{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LFEDNIFKLNKPWPM5UM22SRPFHW","short_pith_number":"pith:LFEDNIFK","schema_version":"1.0","canonical_sha256":"594836a0aa5b54fb3d9da335a945e53d8dcab74fb3aafeb6b23d579e386ec6c0","source":{"kind":"arxiv","id":"2408.00712","version":3},"attestation_state":"computed","paper":{"title":"MotionFix: Text-Driven 3D Human Motion Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Alp\\'ar Cseke, G\\\"ul Varol, Markos Diomataris, Michael J. Black, Nikos Athanasiou","submitted_at":"2024-08-01T16:58:50Z","abstract_excerpt":"The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. In this paper, we address both challenges. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text, introducing the new MotionFix dataset. Access to this data allows us to train "},"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":"2408.00712","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T16:58:50Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"61c4763f0a496120f3f2602cffc47aa12c978c1a04129e93f1aa6320bf48d997","abstract_canon_sha256":"9139f5ebcc000cc32bb1efe01ea6f3c1dfbc6a75126815da24b73828c79adf62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:25.667586Z","signature_b64":"GHpGhHwvKAnJSm5kJHEr5rrcGwHgVG4zMLGSO2O0ZcH0rlqz2DE2lPtUYyXF5CLmJNK7zTxbONCQLTAVdAj7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"594836a0aa5b54fb3d9da335a945e53d8dcab74fb3aafeb6b23d579e386ec6c0","last_reissued_at":"2026-07-05T09:39:25.667065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:25.667065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionFix: Text-Driven 3D Human Motion Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Alp\\'ar Cseke, G\\\"ul Varol, Markos Diomataris, Michael J. Black, Nikos Athanasiou","submitted_at":"2024-08-01T16:58:50Z","abstract_excerpt":"The focus of this paper is on 3D motion editing. Given a 3D human motion and a textual description of the desired modification, our goal is to generate an edited motion as described by the text. The key challenges include the scarcity of training data and the need to design a model that accurately edits the source motion. In this paper, we address both challenges. We propose a methodology to semi-automatically collect a dataset of triplets comprising (i) a source motion, (ii) a target motion, and (iii) an edit text, introducing the new MotionFix dataset. Access to this data allows us to train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00712","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/2408.00712/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":"2408.00712","created_at":"2026-07-05T09:39:25.667127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00712v3","created_at":"2026-07-05T09:39:25.667127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00712","created_at":"2026-07-05T09:39:25.667127+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFEDNIFKLNKP","created_at":"2026-07-05T09:39:25.667127+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFEDNIFKLNKPWPM5","created_at":"2026-07-05T09:39:25.667127+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFEDNIFK","created_at":"2026-07-05T09:39:25.667127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22726","citing_title":"Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10466","citing_title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW","json":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW.json","graph_json":"https://pith.science/api/pith-number/LFEDNIFKLNKPWPM5UM22SRPFHW/graph.json","events_json":"https://pith.science/api/pith-number/LFEDNIFKLNKPWPM5UM22SRPFHW/events.json","paper":"https://pith.science/paper/LFEDNIFK"},"agent_actions":{"view_html":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW","download_json":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW.json","view_paper":"https://pith.science/paper/LFEDNIFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00712&json=true","fetch_graph":"https://pith.science/api/pith-number/LFEDNIFKLNKPWPM5UM22SRPFHW/graph.json","fetch_events":"https://pith.science/api/pith-number/LFEDNIFKLNKPWPM5UM22SRPFHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW/action/storage_attestation","attest_author":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW/action/author_attestation","sign_citation":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW/action/citation_signature","submit_replication":"https://pith.science/pith/LFEDNIFKLNKPWPM5UM22SRPFHW/action/replication_record"}},"created_at":"2026-07-05T09:39:25.667127+00:00","updated_at":"2026-07-05T09:39:25.667127+00:00"}