{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z4EDCR6IFFZSIZZHY2RYPBFNTX","short_pith_number":"pith:Z4EDCR6I","schema_version":"1.0","canonical_sha256":"cf083147c82973246727c6a38784ad9dc6dff0a18e3a27318f4dde5a726b7180","source":{"kind":"arxiv","id":"2303.03761","version":2},"attestation_state":"computed","paper":{"title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gregory Slabaugh, Henry Senior, Luca Rossi, Shanxin Yuan","submitted_at":"2023-03-07T09:56:23Z","abstract_excerpt":"2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image und"},"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":"2303.03761","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T09:56:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0a8ca1d6c82879e92e0ca42691301e8aecc4a48928e046ec2710f0b33c75bad","abstract_canon_sha256":"f4f210b881d920891f108285caf9491269889d04da40bd73c9489505d1ccc4aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:08.951245Z","signature_b64":"1BLySOt6ocY6lh53yhSHhxx6XvrJ4mXUbkd6QiKmQlP0j+mI2CqgWbbDHpZrK/v8wclsJt6ti6gR3HSObX4IDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf083147c82973246727c6a38784ad9dc6dff0a18e3a27318f4dde5a726b7180","last_reissued_at":"2026-07-05T08:07:08.950698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:08.950698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Neural Networks in Vision-Language Image Understanding: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gregory Slabaugh, Henry Senior, Luca Rossi, Shanxin Yuan","submitted_at":"2023-03-07T09:56:23Z","abstract_excerpt":"2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03761","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/2303.03761/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":"2303.03761","created_at":"2026-07-05T08:07:08.950753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03761v2","created_at":"2026-07-05T08:07:08.950753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03761","created_at":"2026-07-05T08:07:08.950753+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4EDCR6IFFZS","created_at":"2026-07-05T08:07:08.950753+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4EDCR6IFFZSIZZH","created_at":"2026-07-05T08:07:08.950753+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4EDCR6I","created_at":"2026-07-05T08:07:08.950753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":97,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX","json":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX.json","graph_json":"https://pith.science/api/pith-number/Z4EDCR6IFFZSIZZHY2RYPBFNTX/graph.json","events_json":"https://pith.science/api/pith-number/Z4EDCR6IFFZSIZZHY2RYPBFNTX/events.json","paper":"https://pith.science/paper/Z4EDCR6I"},"agent_actions":{"view_html":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX","download_json":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX.json","view_paper":"https://pith.science/paper/Z4EDCR6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03761&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4EDCR6IFFZSIZZHY2RYPBFNTX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4EDCR6IFFZSIZZHY2RYPBFNTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX/action/storage_attestation","attest_author":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX/action/author_attestation","sign_citation":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX/action/citation_signature","submit_replication":"https://pith.science/pith/Z4EDCR6IFFZSIZZHY2RYPBFNTX/action/replication_record"}},"created_at":"2026-07-05T08:07:08.950753+00:00","updated_at":"2026-07-05T08:07:08.950753+00:00"}