{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BS7JMER64D4M5GH3KXDRNDYZ45","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":"ada966375c0cd7d8ebb88dad188eccdd1075878d5a67961ca7507c672d9f9d9a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T08:28:38Z","title_canon_sha256":"ddc755d27221d5bd1d35c37df96433046242ecd19dc42879023e5f252f78848a"},"schema_version":"1.0","source":{"id":"2305.13812","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13812","created_at":"2026-07-05T07:04:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13812v3","created_at":"2026-07-05T07:04:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13812","created_at":"2026-07-05T07:04:47Z"},{"alias_kind":"pith_short_12","alias_value":"BS7JMER64D4M","created_at":"2026-07-05T07:04:47Z"},{"alias_kind":"pith_short_16","alias_value":"BS7JMER64D4M5GH3","created_at":"2026-07-05T07:04:47Z"},{"alias_kind":"pith_short_8","alias_value":"BS7JMER6","created_at":"2026-07-05T07:04:47Z"}],"graph_snapshots":[{"event_id":"sha256:8e43acd863544b1b1268841442be8832eeb3db448a860b332a3689e363be74b6","target":"graph","created_at":"2026-07-05T07:04:47Z","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/2305.13812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has highlighted severe limitations of these models in their ability to perform compositional reasoning over objects, attributes, and relations. Scene graphs have emerged as an effective way to understand images compositionally. These are graph-structured semantic representations of images that contain objects, their attributes, and relations with other objects in a scen","authors_text":"Harman Singh, Jingfei Du, Mengjiao Wang, Pengchuan Zhang, Qifan Wang, Wenhan Xiong, Yu Chen","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T08:28:38Z","title":"Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13812","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:cf45ebc0a008873d23a0fd2b8088be5e7b83396d3bb06b2588a723744b3a4b44","target":"record","created_at":"2026-07-05T07:04:47Z","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":"ada966375c0cd7d8ebb88dad188eccdd1075878d5a67961ca7507c672d9f9d9a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T08:28:38Z","title_canon_sha256":"ddc755d27221d5bd1d35c37df96433046242ecd19dc42879023e5f252f78848a"},"schema_version":"1.0","source":{"id":"2305.13812","kind":"arxiv","version":3}},"canonical_sha256":"0cbe96123ee0f8ce98fb55c7168f19e77872f5a9c031c3dbbd3b4ae829ef14ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cbe96123ee0f8ce98fb55c7168f19e77872f5a9c031c3dbbd3b4ae829ef14ff","first_computed_at":"2026-07-05T07:04:47.440886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:47.440886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAFF8pCQOfbFJegle6CCzo1snJJ3d3NqW7c+gkCjsQA4ytlV2wXWEIr2+xhBOz4RTW/5snY9zcLQCBFr7c37Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:47.441349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13812","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf45ebc0a008873d23a0fd2b8088be5e7b83396d3bb06b2588a723744b3a4b44","sha256:8e43acd863544b1b1268841442be8832eeb3db448a860b332a3689e363be74b6"],"state_sha256":"9065742136605efd7607514d654b1a3cbbc6baa0a12a36462a16ebebc3984dc5"}