{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GXNI7QLDSOQVE22BJF2YEIPBNB","short_pith_number":"pith:GXNI7QLD","schema_version":"1.0","canonical_sha256":"35da8fc16393a1526b4149758221e1686b04b8f7f4a18bc09a309a80ea0e6805","source":{"kind":"arxiv","id":"2206.05836","version":2},"attestation_state":"computed","paper":{"title":"GLIPv2: Unifying Localization and Vision-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Haotian Zhang, Jenq-Neng Hwang, Jianfeng Gao, Lijuan Wang, Liunian Harold Li, Lu Yuan, Pengchuan Zhang, Xiaowei Hu, Xiyang Dai, Yen-Chun Chen","submitted_at":"2022-06-12T20:31:28Z","abstract_excerpt":"We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but "},"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":"2206.05836","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-12T20:31:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"fa3b80be56f82a54cbff6127efa6e85a8667f95713fb9a27fafb50a2a4c3a926","abstract_canon_sha256":"0e280ff011032bb9db912b912bc807947022f8f0c0591bd6522370db1fe92abb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:48.371498Z","signature_b64":"WCV1IkwYjguflBRTYlZbnHV/vRHCbE0QIMM7Q0M88fxPb7Ml1zt+hyVt8LNrosAdaxeaDXh6+sIRnPVOqPlGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35da8fc16393a1526b4149758221e1686b04b8f7f4a18bc09a309a80ea0e6805","last_reissued_at":"2026-07-05T05:05:48.370879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:48.370879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLIPv2: Unifying Localization and Vision-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Haotian Zhang, Jenq-Neng Hwang, Jianfeng Gao, Lijuan Wang, Liunian Harold Li, Lu Yuan, Pengchuan Zhang, Xiaowei Hu, Xiyang Dai, Yen-Chun Chen","submitted_at":"2022-06-12T20:31:28Z","abstract_excerpt":"We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05836","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/2206.05836/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":"2206.05836","created_at":"2026-07-05T05:05:48.370958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05836v2","created_at":"2026-07-05T05:05:48.370958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05836","created_at":"2026-07-05T05:05:48.370958+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXNI7QLDSOQV","created_at":"2026-07-05T05:05:48.370958+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXNI7QLDSOQVE22B","created_at":"2026-07-05T05:05:48.370958+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXNI7QLD","created_at":"2026-07-05T05:05:48.370958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31145","citing_title":"FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2509.10026","citing_title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB","json":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB.json","graph_json":"https://pith.science/api/pith-number/GXNI7QLDSOQVE22BJF2YEIPBNB/graph.json","events_json":"https://pith.science/api/pith-number/GXNI7QLDSOQVE22BJF2YEIPBNB/events.json","paper":"https://pith.science/paper/GXNI7QLD"},"agent_actions":{"view_html":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB","download_json":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB.json","view_paper":"https://pith.science/paper/GXNI7QLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05836&json=true","fetch_graph":"https://pith.science/api/pith-number/GXNI7QLDSOQVE22BJF2YEIPBNB/graph.json","fetch_events":"https://pith.science/api/pith-number/GXNI7QLDSOQVE22BJF2YEIPBNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB/action/storage_attestation","attest_author":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB/action/author_attestation","sign_citation":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB/action/citation_signature","submit_replication":"https://pith.science/pith/GXNI7QLDSOQVE22BJF2YEIPBNB/action/replication_record"}},"created_at":"2026-07-05T05:05:48.370958+00:00","updated_at":"2026-07-05T05:05:48.370958+00:00"}