{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:I2TS7WWZ6N65SDIVDM7OIQYWTY","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":"b9c7ab6391f521cca7a7cc314c42a337cfdf993d4d2884439d5408de7aae37ad","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-30T16:03:12Z","title_canon_sha256":"9610245fdcd496fa6df9d6501a9b5b0ec3947aaf0e7ab9aba619433fce0bc3c2"},"schema_version":"1.0","source":{"id":"2006.16934","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16934","created_at":"2026-07-05T02:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16934v3","created_at":"2026-07-05T02:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16934","created_at":"2026-07-05T02:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"I2TS7WWZ6N65","created_at":"2026-07-05T02:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"I2TS7WWZ6N65SDIV","created_at":"2026-07-05T02:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"I2TS7WWZ","created_at":"2026-07-05T02:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:8ab3e2d5cc0cb48bd6cbf3ec9b80066a0db5acd4b82a9456dd787a92e285e81b","target":"graph","created_at":"2026-07-05T02:24:29Z","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/2006.16934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a knowledge-enhanced approach, ERNIE-ViL, which incorporates structured knowledge obtained from scene graphs to learn joint representations of vision-language. ERNIE-ViL tries to build the detailed semantic connections (objects, attributes of objects and relationships between objects) across vision and language, which are essential to vision-language cross-modal tasks. Utilizing scene graphs of visual scenes, ERNIE-ViL constructs Scene Graph Prediction tasks, i.e., Object Prediction, Attribute Prediction and Relationship Prediction tasks in the pre-training phase. Specifically, thes","authors_text":"Fei Yu, HaiFeng Wang, Hao Tian, Hua Wu, Jiji Tang, Weichong Yin, Yu Sun","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-30T16:03:12Z","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16934","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":"sha256:9d9cd61ceabc1c352ec2e4987c450fa5fdbc9d72b7056f633fcbbf5add9f4be8","target":"record","created_at":"2026-07-05T02:24:29Z","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":"b9c7ab6391f521cca7a7cc314c42a337cfdf993d4d2884439d5408de7aae37ad","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-30T16:03:12Z","title_canon_sha256":"9610245fdcd496fa6df9d6501a9b5b0ec3947aaf0e7ab9aba619433fce0bc3c2"},"schema_version":"1.0","source":{"id":"2006.16934","kind":"arxiv","version":3}},"canonical_sha256":"46a72fdad9f37dd90d151b3ee443169e077e1ecf8815fe7d89b2b2d82e67446b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46a72fdad9f37dd90d151b3ee443169e077e1ecf8815fe7d89b2b2d82e67446b","first_computed_at":"2026-07-05T02:24:29.751692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:29.751692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QPLMNMgY1IYpx7Gp7DpwmRZWciFSkUO/aTbYBWt9WQzM4HFRbV0mGlu2Ef6QyIr2FSLSubYMmal44OacH+pQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:29.752074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16934","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d9cd61ceabc1c352ec2e4987c450fa5fdbc9d72b7056f633fcbbf5add9f4be8","sha256:8ab3e2d5cc0cb48bd6cbf3ec9b80066a0db5acd4b82a9456dd787a92e285e81b"],"state_sha256":"d0bfb798cabe810ec30385706ece6695b7c8a2479e5de06625accfeb7cebe91f"}