{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:URXCUSNLRLHVHHQFL7B7SB522Z","short_pith_number":"pith:URXCUSNL","schema_version":"1.0","canonical_sha256":"a46e2a49ab8acf539e055fc3f907bad67c816155bd6cdcc6eb45357283d17276","source":{"kind":"arxiv","id":"2405.16273","version":5},"attestation_state":"computed","paper":{"title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chang, Mingshuang Luo, Ruibing Hou, Shiguang Shan, Yaowei Wang, Zhuo Li, Zimo Liu","submitted_at":"2024-05-25T15:21:59Z","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"},"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":"2405.16273","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-25T15:21:59Z","cross_cats_sorted":[],"title_canon_sha256":"0ef3997b6dd9a811308211ad2a3c8a02578f0980fd8fedda923afbec0938d30d","abstract_canon_sha256":"be355c8c2aa449ece3a4961f181cababae654a266d9de374d1b1a894044f9c9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:14.942081Z","signature_b64":"LtBgE/tSOYJU3U9mS5u2p+rdUu/7iL7mqCG4A/E3oMkTUa8BmGfYP8Uk9n5ggdK5tqZyF40eT4mfUlmtML/EAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a46e2a49ab8acf539e055fc3f907bad67c816155bd6cdcc6eb45357283d17276","last_reissued_at":"2026-07-05T09:30:14.941631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:14.941631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Chang, Mingshuang Luo, Ruibing Hou, Shiguang Shan, Yaowei Wang, Zhuo Li, Zimo Liu","submitted_at":"2024-05-25T15:21:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16273","kind":"arxiv","version":5},"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/2405.16273/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":"2405.16273","created_at":"2026-07-05T09:30:14.941689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16273v5","created_at":"2026-07-05T09:30:14.941689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16273","created_at":"2026-07-05T09:30:14.941689+00:00"},{"alias_kind":"pith_short_12","alias_value":"URXCUSNLRLHV","created_at":"2026-07-05T09:30:14.941689+00:00"},{"alias_kind":"pith_short_16","alias_value":"URXCUSNLRLHVHHQF","created_at":"2026-07-05T09:30:14.941689+00:00"},{"alias_kind":"pith_short_8","alias_value":"URXCUSNL","created_at":"2026-07-05T09:30:14.941689+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/URXCUSNLRLHVHHQFL7B7SB522Z","json":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z.json","graph_json":"https://pith.science/api/pith-number/URXCUSNLRLHVHHQFL7B7SB522Z/graph.json","events_json":"https://pith.science/api/pith-number/URXCUSNLRLHVHHQFL7B7SB522Z/events.json","paper":"https://pith.science/paper/URXCUSNL"},"agent_actions":{"view_html":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z","download_json":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z.json","view_paper":"https://pith.science/paper/URXCUSNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16273&json=true","fetch_graph":"https://pith.science/api/pith-number/URXCUSNLRLHVHHQFL7B7SB522Z/graph.json","fetch_events":"https://pith.science/api/pith-number/URXCUSNLRLHVHHQFL7B7SB522Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z/action/storage_attestation","attest_author":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z/action/author_attestation","sign_citation":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z/action/citation_signature","submit_replication":"https://pith.science/pith/URXCUSNLRLHVHHQFL7B7SB522Z/action/replication_record"}},"created_at":"2026-07-05T09:30:14.941689+00:00","updated_at":"2026-07-05T09:30:14.941689+00:00"}