{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MI5JWDFNOUFJHQALLDUDGOGARI","short_pith_number":"pith:MI5JWDFN","schema_version":"1.0","canonical_sha256":"623a9b0cad750a93c00b58e83338c08a12d8fa0881066fab703b52b96cbd32fe","source":{"kind":"arxiv","id":"2311.16468","version":1},"attestation_state":"computed","paper":{"title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wang, Yu Wan, Zixiang Zhou","submitted_at":"2023-11-28T04:10:07Z","abstract_excerpt":"Large Language Models(LLMs) have shown remarkable emergent abilities in unifying almost all (if not every) NLP tasks. In the human motion-related realm, however, researchers still develop siloed models for each task. Inspired by InstuctGPT, and the generalist concept behind Gato, we introduce AvatarGPT, an All-in-One framework for motion understanding, planning, generations as well as other tasks such as motion in-between synthesis. AvatarGPT treats each task as one type of instruction fine-tuned on the shared LLM. All the tasks are seamlessly interconnected with language as the universal inte"},"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":"2311.16468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T04:10:07Z","cross_cats_sorted":[],"title_canon_sha256":"ae584085d68001eeb0fa7ad38ce46d33edb052e16dd08cdfb66dee60068244ac","abstract_canon_sha256":"a8af6ec76a50dece46c264e83a451745411280d898fa4ea0aebebc3505422860"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:42.235100Z","signature_b64":"Le4d/lsyIcDy3MnfQC+ymFQD27iUm+eTSy9BvNdRMgJOZpv5NJjXxMmex8uRLxK7kxkWCWKY+5fs+cCCS2K/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"623a9b0cad750a93c00b58e83338c08a12d8fa0881066fab703b52b96cbd32fe","last_reissued_at":"2026-07-05T07:17:42.234630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:42.234630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wang, Yu Wan, Zixiang Zhou","submitted_at":"2023-11-28T04:10:07Z","abstract_excerpt":"Large Language Models(LLMs) have shown remarkable emergent abilities in unifying almost all (if not every) NLP tasks. In the human motion-related realm, however, researchers still develop siloed models for each task. Inspired by InstuctGPT, and the generalist concept behind Gato, we introduce AvatarGPT, an All-in-One framework for motion understanding, planning, generations as well as other tasks such as motion in-between synthesis. AvatarGPT treats each task as one type of instruction fine-tuned on the shared LLM. All the tasks are seamlessly interconnected with language as the universal inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16468","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/2311.16468/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":"2311.16468","created_at":"2026-07-05T07:17:42.234682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16468v1","created_at":"2026-07-05T07:17:42.234682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16468","created_at":"2026-07-05T07:17:42.234682+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI5JWDFNOUFJ","created_at":"2026-07-05T07:17:42.234682+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI5JWDFNOUFJHQAL","created_at":"2026-07-05T07:17:42.234682+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI5JWDFN","created_at":"2026-07-05T07:17:42.234682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06590","citing_title":"MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI","json":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI.json","graph_json":"https://pith.science/api/pith-number/MI5JWDFNOUFJHQALLDUDGOGARI/graph.json","events_json":"https://pith.science/api/pith-number/MI5JWDFNOUFJHQALLDUDGOGARI/events.json","paper":"https://pith.science/paper/MI5JWDFN"},"agent_actions":{"view_html":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI","download_json":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI.json","view_paper":"https://pith.science/paper/MI5JWDFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16468&json=true","fetch_graph":"https://pith.science/api/pith-number/MI5JWDFNOUFJHQALLDUDGOGARI/graph.json","fetch_events":"https://pith.science/api/pith-number/MI5JWDFNOUFJHQALLDUDGOGARI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI/action/storage_attestation","attest_author":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI/action/author_attestation","sign_citation":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI/action/citation_signature","submit_replication":"https://pith.science/pith/MI5JWDFNOUFJHQALLDUDGOGARI/action/replication_record"}},"created_at":"2026-07-05T07:17:42.234682+00:00","updated_at":"2026-07-05T07:17:42.234682+00:00"}