{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RLDG62C5NRGN7MIX5G7AI2DRDV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5fe469afb3b83fcaa7f51f981181050ddb64ab435c9090157f91f0a4e0aa77a4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T03:57:05Z","title_canon_sha256":"c8c91c61a6cc8122a4406df18df94702149a4535becec61d4083d1754f935ffa"},"schema_version":"1.0","source":{"id":"2305.06152","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06152","created_at":"2026-07-05T07:23:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06152v3","created_at":"2026-07-05T07:23:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06152","created_at":"2026-07-05T07:23:25Z"},{"alias_kind":"pith_short_12","alias_value":"RLDG62C5NRGN","created_at":"2026-07-05T07:23:25Z"},{"alias_kind":"pith_short_16","alias_value":"RLDG62C5NRGN7MIX","created_at":"2026-07-05T07:23:25Z"},{"alias_kind":"pith_short_8","alias_value":"RLDG62C5","created_at":"2026-07-05T07:23:25Z"}],"graph_snapshots":[{"event_id":"sha256:8449a56674b311afed815ecce82b601ec7d3ff28945862dd9c0ba4e5696dae6e","target":"graph","created_at":"2026-07-05T07:23:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.06152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiji Tang, Rongsheng Zhang, Tangjie Lv, Weijie Chen, Wen Zhang, Xinfeng Zhang, Yufeng Huang, Zeng Zhao, Zhipeng Hu, Zhou Zhao, Zhuo Chen","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T03:57:05Z","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06152","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b15d42365aafc74e12e047e2764569432f64f1e800cc0d2eb49bd9ea1fcffb96","target":"record","created_at":"2026-07-05T07:23:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5fe469afb3b83fcaa7f51f981181050ddb64ab435c9090157f91f0a4e0aa77a4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T03:57:05Z","title_canon_sha256":"c8c91c61a6cc8122a4406df18df94702149a4535becec61d4083d1754f935ffa"},"schema_version":"1.0","source":{"id":"2305.06152","kind":"arxiv","version":3}},"canonical_sha256":"8ac66f685d6c4cdfb117e9be0468711d43652b995ccea8dec2906e58a9192e8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac66f685d6c4cdfb117e9be0468711d43652b995ccea8dec2906e58a9192e8a","first_computed_at":"2026-07-05T07:23:25.768069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:25.768069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zsXoLCjAihAell6YE2g5dPdsewFiBq3tlMDh7OnyhAWNkgrjscro6bAa6UdRrE1xGRTbwsoJPppoBfPq28AmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:25.768543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06152","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b15d42365aafc74e12e047e2764569432f64f1e800cc0d2eb49bd9ea1fcffb96","sha256:8449a56674b311afed815ecce82b601ec7d3ff28945862dd9c0ba4e5696dae6e"],"state_sha256":"8e4b189b9414f524a08fb5712c6122a26e00361f378f25f5a94eea14d255688a"}