{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:COFR6SFESUMGGCYAHJHJ2O2OAR","short_pith_number":"pith:COFR6SFE","schema_version":"1.0","canonical_sha256":"138b1f48a49518630b003a4e9d3b4e0460f76b32fdb7f3cffe90d6ce1dc206bd","source":{"kind":"arxiv","id":"2410.13754","version":2},"attestation_state":"computed","paper":{"title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.AI","authors_text":"Bo Li, David Junhao Zhang, Deepanway Ghosal, Fuzhao Xue, Jinjie Ni, Kabir Jain, Kaichen Zhang, Mahir Shah, Michael Shieh, Xiang Yue, Yang You, Yifan Song, Zian Zheng","submitted_at":"2024-10-17T16:52:28Z","abstract_excerpt":"Perceiving and generating diverse modalities are crucial for AI models to effectively learn from and engage with real-world signals, necessitating reliable evaluations for their development. We identify two major issues in current evaluations: (1) inconsistent standards, shaped by different communities with varying protocols and maturity levels; and (2) significant query, grading, and generalization biases. To address these, we introduce MixEval-X, the first any-to-any, real-world benchmark designed to optimize and standardize evaluations across diverse input and output modalities. We propose "},"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":"2410.13754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-17T16:52:28Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"fe5128b3b59c64c1465d608e338b23066afd4f6d21a1df40dad8193a89a936f7","abstract_canon_sha256":"db190a0f859657af6eb920af19bd42de2303ecd1845d315fadbb01011c1d33c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:24.337780Z","signature_b64":"1bBf9QilddEMWKMOfQKqgV/8mSWRABfKFhXB7HxR5xFDDlvebqzAnrpHQYsjfhSADq5spK5ywXqZN0hoFGKGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"138b1f48a49518630b003a4e9d3b4e0460f76b32fdb7f3cffe90d6ce1dc206bd","last_reissued_at":"2026-07-05T09:22:24.337190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:24.337190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.AI","authors_text":"Bo Li, David Junhao Zhang, Deepanway Ghosal, Fuzhao Xue, Jinjie Ni, Kabir Jain, Kaichen Zhang, Mahir Shah, Michael Shieh, Xiang Yue, Yang You, Yifan Song, Zian Zheng","submitted_at":"2024-10-17T16:52:28Z","abstract_excerpt":"Perceiving and generating diverse modalities are crucial for AI models to effectively learn from and engage with real-world signals, necessitating reliable evaluations for their development. We identify two major issues in current evaluations: (1) inconsistent standards, shaped by different communities with varying protocols and maturity levels; and (2) significant query, grading, and generalization biases. To address these, we introduce MixEval-X, the first any-to-any, real-world benchmark designed to optimize and standardize evaluations across diverse input and output modalities. We propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13754","kind":"arxiv","version":2},"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/2410.13754/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":"2410.13754","created_at":"2026-07-05T09:22:24.337259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13754v2","created_at":"2026-07-05T09:22:24.337259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13754","created_at":"2026-07-05T09:22:24.337259+00:00"},{"alias_kind":"pith_short_12","alias_value":"COFR6SFESUMG","created_at":"2026-07-05T09:22:24.337259+00:00"},{"alias_kind":"pith_short_16","alias_value":"COFR6SFESUMGGCYA","created_at":"2026-07-05T09:22:24.337259+00:00"},{"alias_kind":"pith_short_8","alias_value":"COFR6SFE","created_at":"2026-07-05T09:22:24.337259+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/COFR6SFESUMGGCYAHJHJ2O2OAR","json":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR.json","graph_json":"https://pith.science/api/pith-number/COFR6SFESUMGGCYAHJHJ2O2OAR/graph.json","events_json":"https://pith.science/api/pith-number/COFR6SFESUMGGCYAHJHJ2O2OAR/events.json","paper":"https://pith.science/paper/COFR6SFE"},"agent_actions":{"view_html":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR","download_json":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR.json","view_paper":"https://pith.science/paper/COFR6SFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13754&json=true","fetch_graph":"https://pith.science/api/pith-number/COFR6SFESUMGGCYAHJHJ2O2OAR/graph.json","fetch_events":"https://pith.science/api/pith-number/COFR6SFESUMGGCYAHJHJ2O2OAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR/action/storage_attestation","attest_author":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR/action/author_attestation","sign_citation":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR/action/citation_signature","submit_replication":"https://pith.science/pith/COFR6SFESUMGGCYAHJHJ2O2OAR/action/replication_record"}},"created_at":"2026-07-05T09:22:24.337259+00:00","updated_at":"2026-07-05T09:22:24.337259+00:00"}