{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LXKPD2BW4CRZZ23BS6QD2VVDBJ","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":"e77d61b745e53dee0588c2b87bbc56e48ed5bd689ea295ee62259e67a480f735","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T06:44:11Z","title_canon_sha256":"b57ff06f6136150a5bba4464f529878e4436a893662a252f45fc4a04f1a2ded5"},"schema_version":"1.0","source":{"id":"2402.07116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07116","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07116v2","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07116","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"LXKPD2BW4CRZ","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"LXKPD2BW4CRZZ23B","created_at":"2026-07-05T08:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"LXKPD2BW","created_at":"2026-07-05T08:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:0b7c08e9467ee405993f3736192e2414f5ed8e6ed67ac8449d0f23d3bd58ddb4","target":"graph","created_at":"2026-07-05T08:54:07Z","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/2402.07116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text description","authors_text":"Erli Zhang, Guangtao Zhai, Haoning Wu, Weisi Lin, Zicheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T06:44:11Z","title":"Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07116","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":"sha256:876c9dc760e691206864117608615c0202cd0abe1cf3f292324a20d8f660c4c6","target":"record","created_at":"2026-07-05T08:54:07Z","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":"e77d61b745e53dee0588c2b87bbc56e48ed5bd689ea295ee62259e67a480f735","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-11T06:44:11Z","title_canon_sha256":"b57ff06f6136150a5bba4464f529878e4436a893662a252f45fc4a04f1a2ded5"},"schema_version":"1.0","source":{"id":"2402.07116","kind":"arxiv","version":2}},"canonical_sha256":"5dd4f1e836e0a39ceb6197a03d56a30a7054e0c789f39139e6acc1f6017b3c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dd4f1e836e0a39ceb6197a03d56a30a7054e0c789f39139e6acc1f6017b3c3c","first_computed_at":"2026-07-05T08:54:07.083925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:07.083925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89d8t6eh+C9cVP62p1UOdCMQMH7eObE0KppW8zlBHQeJdgvfurYvd0CNMlH1JLnEMgKRr37qghfFvZDMlZdVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:07.084322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:876c9dc760e691206864117608615c0202cd0abe1cf3f292324a20d8f660c4c6","sha256:0b7c08e9467ee405993f3736192e2414f5ed8e6ed67ac8449d0f23d3bd58ddb4"],"state_sha256":"50e1d3d3999f994d5bdff643a6a99cd7ff3eefc253abb6d0941b33cd522da9b0"}