{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7WUPLCDMYM5ZU5S2ON3WN6EMTZ","short_pith_number":"pith:7WUPLCDM","schema_version":"1.0","canonical_sha256":"fda8f5886cc33b9a765a737766f88c9e5d7d6341c259d3c55eaa8b17776dcf87","source":{"kind":"arxiv","id":"2311.14580","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Enze Xie, Ping Luo, Weikai Kong, Yuanfeng Ji, Zhengguo Li, Zhengying Liu","submitted_at":"2023-11-24T16:12:05Z","abstract_excerpt":"With the advancements in Large Language Models (LLMs), Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. However, existing evaluation benchmarks, primarily relying on rigid, hand-crafted datasets to measure task-specific performance, face significant limitations in assessing the alignment of these increasingly anthropomorphic models with human intelligence. In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient aligners, measuring the alignme"},"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":"2311.14580","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T16:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"9b08e16bfb9810aa1a7015bbd6add796ce10a2c9852e5d9bba58e298723d4ea9","abstract_canon_sha256":"c15134c6c0d1732f2975ed35977e13e7cdd717125fc8784835060f205d70ad57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:20.946336Z","signature_b64":"mI3SiaalpbXP/1noYeAapKaiYtb/TWUROpJITZOcq3A3M7WvUBAcUQ35B2+ojJA4BG9iGDt4zqj9+THSKMhXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda8f5886cc33b9a765a737766f88c9e5d7d6341c259d3c55eaa8b17776dcf87","last_reissued_at":"2026-07-05T07:16:20.945814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:20.945814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Automated Aligners for benchmarking Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongjian Ge, Enze Xie, Ping Luo, Weikai Kong, Yuanfeng Ji, Zhengguo Li, Zhengying Liu","submitted_at":"2023-11-24T16:12:05Z","abstract_excerpt":"With the advancements in Large Language Models (LLMs), Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. However, existing evaluation benchmarks, primarily relying on rigid, hand-crafted datasets to measure task-specific performance, face significant limitations in assessing the alignment of these increasingly anthropomorphic models with human intelligence. In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient aligners, measuring the alignme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14580","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/2311.14580/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":"2311.14580","created_at":"2026-07-05T07:16:20.945873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14580v1","created_at":"2026-07-05T07:16:20.945873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14580","created_at":"2026-07-05T07:16:20.945873+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WUPLCDMYM5Z","created_at":"2026-07-05T07:16:20.945873+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WUPLCDMYM5ZU5S2","created_at":"2026-07-05T07:16:20.945873+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WUPLCDM","created_at":"2026-07-05T07:16:20.945873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11716","citing_title":"SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ","json":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ.json","graph_json":"https://pith.science/api/pith-number/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/graph.json","events_json":"https://pith.science/api/pith-number/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/events.json","paper":"https://pith.science/paper/7WUPLCDM"},"agent_actions":{"view_html":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ","download_json":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ.json","view_paper":"https://pith.science/paper/7WUPLCDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14580&json=true","fetch_graph":"https://pith.science/api/pith-number/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/action/storage_attestation","attest_author":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/action/author_attestation","sign_citation":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/action/citation_signature","submit_replication":"https://pith.science/pith/7WUPLCDMYM5ZU5S2ON3WN6EMTZ/action/replication_record"}},"created_at":"2026-07-05T07:16:20.945873+00:00","updated_at":"2026-07-05T07:16:20.945873+00:00"}