{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RPMPDK2RZNDKKK34CR65TTUMH3","short_pith_number":"pith:RPMPDK2R","schema_version":"1.0","canonical_sha256":"8bd8f1ab51cb46a52b7c147dd9ce8c3ef1cb47eba0ccf0c49753f60f959fc1b3","source":{"kind":"arxiv","id":"2104.00351","version":2},"attestation_state":"computed","paper":{"title":"TrajeVAE: Controllable Human Motion Generation from Trajectories","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kacper Kania, Marek Kowalski, Tomasz Trzci\\'nski","submitted_at":"2021-04-01T09:12:48Z","abstract_excerpt":"The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists. Current machine learning approaches can semi-automate the process, however, they are limited in a significant way: they can handle only a single trajectory of the expected motion that precludes fine-grained control over the output. To mitigate that issue, we reformulate the problem of future pose prediction into pose completion in space and time where multiple trajectories are represented as poses with missing joints. We show that such a frame"},"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":"2104.00351","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T09:12:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3edfcd2644cb85719f89ce3374f9ff6962d43f81bcf9e7b0348ef5fd251b545","abstract_canon_sha256":"23ee93cc0641ce3d97039213df38d4fe85a0a416e0ee6b72861f1a8f419bbe18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:56.400886Z","signature_b64":"IaLwilvhux61M4R53TOx2Jk5ZUFzua/+MUs20py1YYaWIzp+emuNzzrq//c/S2mNdUNC5DYSq+slhPlRXU8wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd8f1ab51cb46a52b7c147dd9ce8c3ef1cb47eba0ccf0c49753f60f959fc1b3","last_reissued_at":"2026-07-05T03:34:56.400537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:56.400537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrajeVAE: Controllable Human Motion Generation from Trajectories","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kacper Kania, Marek Kowalski, Tomasz Trzci\\'nski","submitted_at":"2021-04-01T09:12:48Z","abstract_excerpt":"The creation of plausible and controllable 3D human motion animations is a long-standing problem that requires a manual intervention of skilled artists. Current machine learning approaches can semi-automate the process, however, they are limited in a significant way: they can handle only a single trajectory of the expected motion that precludes fine-grained control over the output. To mitigate that issue, we reformulate the problem of future pose prediction into pose completion in space and time where multiple trajectories are represented as poses with missing joints. We show that such a frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00351","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/2104.00351/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":"2104.00351","created_at":"2026-07-05T03:34:56.400593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00351v2","created_at":"2026-07-05T03:34:56.400593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00351","created_at":"2026-07-05T03:34:56.400593+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPMPDK2RZNDK","created_at":"2026-07-05T03:34:56.400593+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPMPDK2RZNDKKK34","created_at":"2026-07-05T03:34:56.400593+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPMPDK2R","created_at":"2026-07-05T03:34:56.400593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05162","citing_title":"Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3","json":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3.json","graph_json":"https://pith.science/api/pith-number/RPMPDK2RZNDKKK34CR65TTUMH3/graph.json","events_json":"https://pith.science/api/pith-number/RPMPDK2RZNDKKK34CR65TTUMH3/events.json","paper":"https://pith.science/paper/RPMPDK2R"},"agent_actions":{"view_html":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3","download_json":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3.json","view_paper":"https://pith.science/paper/RPMPDK2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00351&json=true","fetch_graph":"https://pith.science/api/pith-number/RPMPDK2RZNDKKK34CR65TTUMH3/graph.json","fetch_events":"https://pith.science/api/pith-number/RPMPDK2RZNDKKK34CR65TTUMH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3/action/storage_attestation","attest_author":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3/action/author_attestation","sign_citation":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3/action/citation_signature","submit_replication":"https://pith.science/pith/RPMPDK2RZNDKKK34CR65TTUMH3/action/replication_record"}},"created_at":"2026-07-05T03:34:56.400593+00:00","updated_at":"2026-07-05T03:34:56.400593+00:00"}