain to a single target, meaning a sole expression is linked to one specific object. Expressions that refer to multiple targets or involve no specific target have not been taken into account. This constraint hinders the practical applicability of REC. This study introduces a new benchmark termed as Generalized Referring Expression Compreh"},"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":"2308.16182","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-30T17:58:50Z","cross_cats_sorted":[],"title_canon_sha256":"674fd9a0db0ecce8b2ef7120e0cb5f8dfd101b7897e9ba950383b4757899f126","abstract_canon_sha256":"5da95625738262ee3fac8ea1644f422fc5b01a5f86cd8f542c924d9344836e48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:49.906730Z","signature_b64":"TcqZmaPD+of9eUyuLqHDcluTuff8XUBc+TCjnHqCMuZbS4yfkvIJujSy8CYa61pw0i6bwtSIV7D2lzlCUT56Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e2f95757e52d78b2ac77d33fae6cfd6df340d1b2eeefcacf0238d01057ab569","last_reissued_at":"2026-07-05T07:27:49.906140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:49.906140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GREC: Generalized Referring Expression Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Henghui Ding, Shuting He, Xudong Jiang","submitted_at":"2023-08-30T17:58:50Z","abstract_excerpt":"The objective of Classic Referring Expression Comprehension (REC) is to produce a bounding box corresponding to the object mentioned in a given textual description. Commonly, existing datasets and techniques in classic REC are tailored for expressions that pertain to a single target, meaning a sole expression is linked to one specific object. Expressions that refer to multiple targets or involve no specific target have not been taken into account. This constraint hinders the practical applicability of REC. This study introduces a new benchmark termed as Generalized Referring Expression Compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16182","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/2308.16182/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":"2308.16182","created_at":"2026-07-05T07:27:49.906198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16182v2","created_at":"2026-07-05T07:27:49.906198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16182","created_at":"2026-07-05T07:27:49.906198+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYXZK5L6KLLY","created_at":"2026-07-05T07:27:49.906198+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYXZK5L6KLLYWKWH","created_at":"2026-07-05T07:27:49.906198+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYXZK5L6","created_at":"2026-07-05T07:27:49.906198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24498","citing_title":"VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26102","citing_title":"InstructSAM: Segment Any Instance with Any Instructions","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22034","citing_title":"AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21976","citing_title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.02791","citing_title":"Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23","json":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23.json","graph_json":"https://pith.science/api/pith-number/BYXZK5L6KLLYWKWHPUZ7VZWP23/graph.json","events_json":"https://pith.science/api/pith-number/BYXZK5L6KLLYWKWHPUZ7VZWP23/events.json","paper":"https://pith.science/paper/BYXZK5L6"},"agent_actions":{"view_html":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23","download_json":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23.json","view_paper":"https://pith.science/paper/BYXZK5L6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16182&json=true","fetch_graph":"https://pith.science/api/pith-number/BYXZK5L6KLLYWKWHPUZ7VZWP23/graph.json","fetch_events":"https://pith.science/api/pith-number/BYXZK5L6KLLYWKWHPUZ7VZWP23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23/action/storage_attestation","attest_author":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23/action/author_attestation","sign_citation":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23/action/citation_signature","submit_replication":"https://pith.science/pith/BYXZK5L6KLLYWKWHPUZ7VZWP23/action/replication_record"}},"created_at":"2026-07-05T07:27:49.906198+00:00","updated_at":"2026-07-05T07:27:49.906198+00:00"}