{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FQZ7EEIKY3LC3VFFDERBHP4PRF","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":"c390bd8dd034259da5be4b3549665e8d2ee037130613e235959bbe7a74feaa6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:57:50Z","title_canon_sha256":"ed740f3f7da9d994aab793e7a9bcc4250a84ed4c6dd343119301b9279d935375"},"schema_version":"1.0","source":{"id":"2502.12084","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12084","created_at":"2026-07-05T11:30:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12084v4","created_at":"2026-07-05T11:30:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12084","created_at":"2026-07-05T11:30:41Z"},{"alias_kind":"pith_short_12","alias_value":"FQZ7EEIKY3LC","created_at":"2026-07-05T11:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"FQZ7EEIKY3LC3VFF","created_at":"2026-07-05T11:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"FQZ7EEIK","created_at":"2026-07-05T11:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:3b444021165ef03b142d4195e2d4364fce8fbb48c239f7d32b170b230c8c9e82","target":"graph","created_at":"2026-07-05T11:30:41Z","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/2502.12084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visually linking matching cues is a crucial ability in daily life, such as identifying the same person in multiple photos based on their cues, even without knowing who they are. Despite the extensive knowledge that vision-language models (VLMs) possess, it remains largely unexplored whether they are capable of performing this fundamental task. To address this, we introduce \\textbf{VLM2-Bench}, a benchmark designed to assess whether VLMs can Visually Link Matching cues, with 9 subtasks and over 3,000 test cases. Comprehensive evaluation across twelve VLMs, along with further analysis of various","authors_text":"Dongyu Yao, Jianshu Zhang, Paul Pu Liang, Renjie Pi, Yi R. Fung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:57:50Z","title":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12084","kind":"arxiv","version":4},"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:dc02eda45c5f2d16342b9e15fbc0cb0f35c57a84c17459aa6cf1ad1782a4ecda","target":"record","created_at":"2026-07-05T11:30:41Z","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":"c390bd8dd034259da5be4b3549665e8d2ee037130613e235959bbe7a74feaa6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T17:57:50Z","title_canon_sha256":"ed740f3f7da9d994aab793e7a9bcc4250a84ed4c6dd343119301b9279d935375"},"schema_version":"1.0","source":{"id":"2502.12084","kind":"arxiv","version":4}},"canonical_sha256":"2c33f2110ac6d62dd4a5192213bf8f89581c80a7629271913f6d9cc67a4f1d83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c33f2110ac6d62dd4a5192213bf8f89581c80a7629271913f6d9cc67a4f1d83","first_computed_at":"2026-07-05T11:30:41.579735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:41.579735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCuPaUhj6eDNBoUTYAk8qNo1uuM7kzKcpGgk3QxE9ynPt/+/VGo74Jh2ZKF9y1hiVDSl/bsLCLUvscYFmYxGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:41.580296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12084","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc02eda45c5f2d16342b9e15fbc0cb0f35c57a84c17459aa6cf1ad1782a4ecda","sha256:3b444021165ef03b142d4195e2d4364fce8fbb48c239f7d32b170b230c8c9e82"],"state_sha256":"0ce62bb43c91d9ceeb7abc37efb9e71f2af9a585381f1e7203ed3ffa3184e5d4"}