{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XNPVKYIEBCPFQOUG5GYYPQD2LN","short_pith_number":"pith:XNPVKYIE","schema_version":"1.0","canonical_sha256":"bb5f556104089e583a86e9b187c07a5b609e51c8e22a832e38747904e1e5811a","source":{"kind":"arxiv","id":"2401.12835","version":1},"attestation_state":"computed","paper":{"title":"SGTR+: End-to-end Scene Graph Generation with Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Rongjie Li, Songyang Zhang, Xuming He","submitted_at":"2024-01-23T15:18:20Z","abstract_excerpt":"Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up, two-stage or point-based, one-stage approach, which often suffers from high time complexity or suboptimal designs. In this work, we propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem. To address the issues above, we create a transformer-based end-to-end framework to generate the entity and entity-aware predicate proposal set, and infer directed edges to form relation tr"},"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":"2401.12835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T15:18:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"487f6d4a977f6e8bbfaa4ec61cd7160154bd96dd9fa9994bda4b50af4e8530bd","abstract_canon_sha256":"ea1d98b794d64bf6f3799c5dfa47ae6114ab597d74f4b79f96b8f7242fabf6dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:36.797779Z","signature_b64":"ID7hULcY2n/5k5AUS3Q6RRKpe68MsFVOPdK1PIUAGSwBQm5CEXjSZO5yjEcFm5FJK3YVhq7ZEQ2x2tEOJt+PAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5f556104089e583a86e9b187c07a5b609e51c8e22a832e38747904e1e5811a","last_reissued_at":"2026-07-05T07:36:36.797374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:36.797374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGTR+: End-to-end Scene Graph Generation with Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Rongjie Li, Songyang Zhang, Xuming He","submitted_at":"2024-01-23T15:18:20Z","abstract_excerpt":"Scene Graph Generation (SGG) remains a challenging visual understanding task due to its compositional property. Most previous works adopt a bottom-up, two-stage or point-based, one-stage approach, which often suffers from high time complexity or suboptimal designs. In this work, we propose a novel SGG method to address the aforementioned issues, formulating the task as a bipartite graph construction problem. To address the issues above, we create a transformer-based end-to-end framework to generate the entity and entity-aware predicate proposal set, and infer directed edges to form relation tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12835","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/2401.12835/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":"2401.12835","created_at":"2026-07-05T07:36:36.797427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12835v1","created_at":"2026-07-05T07:36:36.797427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12835","created_at":"2026-07-05T07:36:36.797427+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNPVKYIEBCPF","created_at":"2026-07-05T07:36:36.797427+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNPVKYIEBCPFQOUG","created_at":"2026-07-05T07:36:36.797427+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNPVKYIE","created_at":"2026-07-05T07:36:36.797427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19021","citing_title":"Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN","json":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN.json","graph_json":"https://pith.science/api/pith-number/XNPVKYIEBCPFQOUG5GYYPQD2LN/graph.json","events_json":"https://pith.science/api/pith-number/XNPVKYIEBCPFQOUG5GYYPQD2LN/events.json","paper":"https://pith.science/paper/XNPVKYIE"},"agent_actions":{"view_html":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN","download_json":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN.json","view_paper":"https://pith.science/paper/XNPVKYIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12835&json=true","fetch_graph":"https://pith.science/api/pith-number/XNPVKYIEBCPFQOUG5GYYPQD2LN/graph.json","fetch_events":"https://pith.science/api/pith-number/XNPVKYIEBCPFQOUG5GYYPQD2LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN/action/storage_attestation","attest_author":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN/action/author_attestation","sign_citation":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN/action/citation_signature","submit_replication":"https://pith.science/pith/XNPVKYIEBCPFQOUG5GYYPQD2LN/action/replication_record"}},"created_at":"2026-07-05T07:36:36.797427+00:00","updated_at":"2026-07-05T07:36:36.797427+00:00"}