{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJEBTNFVAZE3LJCPOF5PSVZC6W","short_pith_number":"pith:ZJEBTNFV","schema_version":"1.0","canonical_sha256":"ca4819b4b50649b5a44f717af95722f5a3ca2185c92fa962808a1f9d9366fe59","source":{"kind":"arxiv","id":"2412.14706","version":2},"attestation_state":"computed","paper":{"title":"EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hehe Fan, Jianrong Zhang, Yi Yang","submitted_at":"2024-12-19T10:19:43Z","abstract_excerpt":"Diffusion models, particularly latent diffusion models, have demonstrated remarkable success in text-driven human motion generation. However, it remains challenging for latent diffusion models to effectively compose multiple semantic concepts into a single, coherent motion sequence. To address this issue, we propose EnergyMoGen, which includes two spectrums of Energy-Based Models: (1) We interpret the diffusion model as a latent-aware energy-based model that generates motions by composing a set of diffusion models in latent space; (2) We introduce a semantic-aware energy model based on cross-a"},"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":"2412.14706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T10:19:43Z","cross_cats_sorted":[],"title_canon_sha256":"002404cd2b430a9778e6cc29a6890efbd9d54b942dd5aaee2bacd788d4a395b2","abstract_canon_sha256":"8e595c5820b7c4b6278cb96783d4070e0efb6066942bcfc1f6af215271685e2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:41.274141Z","signature_b64":"dgqn+g0YiTG38laATKJime9Q0+3Xs6VZTV9V7lGVLDQ5zMpWeCuemUEeFZVkXwfBB6Iv5Rac1PelTzKDocFbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4819b4b50649b5a44f717af95722f5a3ca2185c92fa962808a1f9d9366fe59","last_reissued_at":"2026-07-05T11:15:41.273644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:41.273644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hehe Fan, Jianrong Zhang, Yi Yang","submitted_at":"2024-12-19T10:19:43Z","abstract_excerpt":"Diffusion models, particularly latent diffusion models, have demonstrated remarkable success in text-driven human motion generation. However, it remains challenging for latent diffusion models to effectively compose multiple semantic concepts into a single, coherent motion sequence. To address this issue, we propose EnergyMoGen, which includes two spectrums of Energy-Based Models: (1) We interpret the diffusion model as a latent-aware energy-based model that generates motions by composing a set of diffusion models in latent space; (2) We introduce a semantic-aware energy model based on cross-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14706","kind":"arxiv","version":2},"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/2412.14706/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":"2412.14706","created_at":"2026-07-05T11:15:41.273709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14706v2","created_at":"2026-07-05T11:15:41.273709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14706","created_at":"2026-07-05T11:15:41.273709+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJEBTNFVAZE3","created_at":"2026-07-05T11:15:41.273709+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJEBTNFVAZE3LJCP","created_at":"2026-07-05T11:15:41.273709+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJEBTNFV","created_at":"2026-07-05T11:15:41.273709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W","json":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W.json","graph_json":"https://pith.science/api/pith-number/ZJEBTNFVAZE3LJCPOF5PSVZC6W/graph.json","events_json":"https://pith.science/api/pith-number/ZJEBTNFVAZE3LJCPOF5PSVZC6W/events.json","paper":"https://pith.science/paper/ZJEBTNFV"},"agent_actions":{"view_html":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W","download_json":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W.json","view_paper":"https://pith.science/paper/ZJEBTNFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14706&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJEBTNFVAZE3LJCPOF5PSVZC6W/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJEBTNFVAZE3LJCPOF5PSVZC6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W/action/storage_attestation","attest_author":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W/action/author_attestation","sign_citation":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W/action/citation_signature","submit_replication":"https://pith.science/pith/ZJEBTNFVAZE3LJCPOF5PSVZC6W/action/replication_record"}},"created_at":"2026-07-05T11:15:41.273709+00:00","updated_at":"2026-07-05T11:15:41.273709+00:00"}