{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YEIMMZLIF2K5R2BD45JAQNLTPH","short_pith_number":"pith:YEIMMZLI","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"},"canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","source":{"kind":"arxiv","id":"2411.18654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18654","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18654v1","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18654","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"YEIMMZLIF2K5","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"YEIMMZLIF2K5R2BD","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"YEIMMZLI","created_at":"2026-07-05T09:41:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YEIMMZLIF2K5R2BD45JAQNLTPH","target":"record","payload":{"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"},"canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","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"},"source_kind":"arxiv","source_id":"2411.18654","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0HbmOPEKq5EVJJcbqK3RXb3n40/NFgkkjNyqFbmGTbWYg98Ms8NS2MSJsK+tIvTVSnhX8v+YQZ49sOj37lbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:21:58.812737Z"},"content_sha256":"72f8af5711f58bc4d77c17209d28a30b86113c34ef27de6e23304ea74076ee7f","schema_version":"1.0","event_id":"sha256:72f8af5711f58bc4d77c17209d28a30b86113c34ef27de6e23304ea74076ee7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YEIMMZLIF2K5R2BD45JAQNLTPH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:41:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2JeDDwqbtSYpANixO3ZBqDhEDp1ClbbV/x3VHv/vZxfzXZubto0FfvVNGovn+hefIj88od+EhTVcN1aEbLXlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:21:58.813101Z"},"content_sha256":"fa9958d628b12114146df9de5042ce15c32c946d15db7c6fa58d248dd28b706f","schema_version":"1.0","event_id":"sha256:fa9958d628b12114146df9de5042ce15c32c946d15db7c6fa58d248dd28b706f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/bundle.json","state_url":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T10:21:58Z","links":{"resolver":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH","bundle":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/bundle.json","state":"https://pith.science/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEIMMZLIF2K5R2BD45JAQNLTPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEIMMZLIF2K5R2BD45JAQNLTPH","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":"ce5528bcb452b90afd7af6d41b9ab3643a39b9d677d8d8f301642aaad0b67b56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T05:32:18Z","title_canon_sha256":"6da9b69f6ada3ccdafc50e7d21d8fec530f83b66b156c11c6b3d264a40b6f288"},"schema_version":"1.0","source":{"id":"2411.18654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18654","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18654v1","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18654","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"YEIMMZLIF2K5","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"YEIMMZLIF2K5R2BD","created_at":"2026-07-05T09:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"YEIMMZLI","created_at":"2026-07-05T09:41:48Z"}],"graph_snapshots":[{"event_id":"sha256:fa9958d628b12114146df9de5042ce15c32c946d15db7c6fa58d248dd28b706f","target":"graph","created_at":"2026-07-05T09:41:48Z","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/2411.18654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haonan Han, Huan Liao, Ronghui Li, Xiangzuo Wu, Xiu Li, Yachao Zhang, Zhongyuan Hu, Zunnan Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T05:32:18Z","title":"AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18654","kind":"arxiv","version":1},"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":"sha256:72f8af5711f58bc4d77c17209d28a30b86113c34ef27de6e23304ea74076ee7f","target":"record","created_at":"2026-07-05T09:41:48Z","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":"ce5528bcb452b90afd7af6d41b9ab3643a39b9d677d8d8f301642aaad0b67b56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T05:32:18Z","title_canon_sha256":"6da9b69f6ada3ccdafc50e7d21d8fec530f83b66b156c11c6b3d264a40b6f288"},"schema_version":"1.0","source":{"id":"2411.18654","kind":"arxiv","version":1}},"canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c110c665682e95d8e823e75208357379cb75d810fcaf044da05ac5c012f7a290","first_computed_at":"2026-07-05T09:41:48.792232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:48.792232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lku7Bz1Hj+yCbNUT2GgN/GAIhdUDv0asmdzArX5d8YWWE7cyGl14Id+LfK0J/ayeoivCJELSwf4Cm+rMuJMLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:48.792653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72f8af5711f58bc4d77c17209d28a30b86113c34ef27de6e23304ea74076ee7f","sha256:fa9958d628b12114146df9de5042ce15c32c946d15db7c6fa58d248dd28b706f"],"state_sha256":"29d7030c6707ca0a020eff5c77d5369fb55c6535883d69f15d3514254835b753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFJdvMPJOG2JgxB1xZtBDfRYSBbY2APnzTA28jR/cSmrt8gD5+4hLCwen3kj3KcniLjmLkbpd+5guv4UVqnLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:21:58.815378Z","bundle_sha256":"9ce899872cbba0a03837dff164091847daf8361da521e64e4521631790406185"}}