{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:URXCUSNLRLHVHHQFL7B7SB522Z","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":"be355c8c2aa449ece3a4961f181cababae654a266d9de374d1b1a894044f9c9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T15:21:59Z","title_canon_sha256":"0ef3997b6dd9a811308211ad2a3c8a02578f0980fd8fedda923afbec0938d30d"},"schema_version":"1.0","source":{"id":"2405.16273","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16273","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16273v5","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16273","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"URXCUSNLRLHV","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"URXCUSNLRLHVHHQF","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"URXCUSNL","created_at":"2026-07-05T09:30:14Z"}],"graph_snapshots":[{"event_id":"sha256:6f2d5f9e5c4c1783d52381abac4e4cb7b7b5d93e6540580d58495edf956dc8d5","target":"graph","created_at":"2026-07-05T09:30:14Z","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/2405.16273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents M$^3$GPT, an advanced $\\textbf{M}$ultimodal, $\\textbf{M}$ultitask framework for $\\textbf{M}$otion comprehension and generation. M$^3$GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy ci","authors_text":"Hong Chang, Mingshuang Luo, Ruibing Hou, Shiguang Shan, Yaowei Wang, Zhuo Li, Zimo Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T15:21:59Z","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16273","kind":"arxiv","version":5},"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":"sha256:125d7aeda84c087a4687b842faa9418a8e663424335e78400913340c02467736","target":"record","created_at":"2026-07-05T09:30:14Z","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":"be355c8c2aa449ece3a4961f181cababae654a266d9de374d1b1a894044f9c9a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T15:21:59Z","title_canon_sha256":"0ef3997b6dd9a811308211ad2a3c8a02578f0980fd8fedda923afbec0938d30d"},"schema_version":"1.0","source":{"id":"2405.16273","kind":"arxiv","version":5}},"canonical_sha256":"a46e2a49ab8acf539e055fc3f907bad67c816155bd6cdcc6eb45357283d17276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a46e2a49ab8acf539e055fc3f907bad67c816155bd6cdcc6eb45357283d17276","first_computed_at":"2026-07-05T09:30:14.941631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:14.941631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LtBgE/tSOYJU3U9mS5u2p+rdUu/7iL7mqCG4A/E3oMkTUa8BmGfYP8Uk9n5ggdK5tqZyF40eT4mfUlmtML/EAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:14.942081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16273","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:125d7aeda84c087a4687b842faa9418a8e663424335e78400913340c02467736","sha256:6f2d5f9e5c4c1783d52381abac4e4cb7b7b5d93e6540580d58495edf956dc8d5"],"state_sha256":"f7f43f70163f74a0a49cbe471980b376444f0333b346d37cc3938e87be9c4c73"}