{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TQLYKQJW336MPDK4WQUY3OASOQ","short_pith_number":"pith:TQLYKQJW","schema_version":"1.0","canonical_sha256":"9c17854136defcc78d5cb4298db8127420b1787122a19f4d1168143d1cf444a9","source":{"kind":"arxiv","id":"2203.10202","version":1},"attestation_state":"computed","paper":{"title":"Relationformer: A Unified Framework for Image-to-Graph Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bastian Wittmann, Bjoern Menze, Georgios Kaissis, Hongwei Li, Ivan Ezhov, Jiazhen Pan, Johannes Paetzold, Rajat Koner, Sahand Sharifzadeh, Suprosanna Shit, Volker Tresp","submitted_at":"2022-03-19T00:36:59Z","abstract_excerpt":"A comprehensive representation of an image requires understanding objects and their mutual relationship, especially in image-to-graph generation, e.g., road network extraction, blood-vessel network extraction, or scene graph generation. Traditionally, image-to-graph generation is addressed with a two-stage approach consisting of object detection followed by a separate relation prediction, which prevents simultaneous object-relation interaction. This work proposes a unified one-stage transformer-based framework, namely Relationformer, that jointly predicts objects and their relations. We levera"},"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":"2203.10202","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-19T00:36:59Z","cross_cats_sorted":[],"title_canon_sha256":"990622afc59e423b4669e2bededdc1d6ad9e11be4015914d8ca73c3f91b7946e","abstract_canon_sha256":"4959b11b233300525f699635ad2109d19f48938b89827cec0ea9cc2015d5ad73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:32.617863Z","signature_b64":"MdVPZbj1WJuDiftnqFKNdiUSOinNbqPkC5dQor9ibXDAmDRHKF2p4LqQi0XpR5c2aMDHi2YMAHpZ2WI5D165AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c17854136defcc78d5cb4298db8127420b1787122a19f4d1168143d1cf444a9","last_reissued_at":"2026-07-05T04:06:32.617429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:32.617429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relationformer: A Unified Framework for Image-to-Graph Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bastian Wittmann, Bjoern Menze, Georgios Kaissis, Hongwei Li, Ivan Ezhov, Jiazhen Pan, Johannes Paetzold, Rajat Koner, Sahand Sharifzadeh, Suprosanna Shit, Volker Tresp","submitted_at":"2022-03-19T00:36:59Z","abstract_excerpt":"A comprehensive representation of an image requires understanding objects and their mutual relationship, especially in image-to-graph generation, e.g., road network extraction, blood-vessel network extraction, or scene graph generation. Traditionally, image-to-graph generation is addressed with a two-stage approach consisting of object detection followed by a separate relation prediction, which prevents simultaneous object-relation interaction. This work proposes a unified one-stage transformer-based framework, namely Relationformer, that jointly predicts objects and their relations. We levera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10202","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/2203.10202/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":"2203.10202","created_at":"2026-07-05T04:06:32.617490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10202v1","created_at":"2026-07-05T04:06:32.617490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10202","created_at":"2026-07-05T04:06:32.617490+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQLYKQJW336M","created_at":"2026-07-05T04:06:32.617490+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQLYKQJW336MPDK4","created_at":"2026-07-05T04:06:32.617490+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQLYKQJW","created_at":"2026-07-05T04:06:32.617490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22702","citing_title":"Modular Diffusion Models for Structured Visual Recognition","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16513","citing_title":"SynthPID: P&ID digitization from Topology-Preserving Synthetic Data","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ","json":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ.json","graph_json":"https://pith.science/api/pith-number/TQLYKQJW336MPDK4WQUY3OASOQ/graph.json","events_json":"https://pith.science/api/pith-number/TQLYKQJW336MPDK4WQUY3OASOQ/events.json","paper":"https://pith.science/paper/TQLYKQJW"},"agent_actions":{"view_html":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ","download_json":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ.json","view_paper":"https://pith.science/paper/TQLYKQJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10202&json=true","fetch_graph":"https://pith.science/api/pith-number/TQLYKQJW336MPDK4WQUY3OASOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TQLYKQJW336MPDK4WQUY3OASOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ/action/storage_attestation","attest_author":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ/action/author_attestation","sign_citation":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ/action/citation_signature","submit_replication":"https://pith.science/pith/TQLYKQJW336MPDK4WQUY3OASOQ/action/replication_record"}},"created_at":"2026-07-05T04:06:32.617490+00:00","updated_at":"2026-07-05T04:06:32.617490+00:00"}