{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U237FBZ6DJN4MHYCZMHMM2PGZ6","short_pith_number":"pith:U237FBZ6","schema_version":"1.0","canonical_sha256":"a6b7f2873e1a5bc61f02cb0ec669e6cf87ba78e8785af9ebed517c351b1ff362","source":{"kind":"arxiv","id":"2606.06462","version":1},"attestation_state":"computed","paper":{"title":"Benchmark Everything Everywhere All at Once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bokang Yang, Dongming Wu, Peiwen Sun, Shiyun Xiong, Wencheng Han, Xiangyu Yue, Xiao-Hui Li, Yuang Ai","submitted_at":"2026-06-04T17:52:04Z","abstract_excerpt":"Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their construction is labor-intensive and hard to reuse, raising concerns about sustainability and scalability. Moreover, existing benchmarks often quickly reach performance saturation after their release, resulting in insufficient discrimination among state-of-the-art models. To address these challenges, we introduce Benchmark Agent, a fully autonomous agentic system designed for benchmark building. Our framework orchestrates the complete benchmark co"},"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":"2606.06462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T17:52:04Z","cross_cats_sorted":[],"title_canon_sha256":"34ba87154d58e3ac713a98240c57bea8cd13b3ddc9782f8110213cbf7dc09dde","abstract_canon_sha256":"24877a7a1b8d93d7477a5167bde7a1bffff71650f754f1e09f4f2c7745958487"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:46.276071Z","signature_b64":"LLq+JB+VhSIhRz9hGjiNtoqZHibb1T0Nr/8SaeyQoWw/oygFMciGuMDN56jVDhwzhwC35AeGzjNbUXaxV+M2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6b7f2873e1a5bc61f02cb0ec669e6cf87ba78e8785af9ebed517c351b1ff362","last_reissued_at":"2026-06-05T01:15:46.275576Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:46.275576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmark Everything Everywhere All at Once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bokang Yang, Dongming Wu, Peiwen Sun, Shiyun Xiong, Wencheng Han, Xiangyu Yue, Xiao-Hui Li, Yuang Ai","submitted_at":"2026-06-04T17:52:04Z","abstract_excerpt":"Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their construction is labor-intensive and hard to reuse, raising concerns about sustainability and scalability. Moreover, existing benchmarks often quickly reach performance saturation after their release, resulting in insufficient discrimination among state-of-the-art models. To address these challenges, we introduce Benchmark Agent, a fully autonomous agentic system designed for benchmark building. Our framework orchestrates the complete benchmark co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06462","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/2606.06462/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":"2606.06462","created_at":"2026-06-05T01:15:46.275656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06462v1","created_at":"2026-06-05T01:15:46.275656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06462","created_at":"2026-06-05T01:15:46.275656+00:00"},{"alias_kind":"pith_short_12","alias_value":"U237FBZ6DJN4","created_at":"2026-06-05T01:15:46.275656+00:00"},{"alias_kind":"pith_short_16","alias_value":"U237FBZ6DJN4MHYC","created_at":"2026-06-05T01:15:46.275656+00:00"},{"alias_kind":"pith_short_8","alias_value":"U237FBZ6","created_at":"2026-06-05T01:15:46.275656+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/U237FBZ6DJN4MHYCZMHMM2PGZ6","json":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6.json","graph_json":"https://pith.science/api/pith-number/U237FBZ6DJN4MHYCZMHMM2PGZ6/graph.json","events_json":"https://pith.science/api/pith-number/U237FBZ6DJN4MHYCZMHMM2PGZ6/events.json","paper":"https://pith.science/paper/U237FBZ6"},"agent_actions":{"view_html":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6","download_json":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6.json","view_paper":"https://pith.science/paper/U237FBZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06462&json=true","fetch_graph":"https://pith.science/api/pith-number/U237FBZ6DJN4MHYCZMHMM2PGZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/U237FBZ6DJN4MHYCZMHMM2PGZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6/action/storage_attestation","attest_author":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6/action/author_attestation","sign_citation":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6/action/citation_signature","submit_replication":"https://pith.science/pith/U237FBZ6DJN4MHYCZMHMM2PGZ6/action/replication_record"}},"created_at":"2026-06-05T01:15:46.275656+00:00","updated_at":"2026-06-05T01:15:46.275656+00:00"}