{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6CAEW4H5ZTG55ZYF5RNBKMSOI7","short_pith_number":"pith:6CAEW4H5","schema_version":"1.0","canonical_sha256":"f0804b70fdcccddee705ec5a15324e47dc96a73cb53b49e953a168ebc5fa3be5","source":{"kind":"arxiv","id":"2508.07863","version":1},"attestation_state":"computed","paper":{"title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Cao, Jing Liu, Lujie Xia, Qianshan Wei, Qin Jin, Sipeng Zheng, Ye Wang, Zongqing Lu","submitted_at":"2025-08-11T11:26:10Z","abstract_excerpt":"Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face significant limitations that hinder their practical deployment. We identify controllability as a main bottleneck, manifesting in five key aspects: inadequate response to diverse human commands, limited pose initialization capabilities, poor performance on long-term sequences, insufficient handling of unseen scenarios, and lack of fine-grained control over individual body parts. To overcome these limitations, we pres"},"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":"2508.07863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T11:26:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1f8c396d7adcb656108146c6c6db6f15a9ee70b365604f92e724b259f2a2040","abstract_canon_sha256":"24d798458217b82b65818084a58932c47f43c6fe8490d710a50eeeb314e3dee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:53.541628Z","signature_b64":"3TUZrvegTYIb6wa4tymKrye/qJqdHUA0gRnvcmh7zZfCxxoCarkWHxY3SW4fouTrPy8ioCDTnOgagZBg78T5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0804b70fdcccddee705ec5a15324e47dc96a73cb53b49e953a168ebc5fa3be5","last_reissued_at":"2026-07-05T11:51:53.541134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:53.541134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Cao, Jing Liu, Lujie Xia, Qianshan Wei, Qin Jin, Sipeng Zheng, Ye Wang, Zongqing Lu","submitted_at":"2025-08-11T11:26:10Z","abstract_excerpt":"Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face significant limitations that hinder their practical deployment. We identify controllability as a main bottleneck, manifesting in five key aspects: inadequate response to diverse human commands, limited pose initialization capabilities, poor performance on long-term sequences, insufficient handling of unseen scenarios, and lack of fine-grained control over individual body parts. To overcome these limitations, we pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07863","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/2508.07863/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":"2508.07863","created_at":"2026-07-05T11:51:53.541192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07863v1","created_at":"2026-07-05T11:51:53.541192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07863","created_at":"2026-07-05T11:51:53.541192+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CAEW4H5ZTG5","created_at":"2026-07-05T11:51:53.541192+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CAEW4H5ZTG55ZYF","created_at":"2026-07-05T11:51:53.541192+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CAEW4H5","created_at":"2026-07-05T11:51:53.541192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7","json":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7.json","graph_json":"https://pith.science/api/pith-number/6CAEW4H5ZTG55ZYF5RNBKMSOI7/graph.json","events_json":"https://pith.science/api/pith-number/6CAEW4H5ZTG55ZYF5RNBKMSOI7/events.json","paper":"https://pith.science/paper/6CAEW4H5"},"agent_actions":{"view_html":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7","download_json":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7.json","view_paper":"https://pith.science/paper/6CAEW4H5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07863&json=true","fetch_graph":"https://pith.science/api/pith-number/6CAEW4H5ZTG55ZYF5RNBKMSOI7/graph.json","fetch_events":"https://pith.science/api/pith-number/6CAEW4H5ZTG55ZYF5RNBKMSOI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7/action/storage_attestation","attest_author":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7/action/author_attestation","sign_citation":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7/action/citation_signature","submit_replication":"https://pith.science/pith/6CAEW4H5ZTG55ZYF5RNBKMSOI7/action/replication_record"}},"created_at":"2026-07-05T11:51:53.541192+00:00","updated_at":"2026-07-05T11:51:53.541192+00:00"}