{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MVORD6BQDDSTSDEL5TGPHUEEND","short_pith_number":"pith:MVORD6BQ","schema_version":"1.0","canonical_sha256":"655d11f83018e5390c8becccf3d08468e1101b289328832fd3fbf0da6b8d6740","source":{"kind":"arxiv","id":"2607.02542","version":1},"attestation_state":"computed","paper":{"title":"iFLYTEK-Embodied-Omni Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Chao Ji, Chi Liu, Diyuan Liu, Guanchen Lu, Jiajia Wu, Jia Pan, Jingfei Ni, Lin Gao, Mingxin Zhou, Qingshan Xu, Shiqi Zhang, Wenjie Xu, Xin Nie, Yuan Zhang, Zhiyuan Cheng","submitted_at":"2026-06-24T00:25:44Z","abstract_excerpt":"General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action wi"},"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":"2607.02542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T00:25:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"770f006feb6aa01d103300f372afc9b31ee4d1ee9077a00a859d09f8c309c183","abstract_canon_sha256":"dc5f58bdc484c1e25907dd0d1bb133f3516234ae46401cf7a08f9f226034ee40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:15:59.780308Z","signature_b64":"yMvkzbAO3eY1Zo+84262BGEp62rLFWZS6JnUxoJf5kqs6dMxkVh9UUCVGmiJjqJnDmICGo0zfkIphmX3Bo2CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"655d11f83018e5390c8becccf3d08468e1101b289328832fd3fbf0da6b8d6740","last_reissued_at":"2026-07-07T00:15:59.779544Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:15:59.779544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iFLYTEK-Embodied-Omni Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Chao Ji, Chi Liu, Diyuan Liu, Guanchen Lu, Jiajia Wu, Jia Pan, Jingfei Ni, Lin Gao, Mingxin Zhou, Qingshan Xu, Shiqi Zhang, Wenjie Xu, Xin Nie, Yuan Zhang, Zhiyuan Cheng","submitted_at":"2026-06-24T00:25:44Z","abstract_excerpt":"General-purpose embodied agents must understand multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-language reasoning, video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-Embodied-Omni, a unified multimodal foundation model that jointly models vision(videos and images), language, and action wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02542","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/2607.02542/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":"2607.02542","created_at":"2026-07-07T00:15:59.779659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02542v1","created_at":"2026-07-07T00:15:59.779659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02542","created_at":"2026-07-07T00:15:59.779659+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVORD6BQDDST","created_at":"2026-07-07T00:15:59.779659+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVORD6BQDDSTSDEL","created_at":"2026-07-07T00:15:59.779659+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVORD6BQ","created_at":"2026-07-07T00:15:59.779659+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/MVORD6BQDDSTSDEL5TGPHUEEND","json":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND.json","graph_json":"https://pith.science/api/pith-number/MVORD6BQDDSTSDEL5TGPHUEEND/graph.json","events_json":"https://pith.science/api/pith-number/MVORD6BQDDSTSDEL5TGPHUEEND/events.json","paper":"https://pith.science/paper/MVORD6BQ"},"agent_actions":{"view_html":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND","download_json":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND.json","view_paper":"https://pith.science/paper/MVORD6BQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02542&json=true","fetch_graph":"https://pith.science/api/pith-number/MVORD6BQDDSTSDEL5TGPHUEEND/graph.json","fetch_events":"https://pith.science/api/pith-number/MVORD6BQDDSTSDEL5TGPHUEEND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND/action/storage_attestation","attest_author":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND/action/author_attestation","sign_citation":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND/action/citation_signature","submit_replication":"https://pith.science/pith/MVORD6BQDDSTSDEL5TGPHUEEND/action/replication_record"}},"created_at":"2026-07-07T00:15:59.779659+00:00","updated_at":"2026-07-07T00:15:59.779659+00:00"}