{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3HHEZLGLRBPQ2SC2EDYXSBNXCD","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":"0e5d33f6c4cb63f990ea8e7916ac0f3ded177489145532407389bc45fd8a004b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T06:25:53Z","title_canon_sha256":"da2ff7ed1c68ea91791a20530511830b41fad18206f2e6498ee026d9bf251ea4"},"schema_version":"1.0","source":{"id":"2207.00221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00221","created_at":"2026-07-05T06:23:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00221v2","created_at":"2026-07-05T06:23:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00221","created_at":"2026-07-05T06:23:44Z"},{"alias_kind":"pith_short_12","alias_value":"3HHEZLGLRBPQ","created_at":"2026-07-05T06:23:44Z"},{"alias_kind":"pith_short_16","alias_value":"3HHEZLGLRBPQ2SC2","created_at":"2026-07-05T06:23:44Z"},{"alias_kind":"pith_short_8","alias_value":"3HHEZLGL","created_at":"2026-07-05T06:23:44Z"}],"graph_snapshots":[{"event_id":"sha256:8d2fbadf205a247c90b3740be8f862968faa12349bcfa26ce5ec0faf43f89107","target":"graph","created_at":"2026-07-05T06:23:44Z","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/2207.00221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Pretraining (VLP) models have recently successfully facilitated many cross-modal downstream tasks. Most existing works evaluated their systems by comparing the fine-tuned downstream task performance. However, only average downstream task accuracy provides little information about the pros and cons of each VLP method, let alone provides insights on how the community can improve the systems in the future. Inspired by the CheckList for testing natural language processing, we exploit VL-CheckList, a novel framework to understand the capabilities of VLP models. The proposed method d","authors_text":"Haozhan Shen, Jianwei Yin, Kyusong Lee, Mingwei Zhu, Tiancheng Zhao, Tianqi Zhang, Xiaopeng Lu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T06:25:53Z","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00221","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":"sha256:71adc2a978f12e006923da01bb6c2556fb4ebe108f310684233acdd80038caf0","target":"record","created_at":"2026-07-05T06:23:44Z","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":"0e5d33f6c4cb63f990ea8e7916ac0f3ded177489145532407389bc45fd8a004b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-01T06:25:53Z","title_canon_sha256":"da2ff7ed1c68ea91791a20530511830b41fad18206f2e6498ee026d9bf251ea4"},"schema_version":"1.0","source":{"id":"2207.00221","kind":"arxiv","version":2}},"canonical_sha256":"d9ce4caccb885f0d485a20f17905b710c7de9a9dba99be9a0eb666cafb687dcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9ce4caccb885f0d485a20f17905b710c7de9a9dba99be9a0eb666cafb687dcc","first_computed_at":"2026-07-05T06:23:44.449171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:44.449171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h0TkylF5ZWBdAJ07kTaBgUBwve7AhUPfe6y6tOjgCbxFvrRh1+H2ykjDq/swYOOgefGg0/KexkxtiA5lFcB3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:44.449644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71adc2a978f12e006923da01bb6c2556fb4ebe108f310684233acdd80038caf0","sha256:8d2fbadf205a247c90b3740be8f862968faa12349bcfa26ce5ec0faf43f89107"],"state_sha256":"da61a05078721788fd1db15d51062d3e78b8d3c97346717ceeeeff365e9334f8"}