{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5XI654B2EF5WXHQXQEMCLYPFT4","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":"054b51a9a21224db65448e74c28c17bf21b9417de7fed39dc8eacfb1506d2eba","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T11:35:04Z","title_canon_sha256":"f98584ac1e5d661369e6d37a216b2f2e7f9d4c3d26bf14924a0cdd64aecb945e"},"schema_version":"1.0","source":{"id":"2602.22897","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.22897","created_at":"2026-07-03T01:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2602.22897v3","created_at":"2026-07-03T01:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22897","created_at":"2026-07-03T01:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"5XI654B2EF5W","created_at":"2026-07-03T01:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"5XI654B2EF5WXHQX","created_at":"2026-07-03T01:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"5XI654B2","created_at":"2026-07-03T01:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:08ca788153ce593672ae86456b59d6d45b89f94222638bc4cb5c34be57c82254","target":"graph","created_at":"2026-07-03T01:17:18Z","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/2602.22897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal interactions (e.g., vision-language), lacking the unified cognitive capabilities required for general AI assistants. To bridge this gap, we introduce OmniGAIA, a comprehensive benchmark designed to evaluate omni-modal agents on tasks necessitating deep reasoning and multi-turn tool execution across video, audio, and image modalities. Constructed via a novel","authors_text":"Guanting Dong, Hao Wang, Haoxuan Li, Jiajie Jin, Jiarui Jin, Ji-Rong Wen, Shijian Wang, Wenxiang Jiao, Xiaoxi Li, Yinuo Wang, Yuan Lu, Zhicheng Dou, Zhouchen Lin","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T11:35:04Z","title":"OmniGAIA: Towards Native Omni-Modal AI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22897","kind":"arxiv","version":3},"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:f2554b419653b25994b0535984b954988d8582f00622e791d08707541fabfad9","target":"record","created_at":"2026-07-03T01:17:18Z","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":"054b51a9a21224db65448e74c28c17bf21b9417de7fed39dc8eacfb1506d2eba","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T11:35:04Z","title_canon_sha256":"f98584ac1e5d661369e6d37a216b2f2e7f9d4c3d26bf14924a0cdd64aecb945e"},"schema_version":"1.0","source":{"id":"2602.22897","kind":"arxiv","version":3}},"canonical_sha256":"edd1eef03a217b6b9e17811825e1e59f36f4aed372d9b66ac9e1379da577aa23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd1eef03a217b6b9e17811825e1e59f36f4aed372d9b66ac9e1379da577aa23","first_computed_at":"2026-07-03T01:17:18.012889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:18.012889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EN2Oopjz+E7Vxus8jo8NTe1rb6cisY+Sls1xJoqeRJpBIdjSybjz2PWm+Tc4Vj9H50OdU1GzzSXRVo1DEgIZCw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:18.013380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.22897","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2554b419653b25994b0535984b954988d8582f00622e791d08707541fabfad9","sha256:08ca788153ce593672ae86456b59d6d45b89f94222638bc4cb5c34be57c82254"],"state_sha256":"8d52f1e0c4b34535942f3f63afca6bae62f4625c7dab99fa3e4aba5534706aa1"}