{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RLDG62C5NRGN7MIX5G7AI2DRDV","short_pith_number":"pith:RLDG62C5","schema_version":"1.0","canonical_sha256":"8ac66f685d6c4cdfb117e9be0468711d43652b995ccea8dec2906e58a9192e8a","source":{"kind":"arxiv","id":"2305.06152","version":3},"attestation_state":"computed","paper":{"title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CL","authors_text":"Jiji Tang, Rongsheng Zhang, Tangjie Lv, Weijie Chen, Wen Zhang, Xinfeng Zhang, Yufeng Huang, Zeng Zhao, Zhipeng Hu, Zhou Zhao, Zhuo Chen","submitted_at":"2023-05-06T03:57:05Z","abstract_excerpt":"Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require structured representations, i.e., representations of objects, attributes, and relations. As illustrated in Fig.~reffig:case (a), the models cannot make a distinction between ``An astronaut rides a horse\" and ``A horse rides an astronaut\". This is because they fail to fully leverage structured knowledge when learning representations in multi-modal scenarios. In this paper, we pres"},"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":"2305.06152","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T03:57:05Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"c8c91c61a6cc8122a4406df18df94702149a4535becec61d4083d1754f935ffa","abstract_canon_sha256":"5fe469afb3b83fcaa7f51f981181050ddb64ab435c9090157f91f0a4e0aa77a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:25.768543Z","signature_b64":"zsXoLCjAihAell6YE2g5dPdsewFiBq3tlMDh7OnyhAWNkgrjscro6bAa6UdRrE1xGRTbwsoJPppoBfPq28AmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac66f685d6c4cdfb117e9be0468711d43652b995ccea8dec2906e58a9192e8a","last_reissued_at":"2026-07-05T07:23:25.768069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:25.768069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CL","authors_text":"Jiji Tang, Rongsheng Zhang, Tangjie Lv, Weijie Chen, Wen Zhang, Xinfeng Zhang, Yufeng Huang, Zeng Zhao, Zhipeng Hu, Zhou Zhao, Zhuo Chen","submitted_at":"2023-05-06T03:57:05Z","abstract_excerpt":"Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require structured representations, i.e., representations of objects, attributes, and relations. As illustrated in Fig.~reffig:case (a), the models cannot make a distinction between ``An astronaut rides a horse\" and ``A horse rides an astronaut\". This is because they fail to fully leverage structured knowledge when learning representations in multi-modal scenarios. In this paper, we pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06152","kind":"arxiv","version":3},"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/2305.06152/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":"2305.06152","created_at":"2026-07-05T07:23:25.768127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06152v3","created_at":"2026-07-05T07:23:25.768127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06152","created_at":"2026-07-05T07:23:25.768127+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLDG62C5NRGN","created_at":"2026-07-05T07:23:25.768127+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLDG62C5NRGN7MIX","created_at":"2026-07-05T07:23:25.768127+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLDG62C5","created_at":"2026-07-05T07:23:25.768127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17267","citing_title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV","json":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV.json","graph_json":"https://pith.science/api/pith-number/RLDG62C5NRGN7MIX5G7AI2DRDV/graph.json","events_json":"https://pith.science/api/pith-number/RLDG62C5NRGN7MIX5G7AI2DRDV/events.json","paper":"https://pith.science/paper/RLDG62C5"},"agent_actions":{"view_html":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV","download_json":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV.json","view_paper":"https://pith.science/paper/RLDG62C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06152&json=true","fetch_graph":"https://pith.science/api/pith-number/RLDG62C5NRGN7MIX5G7AI2DRDV/graph.json","fetch_events":"https://pith.science/api/pith-number/RLDG62C5NRGN7MIX5G7AI2DRDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV/action/storage_attestation","attest_author":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV/action/author_attestation","sign_citation":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV/action/citation_signature","submit_replication":"https://pith.science/pith/RLDG62C5NRGN7MIX5G7AI2DRDV/action/replication_record"}},"created_at":"2026-07-05T07:23:25.768127+00:00","updated_at":"2026-07-05T07:23:25.768127+00:00"}