{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JHLHYAUKK5ZWM6TLIMDCN3Q6Z5","short_pith_number":"pith:JHLHYAUK","schema_version":"1.0","canonical_sha256":"49d67c028a5773667a6b430626ee1ecf744bb8c0fc21f0f1956244e6cde857ae","source":{"kind":"arxiv","id":"2312.02772","version":3},"attestation_state":"computed","paper":{"title":"FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanchen Luo, Hongwen Zhang, Junran Peng, Wei Yao, Xu Shi, Yunlian Sun","submitted_at":"2023-12-05T14:01:43Z","abstract_excerpt":"Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, generating motions beyond the distribution of original datasets remains challenging, i.e., zero-shot generation. By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation. Specifically, we first parse previous vague textual annotations into fine-grained descriptions of different body parts by leveragi"},"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":"2312.02772","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T14:01:43Z","cross_cats_sorted":[],"title_canon_sha256":"b1c866f25311999f30af469e45967712771b4ee3bcd02c1ad5d01e7969d7d8f9","abstract_canon_sha256":"e14b817a57c18c97d61693cdce06195649ec169495611ac4756110758866621f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:49.106538Z","signature_b64":"a0sCzo3s++kEY2SiKSUTka4o3teV2wjZ9gsr69N6+wGgMPS2Tjm9oysugDbH+mdLbUKLdAbp75YbcN64xWnECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49d67c028a5773667a6b430626ee1ecf744bb8c0fc21f0f1956244e6cde857ae","last_reissued_at":"2026-07-05T09:44:49.106013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:49.106013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanchen Luo, Hongwen Zhang, Junran Peng, Wei Yao, Xu Shi, Yunlian Sun","submitted_at":"2023-12-05T14:01:43Z","abstract_excerpt":"Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, generating motions beyond the distribution of original datasets remains challenging, i.e., zero-shot generation. By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation. Specifically, we first parse previous vague textual annotations into fine-grained descriptions of different body parts by leveragi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02772","kind":"arxiv","version":3},"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/2312.02772/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":"2312.02772","created_at":"2026-07-05T09:44:49.106078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02772v3","created_at":"2026-07-05T09:44:49.106078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02772","created_at":"2026-07-05T09:44:49.106078+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHLHYAUKK5ZW","created_at":"2026-07-05T09:44:49.106078+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHLHYAUKK5ZWM6TL","created_at":"2026-07-05T09:44:49.106078+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHLHYAUK","created_at":"2026-07-05T09:44:49.106078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19377","citing_title":"Absolute Coordinates Make Motion Generation Easy","ref_index":85,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5","json":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5.json","graph_json":"https://pith.science/api/pith-number/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/graph.json","events_json":"https://pith.science/api/pith-number/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/events.json","paper":"https://pith.science/paper/JHLHYAUK"},"agent_actions":{"view_html":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5","download_json":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5.json","view_paper":"https://pith.science/paper/JHLHYAUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02772&json=true","fetch_graph":"https://pith.science/api/pith-number/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/graph.json","fetch_events":"https://pith.science/api/pith-number/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/action/storage_attestation","attest_author":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/action/author_attestation","sign_citation":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/action/citation_signature","submit_replication":"https://pith.science/pith/JHLHYAUKK5ZWM6TLIMDCN3Q6Z5/action/replication_record"}},"created_at":"2026-07-05T09:44:49.106078+00:00","updated_at":"2026-07-05T09:44:49.106078+00:00"}