{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5WTHO3ZKO4TKMRQDOHZN3DI7F6","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":"6494bf967bdd4c348afff49470bb3b19807c4ebcc925d164fda059868fc57253","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:17:15Z","title_canon_sha256":"4d39afebc64bf09c6837974f69fd83bd60be5c938eada048be6302eca57096af"},"schema_version":"1.0","source":{"id":"2505.21389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21389","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21389v1","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21389","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"5WTHO3ZKO4TK","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"5WTHO3ZKO4TKMRQD","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"5WTHO3ZK","created_at":"2026-07-05T11:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:c6811b37b133ace03b5e4717eabeacf567f67235684ebb89e997abed4510f16d","target":"graph","created_at":"2026-07-05T11:10:41Z","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/2505.21389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating multimodal large language models (MLLMs) is increasingly expensive, as the growing size and cross-modality complexity of benchmarks demand significant scoring efforts. To tackle with this difficulty, we introduce AutoJudger, an agent-driven framework for efficient and adaptive benchmarking of MLLMs that tackles this escalating cost. AutoJudger employs the Item Response Theory (IRT) to estimate the question difficulty and an autonomous evaluation agent to dynamically select the most informative test questions based on the model's real-time performance. Specifically, AutoJudger incorp","authors_text":"Chengjun Pan, Jiwen Zhang, Siyuan Wang, Xuanwen Ding, Zejun Li, Zhongyu Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:17:15Z","title":"AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21389","kind":"arxiv","version":1},"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":"sha256:1e07007cd7012a8314639c7eb0e0407394ee52d14d1bccdd1830313c9a44f3e3","target":"record","created_at":"2026-07-05T11:10:41Z","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":"6494bf967bdd4c348afff49470bb3b19807c4ebcc925d164fda059868fc57253","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T16:17:15Z","title_canon_sha256":"4d39afebc64bf09c6837974f69fd83bd60be5c938eada048be6302eca57096af"},"schema_version":"1.0","source":{"id":"2505.21389","kind":"arxiv","version":1}},"canonical_sha256":"eda6776f2a7726a6460371f2dd8d1f2fa733ea981fe31e43209b6641f5a5654a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eda6776f2a7726a6460371f2dd8d1f2fa733ea981fe31e43209b6641f5a5654a","first_computed_at":"2026-07-05T11:10:41.225169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:41.225169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cFoVkM82ewbgQreVM54reFoM+VUuQbosHUuuieeZ8QpD6lmkcp3x2vvQkIkEyMzHdSN3ERXpMCoynlNL75k0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:41.225652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e07007cd7012a8314639c7eb0e0407394ee52d14d1bccdd1830313c9a44f3e3","sha256:c6811b37b133ace03b5e4717eabeacf567f67235684ebb89e997abed4510f16d"],"state_sha256":"8d7eb7f6c0ccaf58a390f0c90268884838a16ebdcf806d915bb246315f40e89f"}