{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B4BCIR2IUEOVRP3LZ7DKBQBHFI","short_pith_number":"pith:B4BCIR2I","schema_version":"1.0","canonical_sha256":"0f02244748a11d58bf6bcfc6a0c0272a16ec8ef81ee191824b342387b76deaf3","source":{"kind":"arxiv","id":"2104.05670","version":2},"attestation_state":"computed","paper":{"title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, Mathis Petrovich, Michael J. Black","submitted_at":"2021-04-12T17:40:27Z","abstract_excerpt":"We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architectu"},"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":"2104.05670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T17:40:27Z","cross_cats_sorted":[],"title_canon_sha256":"9f22046a7ff9e8d57065b509ff8e74d99a7e73cab385242329680e91d5670daf","abstract_canon_sha256":"125d881e9e313793399e5f110ba43a1d8e9c26aaace16f8959b5e7f0497de591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:32.997326Z","signature_b64":"tewMV/5bijIIi6Q8l3G62PQslFwZvzCApb6fRbZdyKy968jyz/Tzr8/Zag4FvxLSeyQalTidQOrbnOQeauvUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f02244748a11d58bf6bcfc6a0c0272a16ec8ef81ee191824b342387b76deaf3","last_reissued_at":"2026-07-05T03:15:32.996901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:32.996901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"G\\\"ul Varol, Mathis Petrovich, Michael J. Black","submitted_at":"2021-04-12T17:40:27Z","abstract_excerpt":"We tackle the problem of action-conditioned generation of realistic and diverse human motion sequences. In contrast to methods that complete, or extend, motion sequences, this task does not require an initial pose or sequence. Here we learn an action-aware latent representation for human motions by training a generative variational autoencoder (VAE). By sampling from this latent space and querying a certain duration through a series of positional encodings, we synthesize variable-length motion sequences conditioned on a categorical action. Specifically, we design a Transformer-based architectu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05670","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/2104.05670/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":"2104.05670","created_at":"2026-07-05T03:15:32.996959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05670v2","created_at":"2026-07-05T03:15:32.996959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05670","created_at":"2026-07-05T03:15:32.996959+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4BCIR2IUEOV","created_at":"2026-07-05T03:15:32.996959+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4BCIR2IUEOVRP3L","created_at":"2026-07-05T03:15:32.996959+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4BCIR2I","created_at":"2026-07-05T03:15:32.996959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10466","citing_title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI","json":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI.json","graph_json":"https://pith.science/api/pith-number/B4BCIR2IUEOVRP3LZ7DKBQBHFI/graph.json","events_json":"https://pith.science/api/pith-number/B4BCIR2IUEOVRP3LZ7DKBQBHFI/events.json","paper":"https://pith.science/paper/B4BCIR2I"},"agent_actions":{"view_html":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI","download_json":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI.json","view_paper":"https://pith.science/paper/B4BCIR2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05670&json=true","fetch_graph":"https://pith.science/api/pith-number/B4BCIR2IUEOVRP3LZ7DKBQBHFI/graph.json","fetch_events":"https://pith.science/api/pith-number/B4BCIR2IUEOVRP3LZ7DKBQBHFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI/action/storage_attestation","attest_author":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI/action/author_attestation","sign_citation":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI/action/citation_signature","submit_replication":"https://pith.science/pith/B4BCIR2IUEOVRP3LZ7DKBQBHFI/action/replication_record"}},"created_at":"2026-07-05T03:15:32.996959+00:00","updated_at":"2026-07-05T03:15:32.996959+00:00"}