{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KRXMRW4OCZ2HX6XQMRJ6TFW77E","short_pith_number":"pith:KRXMRW4O","schema_version":"1.0","canonical_sha256":"546ec8db8e16747bfaf06453e996dff9378faab5c9294b9058301fec07b71401","source":{"kind":"arxiv","id":"2303.13233","version":2},"attestation_state":"computed","paper":{"title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juncheng Li, Qifan Yu, Siliang Tang, Wei Ji, Yueting Zhuang, Yu Wu","submitted_at":"2023-03-23T13:06:38Z","abstract_excerpt":"Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution issues that tail-predicates are more costly to train and hard to distinguish due to a small amount of annotated data compared to frequent predicates. Existing re-balancing strategies try to handle it via prior rules but are still confined to pre-defined conditions, which are not scalable for various models and datasets. In this paper, we propose a Cross-modal prediCate boostin"},"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":"2303.13233","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T13:06:38Z","cross_cats_sorted":[],"title_canon_sha256":"364f27b9480f7ab50c73334912aaa5bc7caba3b4d9dd1658fe037e572fb19822","abstract_canon_sha256":"18a9dc3129205c86deb97dac582ec17716a461f3ebb34ecc99765b579a317983"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:42.965807Z","signature_b64":"FFUG+RN4Tzfz63wT1Tpe14A4xFSBTHb01dyEPkZR9J4g3BcS2M5tqOlh11G3r66GpzUtUNHeSWTg7e5xScYCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546ec8db8e16747bfaf06453e996dff9378faab5c9294b9058301fec07b71401","last_reissued_at":"2026-07-05T06:42:42.965329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:42.965329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juncheng Li, Qifan Yu, Siliang Tang, Wei Ji, Yueting Zhuang, Yu Wu","submitted_at":"2023-03-23T13:06:38Z","abstract_excerpt":"Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution issues that tail-predicates are more costly to train and hard to distinguish due to a small amount of annotated data compared to frequent predicates. Existing re-balancing strategies try to handle it via prior rules but are still confined to pre-defined conditions, which are not scalable for various models and datasets. In this paper, we propose a Cross-modal prediCate boostin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13233","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/2303.13233/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":"2303.13233","created_at":"2026-07-05T06:42:42.965407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13233v2","created_at":"2026-07-05T06:42:42.965407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13233","created_at":"2026-07-05T06:42:42.965407+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRXMRW4OCZ2H","created_at":"2026-07-05T06:42:42.965407+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRXMRW4OCZ2HX6XQ","created_at":"2026-07-05T06:42:42.965407+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRXMRW4O","created_at":"2026-07-05T06:42:42.965407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21788","citing_title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E","json":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E.json","graph_json":"https://pith.science/api/pith-number/KRXMRW4OCZ2HX6XQMRJ6TFW77E/graph.json","events_json":"https://pith.science/api/pith-number/KRXMRW4OCZ2HX6XQMRJ6TFW77E/events.json","paper":"https://pith.science/paper/KRXMRW4O"},"agent_actions":{"view_html":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E","download_json":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E.json","view_paper":"https://pith.science/paper/KRXMRW4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13233&json=true","fetch_graph":"https://pith.science/api/pith-number/KRXMRW4OCZ2HX6XQMRJ6TFW77E/graph.json","fetch_events":"https://pith.science/api/pith-number/KRXMRW4OCZ2HX6XQMRJ6TFW77E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E/action/storage_attestation","attest_author":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E/action/author_attestation","sign_citation":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E/action/citation_signature","submit_replication":"https://pith.science/pith/KRXMRW4OCZ2HX6XQMRJ6TFW77E/action/replication_record"}},"created_at":"2026-07-05T06:42:42.965407+00:00","updated_at":"2026-07-05T06:42:42.965407+00:00"}