{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BAIFJLZ5DVIHVMUDEVYUVLQLXJ","short_pith_number":"pith:BAIFJLZ5","schema_version":"1.0","canonical_sha256":"081054af3d1d507ab28325714aae0bba648c8ac8ff94752aa884c03edc5930d6","source":{"kind":"arxiv","id":"2606.22437","version":1},"attestation_state":"computed","paper":{"title":"MMGist: A Comprehensive Multimodal Benchmark for 2027","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengping Zhao, Jiacheng Ruan, Ting Liu, Wenzhen Yuan, Wutao Xiong, Yuzhuo Fu","submitted_at":"2026-06-21T10:57:43Z","abstract_excerpt":"We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results. To this end, we propose MMGist, a curated benchmark that covers seven capability dimensions and contains 7,262 items. MMGist is constructed through a three-stage pipeline, which sequ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.22437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T10:57:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2055f26f858c52f28c2e02c70d32f9a705a01c926963a3c9b87e4e5130ae6005","abstract_canon_sha256":"ffe3fe31c5f6f05de35204a1d96e7c3fd5b505853406f9544293aa263e4629ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:38.421706Z","signature_b64":"MVK9jAetj9bkuT5BcrqJo8A+YSbEQqQ+h83R/o+lDVBon3p9U1IujrAvtuZwJLKG1w5uHqKMtbnLLuuvm4VjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081054af3d1d507ab28325714aae0bba648c8ac8ff94752aa884c03edc5930d6","last_reissued_at":"2026-06-23T02:13:38.421333Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:38.421333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMGist: A Comprehensive Multimodal Benchmark for 2027","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengping Zhao, Jiacheng Ruan, Ting Liu, Wenzhen Yuan, Wutao Xiong, Yuzhuo Fu","submitted_at":"2026-06-21T10:57:43Z","abstract_excerpt":"We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results. To this end, we propose MMGist, a curated benchmark that covers seven capability dimensions and contains 7,262 items. MMGist is constructed through a three-stage pipeline, which sequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22437","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.22437/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.22437","created_at":"2026-06-23T02:13:38.421396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22437v1","created_at":"2026-06-23T02:13:38.421396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22437","created_at":"2026-06-23T02:13:38.421396+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAIFJLZ5DVIH","created_at":"2026-06-23T02:13:38.421396+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAIFJLZ5DVIHVMUD","created_at":"2026-06-23T02:13:38.421396+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAIFJLZ5","created_at":"2026-06-23T02:13:38.421396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ","json":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ.json","graph_json":"https://pith.science/api/pith-number/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/graph.json","events_json":"https://pith.science/api/pith-number/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/events.json","paper":"https://pith.science/paper/BAIFJLZ5"},"agent_actions":{"view_html":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ","download_json":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ.json","view_paper":"https://pith.science/paper/BAIFJLZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22437&json=true","fetch_graph":"https://pith.science/api/pith-number/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/action/storage_attestation","attest_author":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/action/author_attestation","sign_citation":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/action/citation_signature","submit_replication":"https://pith.science/pith/BAIFJLZ5DVIHVMUDEVYUVLQLXJ/action/replication_record"}},"created_at":"2026-06-23T02:13:38.421396+00:00","updated_at":"2026-06-23T02:13:38.421396+00:00"}