{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GXNI7QLDSOQVE22BJF2YEIPBNB","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":"0e280ff011032bb9db912b912bc807947022f8f0c0591bd6522370db1fe92abb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-12T20:31:28Z","title_canon_sha256":"fa3b80be56f82a54cbff6127efa6e85a8667f95713fb9a27fafb50a2a4c3a926"},"schema_version":"1.0","source":{"id":"2206.05836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05836","created_at":"2026-07-05T05:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05836v2","created_at":"2026-07-05T05:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05836","created_at":"2026-07-05T05:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"GXNI7QLDSOQV","created_at":"2026-07-05T05:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"GXNI7QLDSOQVE22B","created_at":"2026-07-05T05:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"GXNI7QLD","created_at":"2026-07-05T05:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:02aad3fad0a36308a701d512147eeda9ce3dbe19961b3e67695559b8cbea0eca","target":"graph","created_at":"2026-07-05T05:05:48Z","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/2206.05836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-12T20:31:28Z","title":"GLIPv2: Unifying Localization and Vision-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05836","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:cf20b97a420a01069f63cd2a2c0715acf61e35af957404a424cbc3e0f1fdecd6","target":"record","created_at":"2026-07-05T05:05:48Z","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":"0e280ff011032bb9db912b912bc807947022f8f0c0591bd6522370db1fe92abb","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-12T20:31:28Z","title_canon_sha256":"fa3b80be56f82a54cbff6127efa6e85a8667f95713fb9a27fafb50a2a4c3a926"},"schema_version":"1.0","source":{"id":"2206.05836","kind":"arxiv","version":2}},"canonical_sha256":"35da8fc16393a1526b4149758221e1686b04b8f7f4a18bc09a309a80ea0e6805","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35da8fc16393a1526b4149758221e1686b04b8f7f4a18bc09a309a80ea0e6805","first_computed_at":"2026-07-05T05:05:48.370879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:48.370879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WCV1IkwYjguflBRTYlZbnHV/vRHCbE0QIMM7Q0M88fxPb7Ml1zt+hyVt8LNrosAdaxeaDXh6+sIRnPVOqPlGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:48.371498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf20b97a420a01069f63cd2a2c0715acf61e35af957404a424cbc3e0f1fdecd6","sha256:02aad3fad0a36308a701d512147eeda9ce3dbe19961b3e67695559b8cbea0eca"],"state_sha256":"dc08653bf8abe139cc71c2fd133b28d7115f1addf070cea2a878c15b1c6c071c"}