{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEIMMZLIF2K5R2BD45JAQNLTPH","short_pith_number":"pith:YEIMMZLI","schema_version":"1.0","canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","source":{"kind":"arxiv","id":"2411.18654","version":1},"attestation_state":"computed","paper":{"title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Han, Huan Liao, Ronghui Li, Xiangzuo Wu, Xiu Li, Yachao Zhang, Zhongyuan Hu, Zunnan Xu","submitted_at":"2024-11-27T05:32:18Z","abstract_excerpt":"Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges due to the complex relationship between textual prompts and desired motion outcomes. To address this, we introduce AToM, a framework that enhances the alignment between generated motion and text prompts by leveraging reward from GPT-4Vision. AToM comprises three main stages: Firstly, we construct a dataset MotionPrefer that pairs three types of event-level t"},"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":"2411.18654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T05:32:18Z","cross_cats_sorted":[],"title_canon_sha256":"6da9b69f6ada3ccdafc50e7d21d8fec530f83b66b156c11c6b3d264a40b6f288","abstract_canon_sha256":"ce5528bcb452b90afd7af6d41b9ab3643a39b9d677d8d8f301642aaad0b67b56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:48.792653Z","signature_b64":"Lku7Bz1Hj+yCbNUT2GgN/GAIhdUDv0asmdzArX5d8YWWE7cyGl14Id+LfK0J/ayeoivCJELSwf4Cm+rMuJMLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","last_reissued_at":"2026-07-05T09:41:48.792232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:48.792232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Han, Huan Liao, Ronghui Li, Xiangzuo Wu, Xiu Li, Yachao Zhang, Zhongyuan Hu, Zunnan Xu","submitted_at":"2024-11-27T05:32:18Z","abstract_excerpt":"Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with event-level textual descriptions presents unique challenges due to the complex relationship between textual prompts and desired motion outcomes. To address this, we introduce AToM, a framework that enhances the alignment between generated motion and text prompts by leveraging reward from GPT-4Vision. AToM comprises three main stages: Firstly, we construct a dataset MotionPrefer that pairs three types of event-level t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18654","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/2411.18654/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":"2411.18654","created_at":"2026-07-05T09:41:48.792293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18654v1","created_at":"2026-07-05T09:41:48.792293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18654","created_at":"2026-07-05T09:41:48.792293+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEIMMZLIF2K5","created_at":"2026-07-05T09:41:48.792293+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEIMMZLIF2K5R2BD","created_at":"2026-07-05T09:41:48.792293+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEIMMZLI","created_at":"2026-07-05T09:41:48.792293+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/YEIMMZLIF2K5R2BD45JAQNLTPH","json":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH.json","graph_json":"https://pith.science/api/pith-number/YEIMMZLIF2K5R2BD45JAQNLTPH/graph.json","events_json":"https://pith.science/api/pith-number/YEIMMZLIF2K5R2BD45JAQNLTPH/events.json","paper":"https://pith.science/paper/YEIMMZLI"},"agent_actions":{"view_html":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH","download_json":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH.json","view_paper":"https://pith.science/paper/YEIMMZLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18654&json=true","fetch_graph":"https://pith.science/api/pith-number/YEIMMZLIF2K5R2BD45JAQNLTPH/graph.json","fetch_events":"https://pith.science/api/pith-number/YEIMMZLIF2K5R2BD45JAQNLTPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/action/storage_attestation","attest_author":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/action/author_attestation","sign_citation":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/action/citation_signature","submit_replication":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/action/replication_record"}},"created_at":"2026-07-05T09:41:48.792293+00:00","updated_at":"2026-07-05T09:41:48.792293+00:00"}