{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6CAEW4H5ZTG55ZYF5RNBKMSOI7","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":"24d798458217b82b65818084a58932c47f43c6fe8490d710a50eeeb314e3dee1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T11:26:10Z","title_canon_sha256":"f1f8c396d7adcb656108146c6c6db6f15a9ee70b365604f92e724b259f2a2040"},"schema_version":"1.0","source":{"id":"2508.07863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07863","created_at":"2026-07-05T11:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07863v1","created_at":"2026-07-05T11:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07863","created_at":"2026-07-05T11:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"6CAEW4H5ZTG5","created_at":"2026-07-05T11:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"6CAEW4H5ZTG55ZYF","created_at":"2026-07-05T11:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"6CAEW4H5","created_at":"2026-07-05T11:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:db083c05022c4fca375a47cc96b027385e41c235531f5865f1489d7882b6b115","target":"graph","created_at":"2026-07-05T11:51:53Z","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/2508.07863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Cao, Jing Liu, Lujie Xia, Qianshan Wei, Qin Jin, Sipeng Zheng, Ye Wang, Zongqing Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T11:26:10Z","title":"Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07863","kind":"arxiv","version":1},"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:fbbaa7aac91fda846bdc30ce344b7b5f7f2dc287b81a0ad62846342144a106f4","target":"record","created_at":"2026-07-05T11:51:53Z","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":"24d798458217b82b65818084a58932c47f43c6fe8490d710a50eeeb314e3dee1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T11:26:10Z","title_canon_sha256":"f1f8c396d7adcb656108146c6c6db6f15a9ee70b365604f92e724b259f2a2040"},"schema_version":"1.0","source":{"id":"2508.07863","kind":"arxiv","version":1}},"canonical_sha256":"f0804b70fdcccddee705ec5a15324e47dc96a73cb53b49e953a168ebc5fa3be5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0804b70fdcccddee705ec5a15324e47dc96a73cb53b49e953a168ebc5fa3be5","first_computed_at":"2026-07-05T11:51:53.541134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:53.541134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3TUZrvegTYIb6wa4tymKrye/qJqdHUA0gRnvcmh7zZfCxxoCarkWHxY3SW4fouTrPy8ioCDTnOgagZBg78T5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:53.541628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbbaa7aac91fda846bdc30ce344b7b5f7f2dc287b81a0ad62846342144a106f4","sha256:db083c05022c4fca375a47cc96b027385e41c235531f5865f1489d7882b6b115"],"state_sha256":"4ce6c0bd36bb7cabfdcecc8a4fb425f9c673ce3e9b960fa225ff564e1c3b04f5"}