{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S7LANI5XA27B7VV33EBPDVLBYV","short_pith_number":"pith:S7LANI5X","schema_version":"1.0","canonical_sha256":"97d606a3b706be1fd6bbd902f1d561c5751d9f16725c69086f9de7cfced1aad8","source":{"kind":"arxiv","id":"2312.10993","version":3},"attestation_state":"computed","paper":{"title":"Realistic Human Motion Generation with Cross-Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shaoli Huang, Xiu Li, Zeping Ren","submitted_at":"2023-12-18T07:44:40Z","abstract_excerpt":"We introduce the Cross Human Motion Diffusion Model (CrossDiff), a novel approach for generating high-quality human motion based on textual descriptions. Our method integrates 3D and 2D information using a shared transformer network within the training of the diffusion model, unifying motion noise into a single feature space. This enables cross-decoding of features into both 3D and 2D motion representations, regardless of their original dimension. The primary advantage of CrossDiff is its cross-diffusion mechanism, which allows the model to reverse either 2D or 3D noise into clean motion durin"},"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":"2312.10993","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-18T07:44:40Z","cross_cats_sorted":[],"title_canon_sha256":"994cf4613db8193f8045ac1f5f7ec7613042568e557bb4fc393aafbb13506563","abstract_canon_sha256":"9eb9302764e80b78f2de226b557514950f82804f589664cba85c036654535557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:45.290978Z","signature_b64":"YUe4eDc+HQIHFyV6r8BZhGazPHsaAa5+7yBLK2zjAzfl8t8aHupy+Ly8Uqrzpc9OLzFgP3PmrLK1th8mxXF8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d606a3b706be1fd6bbd902f1d561c5751d9f16725c69086f9de7cfced1aad8","last_reissued_at":"2026-07-05T08:51:45.290559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:45.290559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Realistic Human Motion Generation with Cross-Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shaoli Huang, Xiu Li, Zeping Ren","submitted_at":"2023-12-18T07:44:40Z","abstract_excerpt":"We introduce the Cross Human Motion Diffusion Model (CrossDiff), a novel approach for generating high-quality human motion based on textual descriptions. Our method integrates 3D and 2D information using a shared transformer network within the training of the diffusion model, unifying motion noise into a single feature space. This enables cross-decoding of features into both 3D and 2D motion representations, regardless of their original dimension. The primary advantage of CrossDiff is its cross-diffusion mechanism, which allows the model to reverse either 2D or 3D noise into clean motion durin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10993","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/2312.10993/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":"2312.10993","created_at":"2026-07-05T08:51:45.290614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10993v3","created_at":"2026-07-05T08:51:45.290614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10993","created_at":"2026-07-05T08:51:45.290614+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7LANI5XA27B","created_at":"2026-07-05T08:51:45.290614+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7LANI5XA27B7VV3","created_at":"2026-07-05T08:51:45.290614+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7LANI5X","created_at":"2026-07-05T08:51:45.290614+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/S7LANI5XA27B7VV33EBPDVLBYV","json":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV.json","graph_json":"https://pith.science/api/pith-number/S7LANI5XA27B7VV33EBPDVLBYV/graph.json","events_json":"https://pith.science/api/pith-number/S7LANI5XA27B7VV33EBPDVLBYV/events.json","paper":"https://pith.science/paper/S7LANI5X"},"agent_actions":{"view_html":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV","download_json":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV.json","view_paper":"https://pith.science/paper/S7LANI5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10993&json=true","fetch_graph":"https://pith.science/api/pith-number/S7LANI5XA27B7VV33EBPDVLBYV/graph.json","fetch_events":"https://pith.science/api/pith-number/S7LANI5XA27B7VV33EBPDVLBYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV/action/storage_attestation","attest_author":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV/action/author_attestation","sign_citation":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV/action/citation_signature","submit_replication":"https://pith.science/pith/S7LANI5XA27B7VV33EBPDVLBYV/action/replication_record"}},"created_at":"2026-07-05T08:51:45.290614+00:00","updated_at":"2026-07-05T08:51:45.290614+00:00"}