{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R3OJTZFPGTL63DWI7AKCGMETLH","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":"1916d3732d1e205659ee03e214b3601f90fafd1d580bd3ad285e6cc264bbf3cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-15T01:06:54Z","title_canon_sha256":"5fe3222ad55e6d032abaa7827bfc3d9a227304fef0161e754d79196dc9831cb8"},"schema_version":"1.0","source":{"id":"2005.07310","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07310","created_at":"2026-07-05T01:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07310v2","created_at":"2026-07-05T01:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07310","created_at":"2026-07-05T01:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"R3OJTZFPGTL6","created_at":"2026-07-05T01:20:18Z"},{"alias_kind":"pith_short_16","alias_value":"R3OJTZFPGTL63DWI","created_at":"2026-07-05T01:20:18Z"},{"alias_kind":"pith_short_8","alias_value":"R3OJTZFP","created_at":"2026-07-05T01:20:18Z"}],"graph_snapshots":[{"event_id":"sha256:7907024cf0db4c86df7a937de98e173dda98595f3d60db54df9b7351c8ea65a7","target":"graph","created_at":"2026-07-05T01:20:18Z","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/2005.07310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Transformer-based large-scale pre-trained models have revolutionized vision-and-language (V+L) research. Models such as ViLBERT, LXMERT and UNITER have significantly lifted state of the art across a wide range of V+L benchmarks with joint image-text pre-training. However, little is known about the inner mechanisms that destine their impressive success. To reveal the secrets behind the scene of these powerful models, we present VALUE (Vision-And-Language Understanding Evaluation), a set of meticulously designed probing tasks (e.g., Visual Coreference Resolution, Visual Relation Detection","authors_text":"Jingjing Liu, Jize Cao, Licheng Yu, Yen-Chun Chen, Yu Cheng, Zhe Gan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-15T01:06:54Z","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07310","kind":"arxiv","version":2},"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":"sha256:2877dec3b84da586bd5e8329a3f54fcc6620de684c51f012809224823c28b602","target":"record","created_at":"2026-07-05T01:20:18Z","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":"1916d3732d1e205659ee03e214b3601f90fafd1d580bd3ad285e6cc264bbf3cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-15T01:06:54Z","title_canon_sha256":"5fe3222ad55e6d032abaa7827bfc3d9a227304fef0161e754d79196dc9831cb8"},"schema_version":"1.0","source":{"id":"2005.07310","kind":"arxiv","version":2}},"canonical_sha256":"8edc99e4af34d7ed8ec8f81423309359fdeceeefbf91c73dbe7bee94b02bb372","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8edc99e4af34d7ed8ec8f81423309359fdeceeefbf91c73dbe7bee94b02bb372","first_computed_at":"2026-07-05T01:20:18.114604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:18.114604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ktsx3D4HJzsekdrIpy3GTTY8gZ4m2BdFVfVGMn2i+QIGeUeGSYe/yu1lxFFs/4JvekQyL9xB9WuekIxSQeVEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:18.115067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07310","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2877dec3b84da586bd5e8329a3f54fcc6620de684c51f012809224823c28b602","sha256:7907024cf0db4c86df7a937de98e173dda98595f3d60db54df9b7351c8ea65a7"],"state_sha256":"bf14b9c1efedc46996d468e8c87684d9298d6a9370a113c0ea78f41d4c4d806f"}