{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WALQQLTTMS32TDVZBVXWSASQ4M","short_pith_number":"pith:WALQQLTT","schema_version":"1.0","canonical_sha256":"b017082e7364b7a98eb90d6f690250e3158717277422206c16294a28357355cb","source":{"kind":"arxiv","id":"2506.01934","version":1},"attestation_state":"computed","paper":{"title":"RoboEgo System Card: An Omnimodal Model with Native Full Duplexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aixin Sun, Naitong Yu, Xiang Li, Xin Jiang, Xuezhi Fang, Yequan Wang, Yiqun Yao","submitted_at":"2025-06-02T17:53:10Z","abstract_excerpt":"Humans naturally process real-world multimodal information in a full-duplex manner. In artificial intelligence, replicating this capability is essential for advancing model development and deployment, particularly in embodied contexts. The development of multimodal models faces two primary challenges: (1) effectively handling more than three modalities-such as vision, audio, and text; and (2) delivering full-duplex responses to rapidly evolving human instructions. To facilitate research on models that support both omnimodal processing and full duplexity, we present RoboEgo (alias: FLM-Ego), a "},"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":"2506.01934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-02T17:53:10Z","cross_cats_sorted":[],"title_canon_sha256":"e3b17145fccb5337f584696a2f58c0142575128ab40e07bf036d78c443930ad9","abstract_canon_sha256":"4f65fd91c8105f2cf390e256145345b527f5546483b671bc1dbcff108ecfbbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.606419Z","signature_b64":"NRkiert6b/xaE8BRDnPZzbLbGfDnfoUGceKHP99Hz8uSseUtIG7jXbcCS5fee6A+5HxWaKS2CSDU+ofBignzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b017082e7364b7a98eb90d6f690250e3158717277422206c16294a28357355cb","last_reissued_at":"2026-07-05T11:14:21.605870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.605870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboEgo System Card: An Omnimodal Model with Native Full Duplexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aixin Sun, Naitong Yu, Xiang Li, Xin Jiang, Xuezhi Fang, Yequan Wang, Yiqun Yao","submitted_at":"2025-06-02T17:53:10Z","abstract_excerpt":"Humans naturally process real-world multimodal information in a full-duplex manner. In artificial intelligence, replicating this capability is essential for advancing model development and deployment, particularly in embodied contexts. The development of multimodal models faces two primary challenges: (1) effectively handling more than three modalities-such as vision, audio, and text; and (2) delivering full-duplex responses to rapidly evolving human instructions. To facilitate research on models that support both omnimodal processing and full duplexity, we present RoboEgo (alias: FLM-Ego), a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01934","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/2506.01934/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":"2506.01934","created_at":"2026-07-05T11:14:21.605933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01934v1","created_at":"2026-07-05T11:14:21.605933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01934","created_at":"2026-07-05T11:14:21.605933+00:00"},{"alias_kind":"pith_short_12","alias_value":"WALQQLTTMS32","created_at":"2026-07-05T11:14:21.605933+00:00"},{"alias_kind":"pith_short_16","alias_value":"WALQQLTTMS32TDVZ","created_at":"2026-07-05T11:14:21.605933+00:00"},{"alias_kind":"pith_short_8","alias_value":"WALQQLTT","created_at":"2026-07-05T11:14:21.605933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02605","citing_title":"Do Audio-Visual Large Language Models Really See and Hear?","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M","json":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M.json","graph_json":"https://pith.science/api/pith-number/WALQQLTTMS32TDVZBVXWSASQ4M/graph.json","events_json":"https://pith.science/api/pith-number/WALQQLTTMS32TDVZBVXWSASQ4M/events.json","paper":"https://pith.science/paper/WALQQLTT"},"agent_actions":{"view_html":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M","download_json":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M.json","view_paper":"https://pith.science/paper/WALQQLTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01934&json=true","fetch_graph":"https://pith.science/api/pith-number/WALQQLTTMS32TDVZBVXWSASQ4M/graph.json","fetch_events":"https://pith.science/api/pith-number/WALQQLTTMS32TDVZBVXWSASQ4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M/action/storage_attestation","attest_author":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M/action/author_attestation","sign_citation":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M/action/citation_signature","submit_replication":"https://pith.science/pith/WALQQLTTMS32TDVZBVXWSASQ4M/action/replication_record"}},"created_at":"2026-07-05T11:14:21.605933+00:00","updated_at":"2026-07-05T11:14:21.605933+00:00"}