{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5XI654B2EF5WXHQXQEMCLYPFT4","short_pith_number":"pith:5XI654B2","schema_version":"1.0","canonical_sha256":"edd1eef03a217b6b9e17811825e1e59f36f4aed372d9b66ac9e1379da577aa23","source":{"kind":"arxiv","id":"2602.22897","version":3},"attestation_state":"computed","paper":{"title":"OmniGAIA: Towards Native Omni-Modal AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.AI","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","submitted_at":"2026-02-26T11:35:04Z","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"},"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":"2602.22897","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T11:35:04Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"f98584ac1e5d661369e6d37a216b2f2e7f9d4c3d26bf14924a0cdd64aecb945e","abstract_canon_sha256":"054b51a9a21224db65448e74c28c17bf21b9417de7fed39dc8eacfb1506d2eba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:18.013380Z","signature_b64":"EN2Oopjz+E7Vxus8jo8NTe1rb6cisY+Sls1xJoqeRJpBIdjSybjz2PWm+Tc4Vj9H50OdU1GzzSXRVo1DEgIZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd1eef03a217b6b9e17811825e1e59f36f4aed372d9b66ac9e1379da577aa23","last_reissued_at":"2026-07-03T01:17:18.012889Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:18.012889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniGAIA: Towards Native Omni-Modal AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.AI","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","submitted_at":"2026-02-26T11:35:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22897","kind":"arxiv","version":3},"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/2602.22897/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":"2602.22897","created_at":"2026-07-03T01:17:18.012947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22897v3","created_at":"2026-07-03T01:17:18.012947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22897","created_at":"2026-07-03T01:17:18.012947+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XI654B2EF5W","created_at":"2026-07-03T01:17:18.012947+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XI654B2EF5WXHQX","created_at":"2026-07-03T01:17:18.012947+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XI654B2","created_at":"2026-07-03T01:17:18.012947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.27366","citing_title":"MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16909","citing_title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08762","citing_title":"Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14520","citing_title":"Chain of Modality: From Static Fusion to Dynamic Orchestration in Omni-MLLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15804","citing_title":"Qwen3.5-Omni Technical Report","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18292","citing_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4","json":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4.json","graph_json":"https://pith.science/api/pith-number/5XI654B2EF5WXHQXQEMCLYPFT4/graph.json","events_json":"https://pith.science/api/pith-number/5XI654B2EF5WXHQXQEMCLYPFT4/events.json","paper":"https://pith.science/paper/5XI654B2"},"agent_actions":{"view_html":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4","download_json":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4.json","view_paper":"https://pith.science/paper/5XI654B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22897&json=true","fetch_graph":"https://pith.science/api/pith-number/5XI654B2EF5WXHQXQEMCLYPFT4/graph.json","fetch_events":"https://pith.science/api/pith-number/5XI654B2EF5WXHQXQEMCLYPFT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4/action/storage_attestation","attest_author":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4/action/author_attestation","sign_citation":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4/action/citation_signature","submit_replication":"https://pith.science/pith/5XI654B2EF5WXHQXQEMCLYPFT4/action/replication_record"}},"created_at":"2026-07-03T01:17:18.012947+00:00","updated_at":"2026-07-03T01:17:18.012947+00:00"}